Agent-Skills

Review and prune stale branches safely. Use when branch cleanup needs evidence, protected-branch caution, PR awareness, and non-destructive recommendations.

Analyze repo, tracker, PR, validation, session, and .harness evidence. Use when multi-stage Harness Engineering work needs safe resume routing.

Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans. Use when users ask for tightening, simplification, or lifecycle repair.

Create evidence-backed HE reframe migration programs. Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution.

Create or refresh evidence-bound Harness Engineering learning artifacts from verified solved problems. Use when a fix worked, a repeated failure should become durable knowledge, or .harness/solutions and Project Brain need maintenance.

Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness. Use when the work involves new services, significant service changes, multiple external dependencies, or high blast-radius failure scenarios.

Route ambiguous Harness Engineering requests to one lifecycle stage when users ask where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology.

Write Harness Engineering specs before planning. Use when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract.

Create bounded, evidence-backed Harness Engineering specs from approved intent. Use when a selected issue, milestone, reframe phase, or execution slice needs acceptance criteria, traceability, risk gates, and validation boundaries before planning or implementation.

Compress HE cognition artifacts into evidence-backed strategy. Use when intent, review, triage, ADR, core, or source-prompt comparison evidence needs durable direction.

Build behavior-safe code changes with TDD and RED/GREEN evidence. Use when he-plan or he-work requires TDD for a concrete behavior target.

Review diffs, PRs, specs, plans, or review-feedback items and return severity-ranked engineering findings with exact locations. Use when technical risks or feedback correctness must be verified before implementation.

Executes bounded implementation work from approved specs, plans, issues, or small fixes by editing files, running validation, preserving unrelated work, and recording rollback and handoff evidence. Use when asked to implement, execute a plan, apply changes, or build a scoped feature.

Implement approved Harness Engineering work. Use when a plan, todo list, or tiny spec needs traceable delivery and validation.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

Check if a repository or agent-facing product surface is ready for AI coding agents. Use when you need to audit repo agent compatibility, review AGENTS.md, find missing test/build commands, evaluate docs quality, assess tool/action parity, or produce a file-evidence scorecard with specific fixes.

Review code architecture, code quality, dependency graphs, coupling, technical debt, modularization, ownership, and test seams. Use when refactors, restructuring, tightly coupled code, or architecture decisions need proof-backed options.

Generate local Codex usage reports. Use when users ask for usage analytics, weekly insights, session summaries, telemetry patterns, or prompting help.

Analyze underspecified requests with a short decision interview. Use this skill when guessing would risk the wrong plan.