yarlson
UserEngineering workflows and standards for Codex and Claude Code: plan, implement, test, review, and deliver repository changes.
Categories
Indexed Skills (44)
procedure-promote
Promote a repeated, verified Yarbrain procedure candidate into a user-owned Agent Skill or propose an update to an existing one. Use after the same procedure succeeds in independent episodes or when the user explicitly requests reusable automation; do not promote facts, policy, or unexplained workarounds.
wiki-capture
Convert a completed session or queued Yarbrain session locator into an immutable episode and reviewable knowledge or procedure candidates. Use after substantial work, before context loss, or when pending session records need extraction; never update canonical notes or active skills.
wiki-reconcile
Search, compare, and reconcile pending Yarbrain memory candidates with canonical semantic notes through reviewable patches. Use when processing inbox/memory candidates, resolving conflicting evidence, or applying an explicitly approved knowledge patch; do not capture sessions or promote procedures.
behavior-implement
Implement behavior through a red-green-refactor cycle when focused automated tests are proportionate. Use for product behavior changes and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants dedicated tests.
changes-report
Report all repository changes that entered a target branch during one required date or period, grouped by product change and written as plain English for a broad audience. Use for daily, weekly, date-range, or relative-period change summaries rather than explaining one known diff.
claude-review
Run an independent Claude Opus review of the complete current change against the repository's default branch, then verify its findings locally. Use after focused checks pass when you want a second model to review the change before further edits or delivery.
code-review
Orchestrate an adaptive multi-agent pull-request review that combines structural and semantic context, assigns risk-based reviewer prompts at runtime, deduplicates and verifies findings, and renders an evidence-backed review. Use when a pull request or local change needs independent review lanes, adversarial challenge, or GitHub-ready findings.
crap-index-assess
Assess method-level change risk with the Change Risk Anti-Patterns (CRAP) index and recommend focused testing or complexity reduction. Use when a repository configures CRAP measurement, cyclomatic complexity and automated test coverage data are available, or a user asks what CRAP means, how to calculate or interpret it, or how to reduce a CRAP score.
jira-issue-create
Create one or more Jira issues through acli from user-approved drafts using heading-based Context, Acceptance criteria, and Engineering notes sections. Use only when explicitly invoked to create Jira issues; use jira-issue-refine when requirements still need refinement.
jira-issue-deliver
Autonomously deliver one Jira issue from intake to a ready GitHub pull request. Use only when the user authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback.
jira-issue-refine
Refine one draft or existing Jira issue into a clear, evidence-backed, bounded delivery contract without implementing it. Use when creating or revising an issue before engineering handoff, especially when behavior, repository ownership, acceptance evidence, dependencies, risk, environment needs, or scope remain unclear.
plan-create
Create a final implementation-ready plan from a user brief, settled decisions, and repository evidence. Use when work needs ordered phases, concrete deliverables, dependencies, risks, and validation before coding.
slop-cop
Judge whether a pull request is reviewable by a human, covering title and description value, claims the diff contradicts, splittable scope, and filler content. Use before requesting, accepting, or merging review rather than for correctness defects or prose wording.
system-investigate
Investigate an underdefined product, codebase, architecture, integration, or operational question through read-only repository tracing, bounded runtime evidence, and current public research. Use when the user wants to validate suspected behavior, explain why it occurs, compare plausible designs, or recommend the smallest safe change before planning or implementation.
test-design
Design or write reproducible tests matched to behavioral risk before implementation. Use for product behavior and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants proportionate dedicated tests.
wiki-initialize
Create or adopt a user-controlled Yarbrain Markdown vault and configure lifecycle hooks to find it. Use when setting up Yarbrain, moving its vault, or repairing a missing vault structure; do not use for routine capture or maintenance.
wiki-maintain
Audit and conservatively maintain a configured Yarbrain vault for structural errors, stale knowledge, duplication, conflicts, unprocessed evidence, and skill drift. Use periodically or when recall quality declines; make deterministic checks first and require approval for semantic consolidation or archival.
wiki-recall
Retrieve a small, relevant set of current Yarbrain notes, episodes, and approved procedures for an upcoming task. Use before substantial debugging, design, planning, or repeated work where prior knowledge can change the approach; remain read-only.
alternatives-explore
Generate and evaluate genuinely different approaches to a product, workflow, or system problem. Use when the user explicitly wants a bold, contrarian, experimental, or non-incremental alternative and a testable recommendation.
