all publishers

byerlikaya

@byerlikaya source repo

137 published skills · page 1 of 2

  1. ▌
    Crew Board · byerlikaya
    Manage shared team tasks, track dependencies, and coordinate work across a project by claiming, completing, or dropping items through a simple conversational interface.
    26 repo stars
  2. ▌
    Crew Board 2 · byerlikaya
    Manage shared project tasks, track dependencies, and coordinate team progress by claiming, completing, or documenting work items directly through conversational prompts.
    26 repo stars
  3. ▌
    Frontend Design 3 · byerlikaya bundle
    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.
    26 repo stars
  4. ▌
    Sonarqube Check 3 · byerlikaya bundle
    SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read the real gate + issues, fix by rule id, re-scan and diff. A linter's green build is a pre-check, never the gate.
    26 repo stars
  5. ▌
    Confidence Check 3 · byerlikaya
    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.
    26 repo stars
  6. ▌
    Crew Code Review · byerlikaya bundle
    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.
    26 repo stars
  7. ▌
    Dependency Audit 3 · byerlikaya
    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.
    26 repo stars
  8. ▌
    Frontend Flutter · byerlikaya bundle
    OPTIONAL, stack-specific: Flutter. Flutter projects only; the generic principles live in the `frontend` skill.
    26 repo stars
  9. ▌
    Frontend Rn Expo 3 · byerlikaya
    OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.
    26 repo stars
  10. ▌
    Incident Runbook 3 · byerlikaya bundle
    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, an outage keeps recurring, or for the postmortem.
    26 repo stars
  11. ▌
    Crew Allow Verify · byerlikaya
    Allow a verify command the hook was refused for want of a rule, or list the ones refused.
    26 repo stars
  12. ▌
    Dependency Upgrade 3 · byerlikaya
    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.
    26 repo stars
  13. ▌
    Privacy Compliance 3 · byerlikaya
    KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. crew-privacy-agent applies it.
    26 repo stars
  14. ▌
    Backend Architecture · byerlikaya
    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.
    26 repo stars
  15. ▌
    Systematic Debugging 3 · byerlikaya bundle
    Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and verify. Stops guess-driven patching. For persistent, intermittent, or "already tried a few things" bugs.
    26 repo stars
  16. ▌
    Crew Update · byerlikaya
    Check for a newer version, update, report what changed, then prompt /clear to reload.
    26 repo stars
  17. ▌
    Docs Writer 3 · byerlikaya bundle
    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.
    26 repo stars
  18. ▌
    Eval Grader 3 · byerlikaya bundle
    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).
    26 repo stars
  19. ▌
    MCP Builder 3 · byerlikaya bundle
    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.
    26 repo stars
  20. ▌
    Performance 3 · byerlikaya bundle
    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.
    26 repo stars
  21. ▌
    Crew Approve · byerlikaya
    Approve the commit or push Claude just showed you (auto and dontAsk modes).
    26 repo stars
  22. ▌
    Crew Handoff · byerlikaya
    Session handover — SESSION_STATE.md + /clear suggestion.
    26 repo stars
  23. ▌
    DB Migration 3 · byerlikaya bundle
    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.
    26 repo stars
  24. ▌
    Threat Model 3 · byerlikaya bundle
    Scope a security audit BEFORE scanning, to cut false positives: map assets, entry points, trust boundaries and 5-8 domain-specific attack classes into a parseable THREAT_MODEL.md. A threat survives a patch; a vulnerability is only evidence for one. Feeds security-scan.
    26 repo stars
  25. ▌
    Token Budget 3 · byerlikaya
    Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.
    26 repo stars
  26. ▌
    Observability 3 · byerlikaya
    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.
    26 repo stars
  27. ▌
    Security Scan 3 · byerlikaya bundle
    Stack-agnostic security audit: map the attack surface, trace untrusted input to dangerous calls, surface dependency and configuration flaws. Severity-ranked report with fixes. Use when auth, input handling, secrets or dependencies change, and before a release.
    26 repo stars
  28. ▌
    Spec Planning 3 · byerlikaya
    Spec-first planning: task breakdown, measurable acceptance criteria, dependency order, risk priority. crew-planner applies it; the plan goes to docs/PLAN.md. Use when the scope is unclear or the work spans more than one change.
    26 repo stars
  29. ▌
    Commit Message 3 · byerlikaya bundle
    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.
    26 repo stars
  30. ▌
    I18N Integrity 3 · byerlikaya
    Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
    26 repo stars
  31. ▌
    Automode Policy 3 · byerlikaya bundle
    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.
    26 repo stars
  32. ▌
    Crew Brainstorm · byerlikaya
    Diverge before planning — turn a fuzzy ask into scoped options and a chosen direction.
