byerlikaya
- 137 skills
- 0 followers
- 26 repo stars
- 2 days ago last updated
- ▌ Crew Board · byerlikayaManage shared team tasks, track dependencies, and coordinate work across a project by claiming, completing, or dropping items through a simple conversational interface.
- ▌ Crew Board 2 · byerlikayaManage shared project tasks, track dependencies, and coordinate team progress by claiming, completing, or documenting work items directly through conversational prompts.
- ▌ Frontend Design 3 · byerlikaya bundleVisual 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.
- ▌ Sonarqube Check 3 · byerlikaya bundleSonarQube 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.
- ▌ Confidence Check 3 · byerlikayaReadiness 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.
- ▌ Crew Code Review · byerlikaya bundleCode 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.
- ▌ Dependency Audit 3 · byerlikayaDependency 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.
- ▌ Frontend Flutter · byerlikaya bundleOPTIONAL, stack-specific: Flutter. Flutter projects only; the generic principles live in the `frontend` skill.
- ▌ Frontend Rn Expo 3 · byerlikayaOPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.
- ▌ Incident Runbook 3 · byerlikaya bundleIncident 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.
- ▌ Crew Allow Verify · byerlikayaAllow a verify command the hook was refused for want of a rule, or list the ones refused.
- ▌ Dependency Upgrade 3 · byerlikayaBring 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.
- ▌ Privacy Compliance 3 · byerlikayaKVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. crew-privacy-agent applies it.
- ▌ Backend Architecture · byerlikayaDecide, 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.
- ▌ Systematic Debugging 3 · byerlikaya bundleRoot-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.
- ▌ Crew Update · byerlikayaCheck for a newer version, update, report what changed, then prompt /clear to reload.
- ▌ Docs Writer 3 · byerlikaya bundleKeeps 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.
- ▌ Eval Grader 3 · byerlikaya bundleMeasure 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).
- ▌ MCP Builder 3 · byerlikaya bundleBuild 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.
- ▌ Performance 3 · byerlikaya bundleStack-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.
- ▌ Crew Approve · byerlikayaApprove the commit or push Claude just showed you (auto and dontAsk modes).
- ▌
- ▌ DB Migration 3 · byerlikaya bundleApply 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.
- ▌ Threat Model 3 · byerlikaya bundleScope 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.
- ▌ Token Budget 3 · byerlikayaContext/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.
- ▌ Observability 3 · byerlikayaStack-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.
- ▌ Security Scan 3 · byerlikaya bundleStack-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.
- ▌ Spec Planning 3 · byerlikayaSpec-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.
- ▌ Commit Message 3 · byerlikaya bundleConventional 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.
- ▌ I18N Integrity 3 · byerlikayaTranslation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
- ▌ Automode Policy 3 · byerlikaya bundleAuto-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.
- ▌ Crew Brainstorm · byerlikayaDiverge before planning — turn a fuzzy ask into scoped options and a chosen direction.
- ▌ Release 3 · byerlikayaVersioning 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.
- ▌ Testing 3 · byerlikaya bundleThe 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.
- ▌ Crew Map · byerlikayaMap the project — modules, what they touch, the gaps between them — and describe each module from the lines the scan cites.
- ▌ Frontend 3 · byerlikaya bundleStack-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.
- ▌ Red Team 3 · byerlikayaAttacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.
- ▌ Worktree 3 · byerlikayaIsolate 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.
- ▌
- ▌
- ▌ Teamboard 3 · byerlikaya bundleExperimental: 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.
- ▌ API Design 3 · byerlikayaAPI contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.
- ▌ Brainstorm 3 · byerlikayaDivergent 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.
- ▌ Crew Gates · byerlikayaGate report — what the tool-level gates actually did, and which rules nothing has tripped.
- ▌ Crew Skill · byerlikayaAuthor or change a Crewforth component (skill / agent / command) against the template and its gates.
- ▌ Trace Scan 3 · byerlikayaTrace 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.
- ▌ CI Pipeline 3 · byerlikayaCI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.
