cody-hutson
UserA modular PMO & release-management platform for Claude Code: skills, governance disciplines, and a 13-stage release pipeline.
Categories
Indexed Skills (51)
adr-helper
Scaffolds an Architecture Decision Record (ADR-NNN.md) at a decision moment — allocates the next global-monotonic number across BOTH core/ADRs/ and release/ADRs/, stamps the derivable metadata (title stub, status Proposed, today's date, release slug, canonical Nygard section headers), and leaves every decision-prose section an author-fill placeholder. Scaffold-only: writes what is DERIVABLE, never the rationale that must be DECIDED (No-invention). Fires on an explicit request; a non-blocking passive offer may surface for an ADR-threshold decision but never auto-writes. Reads the ADR home DYNAMICALLY (never hardcoded). Immutable: allocates the next free number, never reuses or renumbers; supersession is a Status transition plus a new ADR. Consumes adr-authoring-guide.md + adr-schema.md; composes decision-discipline.md by reference. Triggers: "record this as an ADR", "scaffold an ADR", "create an ADR", "start an ADR", "write up this decision as an ADR", "adr-helper", "allocate the next ADR number".
context-budget-auditor
Measures token consumption across every loadable pmo-platform component in a Claude Code / Cowork session — the SKILL.md catalog, core/rules/, core/standards/schemas/specs/disciplines, agents, hooks, and the CLAUDE.md context-file chain — and reports total + per-component estimated token cost, a flagged-bloat section with the applied thresholds stated inline, and a K1/K2 load-vs-reference hint per component. Single Measure mode. Estimates are a heuristic, trend-over-time signal (not falsely-precise absolutes), and the skill roster is sourced live, never hardcoded. Read-and-report only — measures cost, changes nothing. Triggers: "audit the context budget", "measure token consumption", "how much context does the platform load", "what's the per-component token cost", "flag context bloat", "which components are bloated", "context budget report".
eval-writer
Authors rigorous eval suites for AI agents, skills, and LLM systems — grounded in the 2026 eval-writing consensus (trace-driven error analysis, binary LLM judges, cross-family validation, α/κ agreement). Produces characterization, failure taxonomies, judge prompts, rubrics, and calibration protocols that harnesses (pmo-skill-refiner, CI) then execute. Two modes — Author (write from scratch) and Review (audit against the framework). First-class playbooks for per-skill evals and for pipeline stage-gate judgment content; generic fallback for arbitrary AI systems. Use whenever the user asks to write evals, audit evals, add eval coverage, calibrate a judge, build a rubric, write a judge prompt, or diagnose why a judge keeps passing broken outputs.
pmo-qa-auditor
Reviews skill outputs against the principal contributor standard. Modes: Single-output review · Cross-output coherence · Evidence audit · Guardrail compliance · Platform health audit · Release-process fitness audit (dated process-audit artifact) · Dev testing (PR + release plan → Stage-7 quality report as PR comment) · Acceptance review (Stage-8 per-criterion AC verdicts) · As-built architecture-conformance audit (delivered-work drift + cross-release fragmentation). Evaluates rigor, accuracy, judgment, and operational value — not formatting. Triggers: "review this output", "audit this", "QA this", "check this against the standard", "is this ready to act on", "quality check this", "is this principal-contributor quality", "dev-test this PR", "run dev testing on PR", "run the DT ladder", "acceptance review this PR", "grade this against the issue AC", "run the release-process fitness audit", "fitness-audit the release pipeline", "as-built architecture-conformance audit."
pmo-skill-router
Suite router for the PMO role-Specialist suite — reads the core/ logical skill registry (core/skills/registry.md) and routes a role-shaped request to the correct role-Specialist by matching the query against each registry row's trigger surface. No hardcoded skill list; routing changes by editing the registry, never the router. Use when a role-shaped request needs to be routed to the right PMO role-Specialist, or "which role skill handles this".
prompt-builder
Builds and improves prompts of every kind — everyday Claude prompts, SKILL.md instruction bodies, skill descriptions, and agent/system prompts. Detects mode from input: critique-and-rewrite when the user pastes a draft, interview-and-build when the user describes a goal without a draft. Always does live web research on current Anthropic prompting guidance before producing output. Returns a short critique plus a copy/paste-ready prompt block. Use whenever the user asks for help writing, improving, rewriting, critiquing, sharpening, or scoping a prompt — including phrases like "help me write a prompt for…", "improve this prompt", "make this better", "what's wrong with this prompt", "rewrite this", "I need a system prompt for…", "draft a SKILL.md description for…", "write a prompt for", "sharpen this prompt", or whenever the user shares a block of text that is clearly an LLM prompt and asks for any kind of feedback or revision.