    26 repo stars
  33. ▌
    Release 3 · byerlikaya
    Versioning and CHANGELOG: SemVer mapped from Conventional Commits, Keep a Changelog format, tagging, pre-release gates. Use when cutting a version: bumping, writing the CHANGELOG entry, or tagging.
    26 repo stars
  34. ▌
    Testing 3 · byerlikaya bundle
    The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green". crew-test-expert applies it. Use when writing or changing tests, or when a suite is flaky, slow or green for the wrong reason.
    26 repo stars
  35. ▌
    Crew Map · byerlikaya
    Map the project — modules, what they touch, the gaps between them — and describe each module from the lines the scan cites.
    26 repo stars
  36. ▌
    Frontend 3 · byerlikaya bundle
    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.
    26 repo stars
  37. ▌
    Red Team 3 · byerlikaya
    Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.
    26 repo stars
  38. ▌
    Worktree 3 · byerlikaya
    Isolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are never clobbered. For fan-out agents that edit files, throwaway experiments, or any change you may want to discard cleanly.
    26 repo stars
  39. ▌
    Crew Plan · byerlikaya
    Spec-first planning — break down ambiguously scoped work with crew-planner.
    26 repo stars
  40. ▌
    Crew Ship · byerlikaya
    DoD gate + commit proposal (waits for approval).
    26 repo stars
  41. ▌
    Teamboard 3 · byerlikaya bundle
    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.
    26 repo stars
  42. ▌
    API Design 3 · byerlikaya
    API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.
    26 repo stars
  43. ▌
    Brainstorm 3 · byerlikaya
    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.
    26 repo stars
  44. ▌
    Crew Gates · byerlikaya
    Gate report — what the tool-level gates actually did, and which rules nothing has tripped.
    26 repo stars
  45. ▌
    Crew Skill · byerlikaya
    Author or change a Crewforth component (skill / agent / command) against the template and its gates.
    26 repo stars
  46. ▌
    Trace Scan 3 · byerlikaya
    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.
    26 repo stars
  47. ▌
    CI Pipeline 3 · byerlikaya
    CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.
    26 repo stars
  48. ▌
    Crew Doctor · byerlikaya
    Health-check the install — hooks executable, core.hooksPath set, gates wired, discipline loaded.
    26 repo stars
  49. ▌
    Crew Loosen · byerlikaya
    Lower a model floor that Crewforth raised for a class of work (one model, once).
    26 repo stars
  50. ▌
    Crew Review · byerlikaya
    Review pass — review + security + quality gates.
    26 repo stars
  51. ▌
    Crew Studio · byerlikaya
    Open Crewforth Studio — the visual panel for what agents are doing, what they spent, and which gates fired.
    26 repo stars
  52. ▌
    Adr 3 · byerlikaya
    Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
    26 repo stars
  53. ▌
    A11Y 3 · byerlikaya
    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.
    26 repo stars
  54. ▌
    Deploy 3 · byerlikaya bundle
    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.
    26 repo stars
  55. ▌
    Handoff 3 · byerlikaya bundle
    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.
    26 repo stars
  56. ▌
    Iterate 3 · byerlikaya
    Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.
    26 repo stars
  57. ▌
    Reflect 3 · byerlikaya
    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.
    26 repo stars
  58. ▌
    A11Y 2 · byerlikaya
    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.
    26 repo stars
  59. ▌
    Deploy 2 · byerlikaya bundle
    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.
    26 repo stars
  60. ▌
    Handoff 2 · byerlikaya bundle
    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.
    26 repo stars
  61. ▌
    Iterate 2 · byerlikaya
    Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.
    26 repo stars
  62. ▌
    Reflect 2 · byerlikaya
    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.
    26 repo stars
  63. ▌
    Release 2 · byerlikaya
    Versioning and CHANGELOG: SemVer mapped from Conventional Commits, Keep a Changelog format, tagging, pre-release gates. Use when cutting a version: bumping, writing the CHANGELOG entry, or tagging.
    26 repo stars
  64. ▌
    Testing 2 · byerlikaya bundle
    The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green". test-expert-csk applies it. Use when writing or changing tests, or when a suite is flaky, slow or green for the wrong reason.
    26 repo stars
  65. ▌
    Frontend 2 · byerlikaya bundle
    Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data fetching, loading/empty/error states, i18n, accessibility, performance. frontend-expert-csk applies it on every stack.
    26 repo stars
  66. ▌
    Red Team 2 · byerlikaya
    Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.
    26 repo stars
  67. ▌
    Worktree 2 · byerlikaya
    Isolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are never clobbered. For fan-out agents that edit files, throwaway experiments, or any change you may want to discard cleanly.