architecture-refine
Refine underdefined product or system architecture through focused interactive decisions. Use when the user wants architecture sparring before a formal implementation plan or contract update.
changes-explain
Explain a pull request, commit range, branch, or local diff from a system-design perspective. Use for practical understanding of changed behavior, boundaries, flow, ownership, operations, risks, and verification rather than defect review.
ci-review
Audit CI workflow architecture and effectiveness without modifying it. Use when triggers, jobs, commands, quality gates, caches, artifacts, matrices, permissions, release paths, or deployment automation may be stale, redundant, unsafe, or unjustified.
cli-control
Verify terminal-hosted CLI or TUI behavior with repeatable local evidence. Use for output, prompts, interactive input, signals, hangs, resizing, startup, exit status, or terminal restoration.
coderabbit-triage
Triage unresolved CodeRabbit feedback on the current GitHub pull request. Use for read-only disposition and, only when separately authorized, scoped remediation and remote thread closure.
critical-journey-document
Create one concise evidence-linked product journey record for one actor pursuing one goal. Use when product behavior needs traceable ownership, acceptance, telemetry, or service-flow documentation for a current decision or delivery gate.
dependency-review
Review dependency provenance and reproducibility without modifying them. Use when manifests, lockfiles, vendor state, generated dependency state, registries, fetched tools, or version pins change.
docs-drift-review
Review documentation for drift caused by the current code or configuration change. Use to identify concrete inaccuracies and, when authorized, repair only directly affected documentation.
docs-review
Audit or improve general repository documentation against implemented behavior. Use for deliberate README or documentation-quality work not owned by a more specific documentation skill.
english-text-review
Review English technical prose without modifying it. Use for plain-English feedback on comments, docstrings, documentation, commit or pull request text, issues, reports, runbooks, logs, errors, command help, and other human-readable technical writing rather than factual or marketing review.
infra-review
Review infrastructure-as-code and rendered deployment configuration without modifying it. Use before plan, apply, or deploy when targeting, replacement, state, availability, cost, ordering, or recovery blast radius may change.
marketing-claims-review
Audit or, when authorized, rewrite persuasive product claims against shipped-product evidence. Use for landing pages, marketing-heavy READMEs, feature or pricing pages, comparisons, and calls to action.
phase-commit
Create one local commit for a completed, validated, and reviewed unit of work. Use only when the user explicitly requests a commit without pushing or other delivery actions.
phase-implement
Implement exactly one selected phase from an authoritative repository plan. Use when a named phase or equivalent scoped implementation unit must be completed without later-phase work.
phase-review
Review one validated phase for behavior-preserving structural regressions introduced or materially worsened by the change. Use after phase validation and before final delivery.
phase-validate
Validate exactly one implemented phase or scoped change against its authoritative contract. Use after implementation to re-derive criterion-level conclusions from current evidence and fix only required implementation gaps.
plan-update
Make the smallest evidence-backed correction to implementation-plan mechanics. Use when implementation or validation proves incorrect ordering, prerequisites, phase scope, dependencies, steps, or validation gates.
pr-draft
Publish confirmed local changes as a monitored GitHub draft pull request. Use only when the user authorizes branch creation, scoped staging, commit, push, draft PR creation, and CI follow-up.
repo-context-document
Create, update, or consolidate adopted current-state documentation under docs/context/. Use for durable implemented architecture, ownership, runtime, domain, flow, terminology, or engineering-practice context.
rollout-readiness-review
Review cross-cutting operational readiness after implementation and before deployment. Use when a concrete change may alter runtime prerequisites, failure visibility, deployment order, rollback, recovery, or production failure modes.
security-review
Review a focused trust-boundary or exploit-path change without modifying it. Use when work introduces or materially changes untrusted input, privilege decisions, secret flow, dangerous sinks, or agent and tool capabilities.
spec-update
Make a minimal evidence-backed update to a non-plan product, architecture, API, schema, or behavior contract. Use when implementation or validation cannot determine correctness from the current authoritative contract.
technical-spike
Resolve one correctness-blocking external or version-specific technical uncertainty through bounded investigation. Use when cheap local inspection cannot establish framework, library, tool, runtime, protocol, or platform behavior needed by the current task.
test-gap-review
Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.
ui-control
Verify graphical browser, desktop, or Electron behavior through the actual interface. Use when screenshot, accessibility, console, network, trace, or browser-driven evidence is required; exclude terminal-hosted interfaces.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.