skill-compliance-auditor
Measures skill trigger-compliance — whether the RIGHT skill actually fires for the requests it should serve — across the pmo-platform skill catalog, closing the coverage gap upstream of output-quality and structural audits. It runs template-seeded scenarios at three strictness levels (explicit / neutral / competing), classifies each tool-call trace deterministic-first, and reports a per-strictness compliance rate. Single Measure mode, plus a read-only re-render variant. A mandatory cost governor makes every run operator-gated, scenario-capped, and --dry-run-first. Distinct from eval-writer (which authors eval suites), pmo-qa-auditor (which grades output quality), and gate-evaluation-spec (which measures gate-decision judgment). Triggers: "measure skill trigger-rate", "audit skill compliance", "does the right skill fire", "is this skill's description drifting", "run the trigger-compliance pass", "check skill firing rate", "skill compliance report".
system-specialist
{{SYSTEM_NAME}} Specialist — principal owner of the {{SYSTEM_NAME}} system. Learns {{SYSTEM_NAME}} from its supplied doc corpus, builds an internal model, and answers/acts as its principal owner — grounded only in the ingested corpus. Composes core/ function-skills per ADR-019 (invokes, never re-implements). Modes: Answer · Assess. Use when a question is about how {{SYSTEM_NAME}} works, what a change to it implies, or a decision that needs its principal owner's grounded judgment. Triggers: {{TRIGGER_SURFACE}}.
artifact-generator
Produces new or updated project artifacts — triggered by user request, PPM Agent gap detection, or phase gate requirements. Stages all output in _generated/ with metadata for user review before promotion. Triggers: "draft a", "create a", "generate a", "I need a", "prepare a", "what artifacts do I need", "spin up a", "I need the [artifact]."
artifact-lint
Scans a project's generated-artifact surface (08-Generated/ + promoted folders) and runs five graph-integrity checks — orphan, sibling duplicate, stale draft, displaced content, version chain — reading the horizontal-lineage frontmatter (parent_artifact / sibling_topic / supersedes) so duplicate, orphaned, stale, or displaced generated content is surfaced for operator approval instead of silently accumulating. Read-and-recommend only — no automatic file moves or deletes. Triggers: "lint the generated artifacts", "check 08-Generated for duplicates", "scan for orphaned artifacts", "find stale drafts", "run artifact lint", "are there duplicate generated artifacts", "check the artifact lineage graph", "version-chain check the generated folder."
comms-writer
The voice of the PMO — produces audience-calibrated, ready-to-send communications. Covers email, Teams, Confluence, exec briefs, meeting agendas, escalation drafts, recaps, and status updates. Use when drafting any stakeholder communication. Triggers: "draft an update for [audience]", "write the exec brief", "prepare the agenda", "send the escalation email", "write the recap", "put together a message", "write a Teams post."
daily-status
Generates Teams-ready AM and PM daily status updates from carry-forward trackers and recent transcripts. Uses the project's Daily Status Update Framework. Triggers: "generate the AM update", "daily status", "morning update", "afternoon update", "PM update", "EOD update", "prep the daily connect", "I just came out of testing — status post."
delivery-engine
Operational backbone for backlog health through release readiness. Modes: Backlog scan · Ticket insight · DoR gate · Sprint planning · Execution control · DoD gate · RAID updates. Use for sprint planning, backlog review, quality gates, or velocity tracking across Agile and Waterfall governance. Triggers: "run DoR on this", "run DoD on this", "check this backlog", "plan the sprint", "velocity check", "is this release ready", "update the RAID log."
file-router
Classifies, routes, and triggers processing for new files arriving in the PMO workspace. Uses three-layer classification (content analysis, project identification, filename patterns) with confidence thresholds. Triggers: "route this", "file this", "where does this go", "classify this", "I have a new transcript", "I just uploaded this", "what folder does this go in."
