ConnorGriffin

writing-for-agents

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable — plus a doctor verb that audits the loaded skill and CLAUDE.md/AGENTS.md estate.

Adversarially review a plan, work order, spec, or agent brief before anything gets built. Use when the user wants a plan reviewed, stress-tested, audited, or countersigned, says "plan review" or "poke holes in this plan", or wants a pre-build check on an issue/brief/PRD.

ui-craft

Lifecycle for user-facing surfaces — revise a shipped surface in the running app, lock a greenfield visual spec, build to a lock, critique/audit/polish a UI, or re-settle a locked term. Use for any request to design, review, or verify rendered UI (screens, dashboards, flows, components). Not for backend-only work or module/API design ("interface" in the code sense — use codebase-design for that).

wayfinder

Chart and resolve a large, foggy effort as a GitHub map of decision tickets, then hand clear independent subtrees to your implementation workflow as ordinary build issues. Use when an idea is too large or uncertain for one session, when the user invokes wayfinder or supplies a wayfinder map, or when planning must settle research, UI, domain, and scope decisions before implementation begins.

cbm-onboard

Register maintained or ephemeral Git checkouts with codebase-memory-mcp, keep long-lived indexes current through non-clobbering Git hooks, and tear down ephemeral indexes by exact deterministic identity. Use when asked to index, onboard, register, remove, or keep a repository current in Codebase Memory, or to resolve which Codebase Memory project belongs to a checkout and make it ready.

ci-design

Vocabulary and principles for well-designed CI. Use when the user wants to design, review, or audit CI, says CI is noisy, slow, or expensive, or is designing a workflow yml.

code-review

Review the changes since a fixed point (commit, branch, tag, PR, or merge-base) on two axes — Standards (does it follow this repo's documented rules?) and Spec (does it do what the originating issue asked?). Each axis returns a verdict per enumerated item rather than an open-ended list of findings, so a round terminates. Use when the user wants to review a branch, a PR, working-tree changes, or asks to "review since X"; and again after fixes, to review the fix.

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

domain-modeling

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

handoff

Produce a decision-safe handoff for a fresh agent. Use when a task changes hands, a session is ending midstream, a user asks for a handoff, or an agent needs to preserve a design/map/implementation decision without making the next agent rediscover it.

orchestrate

Flip the session into coordinator mode — the parent agent plans, scopes, reviews, and ships, but delegates all real work (exploration, implementation, review, fixes) to sub-agents routed by an empirically benchmarked model capability table. Use when the user invokes /orchestrate or asks the parent to act as an orchestrator/coordinator instead of a developer. Literal /orchestrate invocation requests the work order or task prompt plus only needed repository code and documentation for every mandatory worker dispatch, including nested review and nested Orchestrate work: to OpenAI's Codex model service for a Codex UI parent, or OpenAI's Codex model service or Anthropic's Claude model service for a Claude Code parent. Credentials, secrets, patient data, `.env`, and real database contents are excluded. Automatic activation outside an invoked parent workflow asks once before dispatch.

persona-review

Convene a small panel of persistent reviewer personas (curated colleague-likenesses plus invent-on-demand) to review a document cold, in character, then synthesize a panel verdict. Use when the user wants a document reviewed by a panel, wants named perspectives on a plan or design, or when another skill (e.g. plan-review) convenes a persona panel for a load-bearing review.

say-less

Shape every response for a reader who wants the answer first and nothing after it. Answer-first structure, numbered steps, domain language governed by a per-repo glossary of approved terms, one instruction per sentence, no preamble or recap. Invoke with /say-less for full shaping; /say-less distill drafts the current repo's glossary.

scope

Triage front door for work that isn't ready to build. Classifies the dominant uncertainty and routes to one specialist skill. Use for 'let's scope this', '/scope', 'scope this out', 'not sure how to approach', 'grill me on this', 'stress-test this plan', or any request carrying real ambiguity about what to do next.

preflight

Use when a plan, spec, work order, or process doc is drafted and about to enter review or execution — grounds its facts, spikes its first hour, and single-sources its rules so review rounds start deep instead of shallow.

drive-local-webapp

Launch or connect to a local development web server and drive it with a reusable headless-Chromium command interface. Use when asked to render, smoke-test, interact with, verify, or screenshot a local frontend or HTML mockup.

grilling

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

prototype

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

review

Front door for review of any kind — code, a plan, a document that needs named reviewer perspectives, or pending changes with a security question. Classifies the subject in front of it and routes to exactly one review skill; does no reviewing itself. Use for 'review this', '/review', or any request to review a PR, diff, plan, spec, brief, document, or security-sensitive change.

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Data & Documents Listed

research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a research worker.

spin-worktree

Create an isolated Git worktree for issue, pull-request, branch, or parallel agent work without editing the control checkout. Use when starting task work from fresh remote state, avoiding a dirty or shared checkout, or preparing a dedicated worktree for another agent.

openspec-adopt

Adopt OpenSpec in a repo that lacks it: scaffold the openspec/ layout, write baseline specs describing the system as it exists today (from code, docs, and git history), and deliver the whole thing as a documentation-only PR. One-time per repo. Trigger when the user asks to adopt openspec, add openspec to a repo, scaffold openspec, or write baseline specs. Invoked as /openspec-adopt <org/repo or path>.

ticket

Drive one tracked ticket from arrival to resolution through four verbs: triage, start, revise, finalize. Use when the user says triage/start/revise/finalize with a ticket id, asks to turn a ticket into a locked brief, to execute a work order, to action a review round on a ticket's pull request, or to close out a merged ticket. Literal triage, start, or revise invocation requests the work order or task prompt plus only needed repository code and documentation for every mandatory worker dispatch, including nested review and nested Orchestrate work: to OpenAI's Codex model service for a Codex UI parent, or OpenAI's Codex model service or Anthropic's Claude model service for a Claude Code parent. Credentials, secrets, patient data, `.env`, and real database contents are excluded. Automatic activation outside an invoked parent workflow asks once before dispatch; finalize grants no worker-egress consent.

pr-body

Write a pull-request body and score it before the PR is opened, or audit an existing PR's body against the same rubric. Use when about to run gh pr create, when a PR body needs writing or rewriting, or when asked whether a PR description is any good. Invoked as /pr-body write <body-file> or /pr-body audit <pr>.

epic

Maintain an epic ledger and work clear child tickets through a GitHub-backed planning lifecycle. Use when an effort needs multiple attended sessions, recorded decisions, spikes, or independently shippable builds.

clean

Clean the current branch's diff without changing behavior — naming, dead code, duplication, and the charter's deep-module rules — in one pass, then stop. Use when the user says "clean this diff", "/clean", "cleanup pass", or wants the branch tidied before review or hardening.

codebase-memory

Use the codebase knowledge graph for structural code queries, trace call paths and dependencies, inspect architecture, assess change impact, or activate the bundled Claude Code discovery hooks.