Skill rating

Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2). **Use when:** - The auditor integration tests assert PASS verdict on a canonical input **Triggers:** "known-good fixture",

Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.

Operate a caller-selected Gas City 1.4 with upstream registry packs and native run-centered surfaces while keeping GC runtime state out of AgentOps verdicts. Triggers: "using gc", "gas city", "drive t

A test fixture that intentionally fails Pass-2 checks.

Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check facts. Triggers: "implement", "implement this bead", "run the experiment". Full plan-t

Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.

Operate Gas City through its own doors: Mayor, doctor and native run state. Use when: Gas City is selected or a gc run looks stuck.

Give advisory feedback on a plan, design or code change. Use when: asked for an opinion or a look-over, even informally. Not for acceptance; use Validate.

Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p` call, even a simple one.

Brainstorm evidence-backed options for what to build, or stress-test an idea. Use when: deciding what to build next, comparing options or testing an idea.

Measure whether a skill helps by comparing runs with and without it. Use when: reading skill A/B results or deciding to keep, revise or remove one.

Restructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up, extract, dedupe or simplify, even one function.

Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.

Write source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.

Compare interface designs and find structural friction. Use when: a change spreads across modules or a boundary is unclear. For code changes, use Refactor.

Coordinate several workers: what idle agents do next, which finished work gets checked first, how to recover a dead one. Use when: managing multiple agents.

Audit CLI, API, MCP or SDK discovery, first use and error recovery. Use when: designing an agent-facing tool or investigating misuse, including one command.

Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone. Use when: asked to interview you about a goal or plan.

Find how a rollout plan could fail before committing to it. Use when: asked what could go wrong or to poke holes in a plan.

Freshly judge whether a finished change and its claims meet original acceptance: PASS, FAIL or NOT_PROVEN. Use when: asked for a go/no-go, sign-off or independent verdict.

Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.

Settle what domain terms mean per context, and which repository conventions or language standards (Go, Python) apply. Use when: names disagree or a rename is proposed.

Find or curate supported lessons and agent rules. Use when: asked to remember, trace a corrected claim, audit instructions or write an agent rule.

Turn incoming reports, external PRs and alerts into evidence-based decisions and agent-ready briefs. Use when: intake arrives. For accepted work, use Plan.

Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.

Tear down a competitor's repo or product into a feature inventory and adoption choices. Use when: comparing us to another tool or asking what to steal.

Create, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.

Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.

Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a /goal prompt); one change goes to Plan.

Explain why a change, incident or session went as it did, separating proven causes from coincidence. Use when: asked for a postmortem, retro or root-cause write-up.

Pick the next work in an epic or bead graph; closed is not proven. Use when: asked what is next or whether an epic is done.

Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.

Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.

Write or assess tests that prove behavior and would fail without the fix. Use when: writing tests, TDD, or asked whether a green test is enough.

A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly.

Change or repair code, config or services without weakening tests; report what ran and what did not. Use when: implementing a change or fixing a defect.

Freshly judge exact subject content against bead or caller acceptance, optionally persist verdict.v2 for a declared consumer, and stop. Triggers: "validate", "independently validate", "vibe".