generated-cleanup
Scans a project's generated-artifact surface (08-Generated/ + promoted folders), groups retirement candidates into three groups (promoted-and-stale, approaching-timeout, superseded), and stages a cleanup proposal for unconditional operator approval before any archive action. Keys on the reconciled lifecycle fields (lifecycle_state / promotion_state / lifecycle_changed) plus a derived staleness signal and the artifact-lint report; never reads the deprecated single-field workflow machine. The archive action branches by promotion_state: a staged file is swept to _archived/ (archived-in-place); a promoted file is content-retired in place (no move). Recommend-only at Autonomy Tier 1 — nothing is moved or archived without approval; a scheduled run stages a proposal that never self-applies. Distinct from cleanup-orphan-state.sh (a state-file tool, never invoked here). Triggers: "clean up 08-Generated", "run generated cleanup", "archive stale generated artifacts", "what generated files can be retired".
health-check
Intent-driven project-state drift auditor. Audits a single project for drift between its tracked state and its canonical sources (MCP + local), then emits a categorized 5-section punch list — Confirmed / Auto-Actionable / Decisions / Unknowns / Rollup-Diffs — that is never auto-applied. Eight modes: full (total sweep), timeline (date/milestone drift), attribution (owner drift), comms (comms-coverage drift), plan (one named plan), raid (RAID-log drift), sources (canonical-source inventory), rollup (project↔portfolio rollup compose/refresh). Invokable interactively as /health-check and schedulable for file output. Triggers: "health check this project", "is this project's state still accurate", "run a drift check", "check for stale dates", "audit the timeline", "check ownership drift", "are comms overdue", "did this plan land", "audit the RAID log", "are our sources current", "roll up to portfolio", "refresh this project's rollup", "did anything drift since last cycle", "is the tracked state current."
pmo-business-analyst
Business Analyst Specialist — owns the HOW-it-works of delivery: requirements elicitation, process/workflow documentation, traceability, and gap analysis. Operates at the requirements tier: eliciting what the business needs, documenting how work flows, and proving the requirement traces from source to evidence. Composes pmo-process-designer (requirements definition, INVEST, Given-When-Then, process docs, traceability, gap analysis) + delivery-engine (backlog substrate, DoR readiness) — invokes them, never re-implements them. Modes: Requirements Elicitation · Workflow & Process Documentation · Traceability & Coverage · Gap Analysis. Use when the question is what the business needs elicited, how a process is documented, whether a requirement traces end-to-end, or where the coverage gap is. Triggers: "elicit the requirements", "document this process/workflow", "build the traceability matrix", "trace this requirement to Jira", "what's the gap", "map the as-is/to-be", "is this requirement complete".
pmo-knowledge-manager
Knowledge Manager Specialist — captures, structures, routes, and stewards project knowledge assets (lessons learned, runbooks, decision records, reference docs) so they land in their governed home, not as two disconnected generate-then-route steps. Composes artifact-generator (produces/stages the asset) + file-router (classifies + routes it to its governed home) — invokes them via the core/ registry skill-chain, never re-implements them (ADR-019). Modes: Capture · Structure/Steward · Route/File · Knowledge-Gap Audit. Use when you want the platform to act as the Knowledge Manager. Triggers: "act as knowledge manager", "capture this as a knowledge asset", "steward the knowledge base", "file this lesson learned", "build the runbook and file it", "where does this knowledge go", "what knowledge are we missing".
pmo-ocm-lead
Organizational Change Management (OCM) Lead Specialist — emulates an OCM Lead driving a go-live's organizational change end-to-end by composing the change-management function-skill across the full lifecycle. Composes change-management (impact · training · readiness · hypercare · adoption · comms) — invokes it through the core/ registry skill-chain, never re-implements it (ADR-019). Modes: Change Impact · Training & Adoption · Readiness Go/No-Go · Hypercare & Adoption Outcome · Change Comms Program. Use when the platform should act as the OCM lead, run or own the change program for a go-live, or drive organizational change as one coherent workflow. Triggers: "act as OCM lead", "run the change program", "own the change for this go-live", "drive organizational change", "lead the org change for this rollout", "manage the change end-to-end".