    26 repo stars
  68. ▌
    Teamboard 2 · byerlikaya
    Shared team board: claim a work item before starting, hand it over, finish it. The claim is a git-ref lock, so two people cannot take the same item.
    26 repo stars
  69. ▌
    API Design 2 · byerlikaya
    API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.
    26 repo stars
  70. ▌
    Brainstorm 2 · byerlikaya
    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.
    26 repo stars
  71. ▌
    Trace Scan 2 · byerlikaya
    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.
    26 repo stars
  72. ▌
    CI Pipeline 2 · byerlikaya
    CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.
    26 repo stars
  73. ▌
    Docs Writer 2 · byerlikaya bundle
    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.
    26 repo stars
  74. ▌
    Eval Grader 2 · byerlikaya bundle
    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).
    26 repo stars
  75. ▌
    MCP Builder 2 · byerlikaya bundle
    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.
    26 repo stars
  76. ▌
    Performance 2 · byerlikaya bundle
    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.
    26 repo stars
  77. ▌
    DB Migration 2 · byerlikaya bundle
    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.
    26 repo stars
  78. ▌
    Threat Model 2 · byerlikaya bundle
    Scope a security audit BEFORE scanning, to cut false positives: map assets, entry points, trust boundaries and 5-8 domain-specific attack classes into a parseable THREAT_MODEL.md. A threat survives a patch; a vulnerability is only evidence for one. Feeds security-scan.
    26 repo stars
  79. ▌
    Token Budget 2 · byerlikaya
    Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.
    26 repo stars
  80. ▌
    Observability 2 · byerlikaya
    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.
    26 repo stars
  81. ▌
    Security Scan 2 · byerlikaya bundle
    Stack-agnostic security audit: map the attack surface, trace untrusted input to dangerous calls, surface dependency and configuration flaws. Severity-ranked report with fixes. Use when auth, input handling, secrets or dependencies change, and before a release.
    26 repo stars
  82. ▌
    Spec Planning 2 · byerlikaya
    Spec-first planning: task breakdown, measurable acceptance criteria, dependency order, risk priority. planner-csk applies it; the plan goes to docs/PLAN.md. Use when the scope is unclear or the work spans more than one change.
    26 repo stars
  83. ▌
    Commit Message 2 · byerlikaya bundle
    Conventional Commits: reads the staged diff and proposes `type(scope): summary`, with body/footer when needed. One logical change = one commit. commit-agent-csk applies it.
    26 repo stars
  84. ▌
    Devarch Module 2 · byerlikaya bundle
    DevArchitecture backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP chain, FluentValidation, i18n. backend-expert-csk applies it.
    26 repo stars
  85. ▌
    I18N Integrity 2 · byerlikaya
    Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
    26 repo stars
  86. ▌
    Automode Policy 2 · byerlikaya bundle
    Auto-mode classifier config: inspect what the classifier that now answers permission prompts is configured with, and catch the silent case where a custom autoMode block drops the built-in block rules.
    26 repo stars
  87. ▌
    Code Review Csk 2 · byerlikaya bundle
    Code review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall code health. review-agent-csk applies it. Use when reviewing a change set, and when acting on a review someone else wrote.
    26 repo stars
  88. ▌
    Frontend Design 2 · byerlikaya bundle
    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.
    26 repo stars
  89. ▌
    Sonarqube Check 2 · byerlikaya
    SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read the real gate + issues, fix by rule id, re-scan and diff. A linter's green build is a pre-check, never the gate.
    26 repo stars
  90. ▌
    Confidence Check 2 · byerlikaya
    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.
    26 repo stars
  91. ▌
    Dependency Audit 2 · byerlikaya
    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.
    26 repo stars
  92. ▌
    Frontend Rn Expo 2 · byerlikaya
    OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.
    26 repo stars
  93. ▌
    Incident Runbook 2 · byerlikaya bundle
    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.
    26 repo stars
  94. ▌
    Dependency Upgrade 2 · byerlikaya
    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.
    26 repo stars
  95. ▌
    Privacy Compliance 2 · byerlikaya
    KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. privacy-agent-csk applies it.
    26 repo stars
  96. ▌
    Systematic Debugging 2 · byerlikaya bundle
    Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and verify. Stops guess-driven patching. For persistent, intermittent, or "already tried a few things" bugs.
    26 repo stars
  97. ▌
    Adr 2 · byerlikaya
    Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
    26 repo stars
  98. ▌
    Adr · byerlikaya
    Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
    26 repo stars
  99. ▌
    A11Y · byerlikaya
    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.
    26 repo stars
  100. ▌
    Deploy · byerlikaya bundle
    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.
    26 repo stars