All authors
Claude Skills by crewforth
github.com/crewforth58 skills0 installs11 views
- Automode PolicyAuto-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.Votes: 0GitHub stars: 24
- Crew BoardExperimental: team board — claim an item, hand it over, complete it.Votes: 0GitHub stars: 24
- Crew DoctorHealth-check the install — hooks executable, core.hooksPath set, gates wired, discipline loaded.Votes: 0GitHub stars: 24
- Crew GatesGate report — what the tool-level gates actually did, and which rules nothing has tripped.Votes: 0GitHub stars: 24
- Crew HandoffSession handover — SESSION_STATE.md + /clear suggestion.Votes: 0GitHub stars: 24
- Crew SkillAuthor or change a Crewforth component (skill / agent / command) against the template and its gates.Votes: 0GitHub stars: 24
- Crew StudioOpen Crewforth Studio — the visual panel for what agents are doing, what they spent, and which gates fired.Votes: 0GitHub stars: 24
- Crew UpdateCheck for a newer version, update, report what changed, then prompt /clear to reload.Votes: 0GitHub stars: 24
- Frontend Rn ExpoOPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.Votes: 0GitHub stars: 24
- FrontendStack-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.Votes: 0GitHub stars: 24
- HandoffSession handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.Votes: 0GitHub stars: 24
- ReflectRetrospective 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.Votes: 0GitHub stars: 24
- TeamboardExperimental: 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.Votes: 0GitHub stars: 24
- Token BudgetContext/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.Votes: 0GitHub stars: 24
- Trace ScanTrace 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.Votes: 0GitHub stars: 24
- Automode PolicyAuto-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.Votes: 0GitHub stars: 24
- Crew BoardExperimental: team board — claim an item, hand it over, complete it.Votes: 0GitHub stars: 24
- Crew HandoffSession handover — SESSION_STATE.md + /clear suggestion.Votes: 0GitHub stars: 24
- HandoffSession handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.Votes: 0GitHub stars: 24
- ReflectRetrospective 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.Votes: 0GitHub stars: 24
- TeamboardExperimental: 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.Votes: 0GitHub stars: 24
- Token BudgetContext/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.Votes: 0GitHub stars: 24
- A11yFrontend 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.Votes: 0GitHub stars: 24
- AdrArchitecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.Votes: 0GitHub stars: 24
- Api DesignAPI contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.Votes: 0GitHub stars: 24
- Backend ArchitectureDecide, 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.Votes: 0GitHub stars: 24
- BrainstormDivergent 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.Votes: 0GitHub stars: 24
- Ci PipelineCI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.Votes: 0GitHub stars: 24
- Commit MessageConventional 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.Votes: 0GitHub stars: 24
- Confidence CheckReadiness 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.Votes: 0GitHub stars: 24
- Crew BrainstormDiverge before planning — turn a fuzzy ask into scoped options and a chosen direction.Votes: 0GitHub stars: 24
- Crew Code ReviewCode 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.Votes: 0GitHub stars: 24
- Crew PlanSpec-first planning — break down ambiguously scoped work with crew-planner.Votes: 0GitHub stars: 24
- Crew ReviewReview pass — review + security + quality gates.Votes: 0GitHub stars: 24
- Crew ShipDoD gate + commit proposal (waits for approval).Votes: 0GitHub stars: 24
- Db MigrationApply 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.Votes: 0GitHub stars: 24
- Dependency AuditDependency 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.Votes: 0GitHub stars: 24
- Dependency UpgradeBring 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.Votes: 0GitHub stars: 24
- DeployShip 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.Votes: 0GitHub stars: 24
- Docs WriterKeeps 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.Votes: 0GitHub stars: 24
- Eval GraderMeasure 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).Votes: 0GitHub stars: 24
- Frontend DesignVisual 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.Votes: 0GitHub stars: 24
- I18n IntegrityTranslation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.Votes: 0GitHub stars: 24
- Incident RunbookProduction 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.Votes: 0GitHub stars: 24
- IterateRefine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.Votes: 0GitHub stars: 24
- Mcp BuilderBuild 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.Votes: 0GitHub stars: 24
- ObservabilityStack-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.Votes: 0GitHub stars: 24
- PerformanceStack-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.Votes: 0GitHub stars: 24
- Privacy ComplianceKVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. crew-privacy-agent applies it.Votes: 0GitHub stars: 24
- Red TeamAttacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.Votes: 0GitHub stars: 24