pmo-portfolio-manager
Portfolio Manager Specialist — synthesizes the cross-project health picture into portfolio-level calls. Operates at the portfolio tier above any single project, deciding which cross-project signal moves the portfolio posture and binding the roll-up's health verdicts to the portfolio's resource and capacity trade-offs. Composes ppm-agent (strategic triage + intake-governance) + weekly-status-rollup (cross-project roll-up + portfolio health write-back) — invokes them, never re-implements them. Modes: Portfolio Health Synthesis · Cross-Project Risk & Decision Triage · Portfolio Intake & Trade-off · SteerCo / Executive Readiness. Use when leadership needs the portfolio-altitude health, risk, intake, or SteerCo-readiness call across projects. Triggers: "what's the portfolio health", "what cross-project risk needs my attention", "triage the portfolio", "should the portfolio take this on", "score this new initiative", "prep the SteerCo", "portfolio summary for leadership".
pmo-process-designer
Converts business context into structured, traceable requirements and process documentation. Modes: Requirements definition · Workflow documentation · Gap analysis · Traceability matrix · Compliance mapping. Use when uploading business requirements, FDDs, or Jira exports. Triggers: "document this process", "build the requirements", "build the traceability matrix", "write the FRD", "trace from requirement to Jira", "what's the gap."
pmo-product-owner
Product Owner Specialist — owns the WHAT and the WHY of the backlog: value framing, prioritization, story authoring with acceptance criteria, and the accept/reject decision. Operates at the backlog tier, deciding which item is most valuable to build next and whether its value is accepted. Composes pmo-process-designer (story/requirement authoring, INVEST scoring, Given-When-Then acceptance criteria) + delivery-engine (backlog health, DoR readiness, sprint-scope fit) — invokes them, never re-implements them. Modes: Backlog Prioritization · Story Authoring & Acceptance · Backlog Readiness · Value & Scope Decision. Use when the question is what to build next, how to value-rank the backlog, whether a story's acceptance criteria are accepted, or whether to include / defer / cut scope by value. Triggers: "prioritize the backlog", "what's most valuable", "rank these stories", "is this ready to pull", "should we build or defer X", "write the story and acceptance criteria for [value]", "accept this story".
pmo-program-coordinator
Program Coordinator Specialist — keeps a program's operational trackers and status cadence coherent. Operates at the project tier across the program's workstreams, reconciling tracker state against the status cadence so nothing falls through the daily rhythm. Composes tracker-manager (tracker writes) + daily-status (AM/PM/Connect cadence) — invokes them, never re-implements them. Modes: Cadence Sync · Tracker Reconciliation. Use when the program's trackers and status updates need to be kept in lockstep. Triggers: "keep the trackers and status in sync", "reconcile the trackers before the update", "run the cadence sync", "did anything drop between the tracker and the status", "coordinate the program's daily rhythm", "tracker-to-status coherence check".
pmo-program-manager
Program Manager Specialist — drives a program's multiple coordinated workstreams to outcomes, deciding which cross-project signal moves the delivery plan and binding the program's risk posture to its delivery decisions. Operates at the program tier above any single project's delivery and below portfolio strategy, across agile and waterfall governance. Composes ppm-agent (strategic synthesis + intake-governance) + delivery-engine (backlog→release-readiness mechanics) — invokes them, never re-implements them. Modes: Cross-Project Risk & Dependency Synthesis · Program Delivery Posture · Program Release-Readiness · Program Intake & Capacity Trade-off · Program RAID & Decision Stewardship. Use when one program's multi-workstream delivery needs a risk read, a posture call, a go/no-go, an intake trade-off, or RAID stewardship. Triggers: "program-level risk to delivery", "is this program ready to release", "across these workstreams", "program go/no-go", "cross-project dependency", "how's the program tracking".
pmo-project-manager
Project Manager Specialist — owns a single named project's delivery end-to-end at the single-project tier (not a program or portfolio): renders the project's go/no-go, owns its RAID, stewards its milestone. Composes delivery-engine only — invokes it across modes A/C/D/E/F/G, never re-implements it; the value-add is single-project delivery accountability plus cross-mode coherence within delivery-engine (a DoR gap conditioning the sprint plan, a DoD failure originating a RAID entry). Modes: Project Backlog & Readiness Health · Project Sprint Planning & Execution · Project Release-Readiness (DoD) · Project RAID & Decision Stewardship. Use when one named project needs its delivery owned. Triggers: "is this project ready to release", "run DoR/DoD on this project", "plan this project's sprint", "check this project's backlog", "update this project's RAID", "this project's go/no-go". Routes program / multi-workstream requests to pmo-program-manager; routes ceremony-facilitation requests to pmo-scrum-master.
