Claude Skills by crewforth

Auto-mode classifier config: inspect what the classifier that answers permission prompts is configured with, and catch the silent case where a custom autoMode block drops the built-in block rules.

Experimental: team board — claim an item, hand it over, complete it.

Health-check the install — hooks executable, core.hooksPath set, gates wired, discipline loaded.

Gate report — what the tool-level gates actually did, and which rules nothing has tripped.

Session handover — SESSION_STATE.md + /clear suggestion.

Author or change a Crewforth component (skill / agent / command) against the template and its gates.

Open Crewforth Studio — the visual panel for what agents are doing, what they spent, and which gates fired.

Check for a newer version, update, report what changed, then prompt /clear to reload.

OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.

Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data fetching, loading/empty/error states, i18n, accessibility, performance. crew-frontend-expert applies it on every stack.

Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.

Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach — findings, not code. The step-back counterpart to iterate's refine-to-done loop.

Experimental: a shared team board. Claim a work item, hand it over, finish it; the claim is a git-ref lock, so two people cannot take the same item.

Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.

Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers, footers, robot emoji, tool names) and vendor template names. The git hooks apply it automatically.

Auto-mode classifier config: inspect what the classifier that answers permission prompts is configured with, and catch the silent case where a custom autoMode block drops the built-in block rules.

Experimental: team board — claim an item, hand it over, complete it.

Session handover — SESSION_STATE.md + /clear suggestion.

Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.

Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach — findings, not code. The step-back counterpart to iterate's refine-to-done loop.

Experimental: a shared team board. Claim a work item, hand it over, finish it; the claim is a git-ref lock, so two people cannot take the same item.

Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.

Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen readers. Use when building or changing UI, or before shipping a user-facing screen.

Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.

API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.

Decide, record and apply the backend stack and architecture pattern. Use when backend work starts with no recorded stack, or a framework/DB/pattern must be chosen.

Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand to spec-planning. Bounded; converges to explicit choices, never guesses.

CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.

Conventional Commits: reads the staged diff and proposes `type(scope): summary`, with body/footer when needed. One logical change = one commit. crew-commit-agent applies it.

Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is the API claim actually checked, is there a working reference, is the root cause known.

Diverge before planning — turn a fuzzy ask into scoped options and a chosen direction.

Code review discipline: review only what changed, rank each finding by severity and category, and fact-check it first. crew-review-agent applies it. Use when reviewing a change set, and when acting on a review someone else wrote.

Spec-first planning — break down ambiguously scoped work with crew-planner.

Review pass — review + security + quality gates.

DoD gate + commit proposal (waits for approval).

Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval, back up in prod, preview-apply-verify, roll back on failure. Use when a schema change is about to be applied to any environment.

Dependency risk assessment, read-only: known CVEs, deprecated packages, licence compliance, maintenance status, lockfile integrity, and a justification for every new dependency. Acting on it is dependency-upgrade.

Bring dependencies current without breaking the build: find what is vulnerable, deprecated or behind, classify each target version by risk, apply what is safe, verify, and roll back what is not.

Ship a build reversibly — to a host you manage or a platform that manages it. Pick the topology first, keep the previous version reachable, gate on health, roll back without rebuilding. Use when shipping anywhere users can reach.

Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. Leaves no dead or misleading docs behind.

Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow).

Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system, layout composition, and polished states. The taste layer above frontend architecture and a11y.

Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.

Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. Stop the impact first, root cause second. Use when production is degraded or broken, and again for the postmortem afterwards.

Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.

Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a transport, handle errors, and test it. For exposing an API, database, or service to Claude and other clients.

Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. Makes a production issue traceable to why it happened. Use when adding a log line, an error path, a metric, or when an incident could not be traced.

Stack-agnostic performance: measure first, find the bottleneck, then optimise. N+1, needless allocation, wrong async boundary, missing index/cache, heavy payload. No premature optimisation. Use when something is slow, before optimising anything, and when a change touches a hot path.

KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. crew-privacy-agent applies it.

Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.