safeword

Use when finishing spec.md before writing test-definitions.md, or when the review gate asks for a spec review — self-reviews the just-authored spec inline and earns its Tier 1 review stamp. Your own inline pass; do not spawn a sub-agent.

Safeword semver commitment and release discipline. Use when bumping versions, cutting releases, deciding what goes in a patch vs minor vs major, or reviewing changelog entries. Also use when auto-upgrade logic needs to know what's safe to apply silently.

Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.

Behavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.

Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner.

Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.

Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.

Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.

Use when you need safeword's dense artifacts or current state translated into plain English — what this is, why it matters, what to do next, with the internal jargon stripped. Targets a safeword ticket, a blocked gate, or a verdict; with no target it recaps where you are in the current safeword work. Read-only. Do NOT use to explain code diffs or PRs (base Claude handles those), for general status questions unrelated to safeword artifacts, or to make any change.

Explore and debate options with fresh documentation and research before committing. Use when facing a real decision with multiple plausible approaches — library/framework choice, architecture call, API or schema design, algorithm selection, or any communication / strategy call where being wrong has cost. Enumerates relevant research domains, looks up current docs and evidence-based methods, weighs options on correctness and elegance, resists bloat. Do NOT use for divergent ideation (brainstorm), extracting user intent (elicit), or reviewing already-written code (quality-review).

Run linters and formatters to fix code style issues. Use when cleaning up style violations, formatting code, or after implementation to ensure code meets project standards.

Deep code review with web research. Use when double-checking code against latest docs, verifying dependency versions, or reviewing security concerns. Complements automatic quality hook with ecosystem verification.

Improve code structure without changing behavior. Use when refactoring, restructuring, simplifying, or extracting code. Also for reducing duplication, renaming for clarity, or addressing code smells. Enforces one change → test → commit when the commit can stay scoped. NOT for style/formatting (use $safeword:lint), features, or bug fixes.

Run a safeword retrospective on the current session on demand — mine the session transcript for qualitative safeword friction (bugs / rough edges / gaps) and file it upstream behind the egress guard. Use when the user says "run a retro", "$safeword:retro", "retrospective on this session", or wants to capture friction before the session ends. The retro also auto-fires at Stop; this is the manual, on-demand path.

Use when reviewing a ticket's scenarios (`.feature` source, with legacy test-definitions.md fallback) — auto-fired by the bdd scenario-gate and re-invokable after scenario edits. Runs vacuous-pass, AODI, determinism, negative-case, and cross-cutting checks and produces a structured findings report. NOT for spec.md JTBD/criteria/persona framing — that is self-review.

Use when finishing spec.md before writing test-definitions.md, or when the review gate asks for a spec review — self-reviews the just-authored spec inline and earns its Tier 1 review stamp. Your own inline pass; do not spawn a sub-agent.

Use when completing a TDD step and wanting a quality check. Reviews test quality after RED, implementation correctness after GREEN, and scenario completeness after REFACTOR.

How to write good tests. Use when writing tests, improving test coverage, or evaluating test quality. Also invoked by other skills — BDD at RED phase, tdd-review at GREEN gate, refactor at PROTECT phase, and debug. Core test quality knowledge across all workflows.

Ticket system and work logs for context anchoring. Use when creating tickets, managing work logs, or anchoring context across multi-step tasks or sessions. Do NOT use for simple patches or single-step tasks.

Verify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criteria. Runs tests, build, lint, scenarios, and dependency drift checks.

Behavior-first feature development — use when building new capabilities, continuing feature work, or when work introduces new state or multiple user flows. Discovers desired behavior through examples and scenarios before implementation. Do NOT use for bug fixes, typos, or small isolated changes.

Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.

Deep code review with web research. Use when double-checking code against latest docs, verifying dependency versions, or reviewing security concerns. Complements automatic quality hook with ecosystem verification.

Use when reviewing a ticket's scenarios (`.feature` source, with legacy test-definitions.md fallback) — auto-fired by the bdd scenario-gate and re-invokable after scenario edits. Runs vacuous-pass, AODI, determinism, negative-case, and cross-cutting checks and produces a structured findings report. NOT for spec.md JTBD/criteria/persona framing — that is self-review.

Use when completing a TDD step and wanting a quality check. Reviews test quality after RED, implementation correctness after GREEN, and scenario completeness after REFACTOR.

Ticket system and work logs for context anchoring. Use when creating tickets, managing work logs, or anchoring context across multi-step tasks or sessions. Do NOT use for simple patches or single-step tasks.

Kill zombie dev servers and test processes. Use when ports are blocked, processes are hanging, or test runners won't start.

Run a safeword retrospective on the current session on demand — mine the session transcript for qualitative safeword friction (bugs / rough edges / gaps) and file it upstream behind the egress guard. Use when the user says "run a retro", "/retro", "retrospective on this session", or wants to capture friction before the session ends. The retro also auto-fires at Stop; this is the manual, on-demand path.

Verify ticket completion criteria — use when finishing a ticket, before marking work done, or checking acceptance criteria. Runs tests, build, lint, scenarios, and dependency drift checks.

Use when finishing spec.md before writing test-definitions.md, or when the review gate asks for a spec review — self-reviews the just-authored spec inline and earns its Tier 1 review stamp. Your own inline pass; do not spawn a sub-agent.

Use when the user wants to explore options, weigh approaches, or think through uncertainty before committing to a direction. Collaborative brainstorming and rubber ducking — divergence-first thinking partner.

Root cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.

Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.

Explore and debate options with fresh documentation and research before committing. Use when facing a real decision with multiple plausible approaches — library/framework choice, architecture call, API or schema design, algorithm selection, or any communication / strategy call where being wrong has cost. Enumerates relevant research domains, looks up current docs and evidence-based methods, weighs options on correctness and elegance, resists bloat. Do NOT use for divergent ideation (brainstorm), extracting user intent (elicit), or reviewing already-written code (quality-review).

Improve code structure without changing behavior. Use when refactoring, restructuring, simplifying, or extracting code. Also for reducing duplication, renaming for clarity, or addressing code smells. Enforces one change → test → commit when the commit can stay scoped. NOT for style/formatting (use /lint), features, or bug fixes.

How to write good tests. Use when writing tests, improving test coverage, or evaluating test quality. Also invoked by other skills — BDD at RED phase, tdd-review at GREEN gate, refactor at PROTECT phase, and debug. Core test quality knowledge across all workflows.

Use when you need safeword's dense artifacts or current state translated into plain English — what this is, why it matters, what to do next, with the internal jargon stripped. Targets a safeword ticket, a blocked gate, or a verdict; with no target it recaps where you are in the current safeword work. Read-only. Do NOT use to explain code diffs or PRs (base Claude handles those), for general status questions unrelated to safeword artifacts, or to make any change.

Run linters and formatters to fix code style issues. Use when cleaning up style violations, formatting code, or after implementation to ensure code meets project standards.