pmo-release-train-engineer
Release Train Engineer Specialist (SAFe) — facilitates the Agile Release Train: PI-planning facilitation, cross-team program-increment dependency and risk management, and program-level flow/impediment escalation. SAFe-conditional — active only when the instance runs a SAFe delivery_approach; dormant (does not fire) under a non-SAFe delivery_approach. Composes delivery-engine (sprint/exec/RAID mechanics) + ppm-agent (strategic push-to-resolution) — invokes them, never re-implements them. Modes: PI-Planning Facilitation · ART Dependency & PI-Risk Management · Program-Flow & Impediment Escalation · ART Release-Readiness Synthesis. Triggers: "facilitate PI planning", "run the PI planning", "map the ART dependencies", "what's blocking the release train", "program increment risk", "ART impediment escalation", "is the ART ready for the PI release", "release train readiness".
pmo-scrum-master
Scrum Master Specialist — facilitates a single team's process and flow: sprint ceremonies, impediment removal, and team flow/velocity health. Owns team process, NOT delivery accountability — renders no go/no-go and owns no milestone. Composes delivery-engine only (its B/C/D/E/G facilitation slice; Mode F / DoD is deliberately omitted), never re-implements it; the value-add is facilitation framing on its signals (the team commits, the SM facilitates). Default-active under Scrum (the platform default). Modes: Sprint Facilitation & Planning · Impediment Removal · Ceremony Support · Team Flow & Velocity Health. Use when a single team needs its process facilitated. Triggers: "facilitate sprint planning", "remove this impediment", "the team is blocked", "run the retro", "facilitate the review", "team velocity/flow health", "set the sprint goal with the team". Routes go/no-go, DoD, and project/program delivery-status to pmo-project-manager / pmo-program-manager; routes PI/ART requests to pmo-release-train-engineer.
pmo-technical-analyst
Reviews technical artifacts with senior TPM judgment — surfaces risks not obvious from the document alone. Modes: FDD review · Integration risk · Architecture assessment · Dependency identification · Feasibility feedback. Use when uploading FDDs, integration specs, or architecture documents. Triggers: "review this FDD", "what are the technical risks", "check this integration design", "architecture review", "feasibility check", "what's missing from this spec."
pmo-technical-program-manager
Technical Program Manager Specialist — synthesizes program-level technical risk into delivery decisions. Operates at the program tier across concurrent projects, deciding which technical risk actually moves the delivery plan. Composes pmo-technical-analyst (technical review) + delivery-engine (delivery orchestration) — invokes them, never re-implements them. Modes: Technical-Delivery Risk · Release-Readiness Orchestration. Use when a program needs a technical risk read tied to its delivery posture. Triggers: "what's the technical risk to this program's delivery", "is this program technically ready to release", "tie the integration risk to the sprint plan", "should this go-live given the open technical risks", "program technical readiness", "TPM read on this delivery".
pmo-tier-1-support
First-line support Specialist — triages an incoming issue, resolves known/documented issues from runbooks and FAQs, and escalates anything out of first-line scope to pmo-tier-2-support with a structured Escalation Handoff Record. Owns no RCA — a novel problem is escalated, never root-caused inline. Composes artifact-generator (triage record + the EHR artifact) and hands genuinely-new intake to intake-desk — invokes them via the core/ registry skill-chain, never re-implements them (ADR-019). Modes: Triage · Resolve-Known · Escalate. Use when the question is a first-contact known-issue lookup or a triage. Triggers: "first-line support", "tier 1 support", "how do I…", "is this a known issue", "triage this issue", "what's the status of this issue", "is there a fix for this".
pmo-tier-2-support
Escalation/RCA support Specialist — consumes the pmo-tier-1-support Escalation Handoff Record, performs a structured root-cause analysis, drives the issue to resolution, and authors/updates a runbook so it becomes first-line-resolvable. Owns the RCA method (invokes core/disciplines/root-cause-analysis.md, never redefines it); composes artifact-generator (runbook + RCA record), routes via file-router / pmo-knowledge-manager (persist to the knowledge base), and intake-desk (tracked work items) — invokes them via the core/ registry skill-chain (ADR-019). Modes: RCA · Drive-to-Resolution · Runbook-Authorship. Use for an escalated or novel problem that needs a causal explanation. Triggers: "tier 2 support", "escalated issue", "root cause this", "RCA", "write a runbook for this", "why did this break", "this keeps happening — why".