- ▌ Crew Doctor · byerlikayaHealth-check the install — hooks executable, core.hooksPath set, gates wired, discipline loaded.
- ▌ Crew Loosen · byerlikayaLower a model floor that Crewforth raised for a class of work (one model, once).
- ▌
- ▌ Crew Studio · byerlikayaOpen Crewforth Studio — the visual panel for what agents are doing, what they spent, and which gates fired.
- ▌ Adr 3 · byerlikayaArchitecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
- ▌ A11Y 3 · byerlikayaFrontend 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.
- ▌ Deploy 3 · byerlikaya bundleShip 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.
- ▌ Handoff 3 · byerlikaya bundleSession handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.
- ▌ Iterate 3 · byerlikayaRefine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.
- ▌ Reflect 3 · byerlikayaRetrospective 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.
- ▌ A11Y 2 · byerlikayaFrontend 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.
- ▌ Deploy 2 · byerlikaya bundleShip 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.
- ▌ Handoff 2 · byerlikaya bundleSession handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear.
- ▌ Iterate 2 · byerlikayaRefine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.
- ▌ Reflect 2 · byerlikayaRetrospective 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.
- ▌ Release 2 · byerlikayaVersioning 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.
- ▌ Testing 2 · byerlikaya bundleThe 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.
- ▌ Frontend 2 · byerlikaya bundleStack-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.
- ▌ Red Team 2 · byerlikayaAttacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.
- ▌ Worktree 2 · byerlikayaIsolate 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.
- ▌ Teamboard 2 · byerlikayaShared 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.
- ▌ API Design 2 · byerlikayaAPI contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.
- ▌ Brainstorm 2 · byerlikayaDivergent 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.
- ▌ Trace Scan 2 · byerlikayaTrace 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.
- ▌ CI Pipeline 2 · byerlikayaCI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.
- ▌ Docs Writer 2 · byerlikaya bundleKeeps 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.
- ▌ Eval Grader 2 · byerlikaya bundleMeasure 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).
- ▌ MCP Builder 2 · byerlikaya bundleBuild 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.
- ▌ Performance 2 · byerlikaya bundleStack-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.
- ▌ DB Migration 2 · byerlikaya bundleApply 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.
- ▌ Threat Model 2 · byerlikaya bundleScope 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.
- ▌ Token Budget 2 · byerlikayaContext/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.
- ▌ Observability 2 · byerlikayaStack-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.
- ▌ Security Scan 2 · byerlikaya bundleStack-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.
- ▌ Spec Planning 2 · byerlikayaSpec-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.
- ▌ Commit Message 2 · byerlikaya bundleConventional 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.
- ▌ Devarch Module 2 · byerlikaya bundleDevArchitecture backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP chain, FluentValidation, i18n. backend-expert-csk applies it.
- ▌ I18N Integrity 2 · byerlikayaTranslation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
- ▌ Automode Policy 2 · byerlikaya bundleAuto-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.
- ▌ Code Review Csk 2 · byerlikaya bundleCode 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.
- ▌ Frontend Design 2 · byerlikaya bundleVisual 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.
- ▌ Sonarqube Check 2 · byerlikayaSonarQube 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.
- ▌ Confidence Check 2 · byerlikayaReadiness 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.
- ▌ Dependency Audit 2 · byerlikayaDependency 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.
- ▌ Frontend Rn Expo 2 · byerlikayaOPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the `frontend` skill.
- ▌ Incident Runbook 2 · byerlikaya bundleProduction 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.
- ▌ Dependency Upgrade 2 · byerlikayaBring 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.
- ▌ Privacy Compliance 2 · byerlikayaKVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border transfer. privacy-agent-csk applies it.
- ▌ Systematic Debugging 2 · byerlikaya bundleRoot-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.
- ▌ Adr 2 · byerlikayaArchitecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
- ▌ Adr · byerlikayaArchitecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.
- ▌ A11Y · byerlikayaFrontend 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.
- ▌ Deploy · byerlikaya bundleShip 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.