skills

Use when non-trivial software engineering or an engineering completion claim involves implementation, debugging, refactoring, migration, architecture, technical planning, code review, material assumptions, scope pressure, or unverified evidence. Skip for trivial mechanical edits and pure factual explanation.

Use only when the user explicitly invokes $agent-debate, or when a loaded workflow routes here, and same-topic shared material needs adversarial product tradeoffs, requirement convergence, scope pruning, or decision clarity. Do not use for lanes, returned-lane review, code review, or single-agent brainstorming.

Use only when the user explicitly invokes $agent-eval, or when an active workflow routes here, to convert locked Spec behavior into acceptance evidence, automated/manual checks, failure conditions, fixtures, risk coverage, and implementation evidence requirements before Plan.

Use when the user explicitly invokes $agent-improve or asks what is worth improving in a codebase or branch and wants a read-only ranked audit. Return source-backed findings and stop. Do not use to review a specific artifact or diff (agent-review), implement a known change (steady-coding), or deliver a chosen finding (dev-flow).

Use only when the user explicitly invokes $agent-plan, or when an active workflow routes here, to convert locked Spec and Eval into implementation tasks, coverage matrix, dependencies, files/interfaces, verification commands, evidence expectations, risks, stop conditions, and lane candidates before execution.

Use only when the user explicitly invokes $agent-review, or when a loaded workflow routes here, for one focused reviewer or multiple agents to review the same artifact: Spec, Eval, plan, design, PR, diff, implementation, evidence package, or final result. Do not use for debate, lanes, or returned-lane integration.

Use only when the user explicitly invokes $agent-spec, or when an active workflow routes here, and a governed Requirements Baseline is ready to become implementation behavior before Eval.

Use when the user explicitly invokes $dev-flow, or an already-loaded controller needs development lifecycle routing across multiple gates, resume/handoff state, or unclear ownership. Do not use for ordinary implementation or a single known leaf task.

Use only when the user explicitly invokes $doc-driven-workflows, or an active workflow/project instruction routes here, for doc-driven code/docs sync, architecture/tech-stack/operation-flow/call-path docs, alignment review, open-question ledgers, or required source-of-truth maintenance. Do not use merely because docs exist.

Use only when an active workflow routes here and a goal, requirement, design direction, plan boundary, or lane split may hide omitted actors, flows, edge cases, assumptions, dependencies, contradictions, risks, or second-order effects before downstream work. Do not use for review or returned-lane integration.

Use only when the user explicitly invokes $agent-requirements-analysis, or when an active workflow routes here, and a direction, new requirement, update, bug intent, or discussion result still needs discovery, convergence, scope pruning, or a governed Requirements Baseline before Spec.

Use only when the user explicitly invokes $agent-self-driving, or an active self-driving controller already owns the task, for long-task automation that must keep lifecycle owners, agents, review/repair, evidence, and closure moving until completion or a true user decision. Do not use merely because work is large or for routine debate, review, lanes, or integration.

Use only as an internal dependency after another workflow has selected an agent-backed step and explicitly routes here for shared runtime gates. Do not use as a user-facing entry workflow.

Use only when the user explicitly invokes $agent-lanes, or when an active workflow routes here, to coordinate the initial or integration-approved dispatch of two or more independent lane/worktree/subagent tasks with owned surfaces, collision checks, coverage trace, handoff packets, and direct dispatch. Do not use for debate, review, returned-lane integration, or next-batch eligibility.

Use when the user explicitly invokes $discussion-workflows, or when an active workflow routes here, for long/corrected/decision-heavy discussion governance: recap, boundaries, reference comparison, complexity checks, drift control, confirmed/draft/open state, inbox material, or durable discussion notes.

Use only when an active workflow routes here, to review returned lane/worktree handoffs with owned surfaces and lane evidence: scope, diffs, coverage, conflicts, lane status, integration verdicts, and next-batch eligibility. Do not use for ordinary PR/code review, debate/review agents finishing, or non-lane worker results.

Use only when an active workflow routes here, to restore authoritative project state before planning, delegation, integration, or doc maintenance: handoff, coordination, specs, lanes, discussion state, source-of-truth docs, verification conventions, and collision risks. Do not use merely because ordinary docs exist.

Use when the user wants to generate, render, batch-generate, or edit raster images such as photos, illustrations, product mockups, icons, hero images, textures, concept art, wallpapers, transparent cutouts, or reference-based image edits through a codex-compatible image generation API.