pmo-wms-specialist
WMS Specialist — principal owner of the warehouse management system (WMS). Learns the WMS from its supplied doc corpus, builds an internal model, and answers/acts as its principal owner — grounded only in the ingested corpus. Composes artifact-generator and intake-desk per ADR-019 (invokes, never re-implements). Modes: Answer · Assess. Use when a question is about how the warehouse management system works, what a change to WMS configuration or a wave/allocation/replenishment flow implies, or a decision that needs the WMS principal owner's grounded judgment. Triggers: "wms question", "warehouse management system", "how does the WMS handle allocation", "wms wave / pick / putaway / replenishment behavior", "assess this change against the WMS", "what does the WMS corpus say about ...".
ppm-agent
The strategic brain of the PMO — reads any project artifact and pushes every actionable item toward resolution. Use when uploading transcripts, asking about project status, needing decisions framed, or requesting risk assessment. Triggers: "review this", "what's the state of [project]", "process this transcript", "triage this", "what needs my attention", "what actions came out of this", "what needs to surface."
project-initiator
Manages the full project lifecycle — scaffolding new projects and closing completed ones. Modes: Initiation (creates folder structure, populates PROJECT.md, updates PORTFOLIO.md) · Closure (finalizes trackers, produces closure summary, archives). Triggers: "new project", "start project", "kick off [project]", "close project", "archive project", "project closure", "wrap up [project]."
tracker-manager
Generic update engine for all operational trackers in 3-Operations/. Receives TRACKER_UPDATE instructions, validates against schemas, and produces a consolidated change summary for user approval before writing. Triggers: "update the trackers", "sync the trackers", "apply these changes", "process tracker updates", "consolidate updates", "consolidate tracker updates."
weekly-status-rollup
Generates a weekly executive status roll-up across all active projects. Covers project health, key risks, decisions made/pending, and upcoming milestones. Writes back updated health indicators to PORTFOLIO.md. Triggers: "weekly roll-up", "weekly status", "SteerCo prep", "SteerCo update", "executive status", "portfolio summary", "portfolio health", "cross-project status."
build-reviewer
Conducts final production-readiness review of any governed document pack — Copilot Builder Agent, PMO platform, or generic — using the shared review discipline (see `core/disciplines/review-discipline-principles.md`). Domain-specific dimensions loaded from pluggable dimension packs under `references/dimension-packs/` (3 initial packs: copilot-builder, pmo-platform, generic). Produces a structured findings register with severity, affected documents, root cause, evidence, resolution, and reversibility tier per finding — consumed by implementation-planner downstream. Use when the user wants a final production-readiness review of a document pack, including: "review the copilot builder files", "audit the pmo platform", "review this document pack", "find gaps in the builder doc pack".
implementation-planner
Converts build-reviewer findings registers into sequenced, minimal-change remediation implementation plans for any governed document pack — Copilot Builder Agent, PMO platform, or generic. Domain-specific planning context loaded from pluggable domain packs under `references/domain-packs/`. Applies the Minimal-Change Remediation Bias and classifies every confirmed finding to one of 8 remediation types (RT-1 text correction through RT-8 accepted residual). Produces implementation records (RI-NNN) as Edit-ready specs and Bash scripts directly consumable by Claude Code's native tools per the reference workflow in `release/references/how-to/implementation-execution-pattern.md`. Use when the user has a build-reviewer findings register ready for planning, needs remediation sequencing, or wants to plan the fixes before execution.
pipeline-triage
Runs Stage-2 Triage over the platform's improvement backlog — reads `status: proposed` GitHub Issues, executes the Phase-A analysis sequence (A1–A6.5: DoR completeness, duplicate/subsumption + similarity, dependency-state validation + native-dep mirror, feasibility, priority re-evaluation, oversize routing, per-issue summary, management-task signals), and produces ONE consolidated triage summary with a per-issue Approve/Defer/Reject recommendation. Auto-execute is the operative default: the A1–A6 enrichment runs end-to-end without per-action approval; only the state-mutating Close/Reject requires operator confirmation, and the Approve/Defer/Reject verdict itself stays operator-only (Tier 3). Reads the pipeline improvement backlog, not the Jira / project delivery backlog. Triggers: "triage the proposed queue", "run Stage-2 triage", "triage the improvement backlog", "run the triage analysis on the proposed issues", "what's the triage recommendation for the proposed backlog".
pmo-architect
System-scope Architect Specialist — cross-component, middleware, and data architecture; integration design and blast-radius assessment; system-level ADR authorship. Composes pmo-principal-engineer (within-component solution depth) and pmo-technical-analyst (technical review) — invokes each, re-implements neither. Modes: System-Design · Integration-Review. Use for system design across components, integration design, blast-radius assessment, cross-component architecture, or to write a system ADR. Triggers: "architecture review", "system design", "integration design", "blast-radius assessment", "cross-component design", "write a system ADR". Distinct from the solution-scope Principal Engineer (within-component depth).
pmo-devops-sre
DevOps/SRE Specialist — owns deploy mechanics + reliability/rollback triggers; composes `release-executor` — invokes it, never re-implements it. Executes the go/no-go the operator/Release-Manager already made; never makes the go/no-go itself. Modes: Pipeline · Deploy-Exec · Reliability. Use when a release needs its deploy run, its pipeline/rollout configured, or a reliability signal turned into a rollback proposal. Triggers: "configure the deploy pipeline", "run the deploy", "push the release through the pipeline", "set up the rollout", "we have a regression — trigger the rollback", "is the deploy healthy".
pmo-principal-engineer
Principal Engineer Specialist — solution-scope design depth at Stage 5. Decides the architecture for a within-component solution, governs its NFRs, adjudicates build-vs-buy, and authors the ADR when the decision is non-obvious. Composes pmo-technical-analyst (technical review) — invokes it, never re-implements it. Modes: Architecture & NFR Governance · Build-vs-Buy & Design Review. Use for solution-level design decisions distinct from system-scope architecture. Triggers: "design this solution", "what NFRs bind this design", "build-vs-buy for this component", "architecture decision for this solution", "is this design implementation-ready", "author the ADR for this decision".
pmo-qa-lead
QA Lead Specialist — composes pmo-qa-auditor + build-reviewer into program-level QA leadership. Owns the system-level test strategy, binds acceptance scope to delivery readiness, governs defect disposition, and gates dev-testing — invoking the composed reviewers, never re-implementing them. Modes: Strategy · Acceptance · Defect-Governance · Dev-Test. Use when a release needs a QA-leadership read rather than a single review pass. Triggers: "what's the test strategy for this release", "does this meet the acceptance criteria", "is this acceptable to ship", "govern the defects on this release", "how should we disposition these findings", "gate the dev-testing on this PR", "run the dev-test quality gate", "QA-lead read on this release".
pmo-release-manager
Release Manager Specialist — owns the release tail (go/no-go decision · deploy authorization · close-out); composes `release-planner` + `release-executor` — invokes them, never re-implements them. Makes the go/no-go the operator ratifies and sequences Stage 9 → 12 → 13; owns no standalone release mechanics. Modes: Go/No-Go Evidence · Deploy Execution · Close-out. Use when a release needs its tail driven end-to-end — the go/no-go evidence assembled, the deploy driven, or the release closed out. Triggers: "act as release manager", "run the release tail", "assemble the go/no-go evidence", "drive the deploy", "close out the release", "is this release ready to ship".
pmo-skill-editor
Edit, audit, and regression-test any skill in the PMO Agent Suite. Modes: Targeted edit · Full audit · Regression check · Remediation apply. Maintains skill definitions with full awareness of cross-skill contracts and architecture. Triggers: "edit this skill", "modify this skill", "change this skill", "check for regressions", "audit this skill", "apply these fixes", "what breaks if I change this."
pmo-skill-refiner-selftest-canary
Smoke test for the pmo-skill-refiner factory — produced via the refiner's Create-New workflow during an AC demonstration. Reports the count of skill directories currently present in `release/skills/` and flags any that are missing from the `deploy.sh` per-module skill arrays (`OPERATIONS_SKILLS` / `RELEASE_SKILLS` / `CORE_SKILLS` / `CANARY_SKILLS`). Report-only (no decision-class outputs, no recommendations, no actions). Permanent fixture per ADR-04 (Stage 5 design for ) — functions as an always-on smoke test that detects factory regressions. Use when the user wants to check skill-roster consistency ("check the skill roster", "count tracked skills", "audit skill deployment drift", "verify skills/ folder matches deploy.sh", "are all my skills deployed").
pmo-skill-refiner
Creates and refines PMO-platform skills by wrapping an Anthropic scaffolding skill (default: anthropic-skills:skill-creator) with a PMO refinement layer. Captures intent via Interview mode (methodology, failure modes, dependencies, reversibility, trigger evidence), delegates commodity scaffolding to the Anthropic skill, then injects PMO-platform fields into the produced SKILL.md (delivery_approach, output-contract stub, dependency-graph node, evidence- quality protocol, failure-mode discipline, Principal Standard checklist, reversibility declaration). Runs the preserved eval harness from skill-creator (variance analysis, description-trigger optimization, blind A/B comparison, cross-skill false-positive detection). For modifying EXISTING PMO skills, coordinates with pmo-skill-editor. Use when the user wants to create a new PMO skill or iterate on an existing skill's eval/description/trigger set.
pmo-software-engineer
Software Engineer Specialist — executes end-to-end Stage-6 Engineering; turns an approved implementation plan into executed change, verification, and a PR. Composes implementation-planner (RT-classification + Edit-ready spec generation from a findings register) — invokes it, never re-implements it. Mode: Development. Input is scoped to an executable plan / findings register; a bare ticket with no plan routes to planning first. Use when an approved plan or findings register is ready to build. Triggers: "implement this plan", "execute the remediation plan", "engineer this change", "run the Stage-6 build", "turn this plan into a PR".
session-retro
Runs a per-session self-retrospective at a session boundary — reflects on the session that just ended and emits SESSION-grained learnings as signal-only rows in the pipeline event log. Captures the class the decision-moment path structurally cannot: operator feedback arriving with NO recommendation on the table (an unprompted correction, a stated preference, a redirection, expressed friction), plus recurring session friction. Records an EXPLICIT no-learning row when a session produced nothing, so "ran and found nothing" is never confused with "never ran". Sensor, never actuator — a run makes zero toolkit changes, a cross-session cluster promotes to an improvement CANDIDATE through the governance gate, and the operator memory store is never written. Sampled, not fire-always. Triggers: "run the session retro", "retro this session", "session-retro", "what did this session teach us", "capture learnings from this session".
finops-usage-extractor
Extracts per-session and per-subagent agent token-spend from local Claude Code session data into the operator-local, git-ignored FinOps usage store (schema authority: core/schemas/finops-usage-store-schema.md). Exact message.usage counts are primary; the context-budget-auditor skill's ceil(words/0.75) heuristic is the fallback for usage-less records only. Read-only on the source transcripts — writes only the resolved store. It also attributes and rolls per-session spend up to its owning work item (milestone-grain reliable; unattributed fail-visible) with a coverage metric. Distinct from context-budget-auditor, which measures STATIC corpus footprint; this measures RUNTIME session spend. Use to populate or refresh token-usage data, or to attribute and roll it up, for FinOps reporting. Triggers: "extract token usage", "refresh the finops store", "how much token spend", "run the finops extractor", "roll up token usage", "attribute token spend", "which work item spent the tokens".
intake-desk
The conversational front door for intake — turns a half-formed idea into a well-formed, correctly-typed, correctly-placed work item logged to the work tracker, never a scratch file. Meets you at any altitude (a single bug or a portfolio initiative), proposes the work-item type and its place in the intake hierarchy, elicits the type- and level-appropriate fields (a bug's reproduction and environment; a story's acceptance criteria and value), applies the 5-test rule live, and confirms before logging. One work item per request (child candidates noted in the body for later slicing; no auto-decompose). Two interactive modes — Elicit (guided interview) and Triage-readiness check (5-test a draft you wrote) — plus Ambient Auto-Log (Mode C), a non- interactive path invoked programmatically, not by a conversational phrase. Use when the user says "help me file this idea as an issue", "turn this into a work item", "log this idea", "is this intake-ready", or "help me write up this bug/story/initiative".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.