agentsclimarketplace

Review & quality

19,016 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Qa only

    kjuhwa/skills-hub/skills/cli/gstack/qa-only Skill

    0★ repo

    Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".

  • Review

    kjuhwa/skills-hub/skills/cli/gstack/review Skill

    0★ repo

    Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)

  • Ship

    kjuhwa/skills-hub/skills/cli/gstack/ship Skill

    0★ repo

    Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)

  • Golden

    kjuhwa/skills-hub/skills/cli/gstack/test/fixtures/golden Skill

    0★ repo

    Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)

  • Setup pre commit

    kjuhwa/skills-hub/skills/cli/setup-pre-commit Skill

    0★ repo

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

  • Design review

    kjuhwa/skills-hub/skills/design/design-review Skill

    0★ repo

    Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site. (gstack)

  • Game design doc review

    kjuhwa/skills-hub/skills/design/game-design-doc-review Skill

    0★ repo

    Reviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.

  • Health check visualization pattern

    kjuhwa/skills-hub/skills/design/health-check-visualization-pattern Skill

    0★ repo

    Dashboard layout pattern for rendering heterogeneous health-check signals into a single at-a-glance status surface

  • Plan design review

    kjuhwa/skills-hub/skills/design/plan-design-review Skill

    0★ repo

    Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively suggest when the user has a plan with UI/UX components that should be reviewed before implementation. (gstack)

  • Review all gdds

    kjuhwa/skills-hub/skills/design/review-all-gdds Skill

    0★ repo

    Holistic cross-GDD consistency and game design review. Reads all system GDDs simultaneously and checks for contradictions between them, stale references, ownership conflicts, formula incompatibilities, and game design theory violations (dominant strategies, economic imbalance, cognitive overload, pillar drift). Run after all MVP GDDs are written, before architecture begins.

  • Ux review

    kjuhwa/skills-hub/skills/design/ux-review Skill

    0★ repo

    Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.

  • Finishing a development branch

    kjuhwa/skills-hub/skills/devops/finishing-a-development-branch Skill

    0★ repo

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

  • Make check verification loop

    kjuhwa/skills-hub/skills/devops/make-check-verification-loop Skill

    0★ repo

    Single make check command that runs typecheck + TS tests + Go tests + Playwright E2E for agents and CI, only starting services that aren't already running.

  • Skill md validator

    kjuhwa/skills-hub/skills/devops/skill-md-validator Skill

    0★ repo

    [Tooling] SKILL.md frontmatter + 필수 섹션을 CRITICAL/WARNING 등급으로 검증하는 품질 게이트.

  • Using git worktrees

    kjuhwa/skills-hub/skills/devops/using-git-worktrees Skill

    0★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

  • Architecture review

    kjuhwa/skills-hub/skills/engineering/architecture-review Skill

    0★ repo

    Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.

  • Code review

    kjuhwa/skills-hub/skills/engineering/code-review Skill

    0★ repo

    Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.

  • Receiving code review

    kjuhwa/skills-hub/skills/engineering/receiving-code-review Skill

    0★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

  • Requesting code review

    kjuhwa/skills-hub/skills/engineering/requesting-code-review Skill

    0★ repo

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

  • Verification before completion

    kjuhwa/skills-hub/skills/engineering/verification-before-completion Skill

    0★ repo

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

  • Git worktree isolation per thread

    kjuhwa/skills-hub/skills/git/git-worktree-isolation-per-thread Skill

    0★ repo

    Use git worktrees to isolate filesystem state per conversation thread, avoiding conflicts between concurrent edits

  • Kernel validation with corrupted cache detection

    kjuhwa/skills-hub/skills/gpu-kernels/kernel-validation-with-corrupted-cache-detection Skill

    0★ repo

    On JIT cache load, validate that every expected artifact (kernel.cu + kernel.cubin) is present and abort with an actionable 'rm -rf CACHE_PATH' error if not.

  • Mcp multi transport config pydantic

    kjuhwa/skills-hub/skills/integration/mcp-multi-transport-config-pydantic Skill

    0★ repo

    Single Pydantic config that supports three MCP transports (stdio, sse, streamable-http) with per-transport required-field validation in a model_validator(after) so users get a clear error when the wrong combination is set.

  • Git rollback mode selector

    kjuhwa/skills-hub/skills/operations/git-rollback-mode-selector Skill

    0★ repo

    Let operators pick how failed autonomous changes unwind — hard reset, stash-and-continue, or no-op — via one env var. The three modes trade audit-trail preservation against blast-radius containment.

  • Orphaned daemon termination guard

    kjuhwa/skills-hub/skills/process/orphaned-daemon-termination-guard Skill

    0★ repo

    Kill an orphaned background daemon when no non-daemon sibling process is alive. Prevents LevelDB/file lock contention after unclean parent shutdown. Pattern: scan for daemon PIDs, then check if any non-daemon parent process exists before killing.

  • Gate check

    kjuhwa/skills-hub/skills/production/gate-check Skill

    0★ repo

    Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts. Use when user says 'are we ready to move to X', 'can we advance to production', 'check if we can start the next phase', 'pass the gate'.

  • Milestone review

    kjuhwa/skills-hub/skills/production/milestone-review Skill

    0★ repo

    Generates a comprehensive milestone progress review including feature completeness, quality metrics, risk assessment, and go/no-go recommendation. Use at milestone checkpoints or when evaluating readiness for a milestone deadline.

  • Release checklist

    kjuhwa/skills-hub/skills/production/release-checklist Skill

    0★ repo

    Generates a comprehensive pre-release validation checklist covering build verification, certification requirements, store metadata, and launch readiness.

  • Scope check

    kjuhwa/skills-hub/skills/production/scope-check Skill

    0★ repo

    Analyze a feature or sprint for scope creep by comparing current scope against the original plan. Flags additions, quantifies bloat, and recommends cuts. Use when user says 'any scope creep', 'scope review', 'are we staying in scope'.

  • Balance check

    kjuhwa/skills-hub/skills/qa/balance-check Skill

    0★ repo

    Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.

  • Consistency check

    kjuhwa/skills-hub/skills/qa/consistency-check Skill

    0★ repo

    Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.

  • Smoke check

    kjuhwa/skills-hub/skills/qa/smoke-check Skill

    0★ repo

    Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.

  • Test evidence review

    kjuhwa/skills-hub/skills/qa/test-evidence-review Skill

    0★ repo

    Quality review of test files and manual evidence documents. Goes beyond existence checks — evaluates assertion coverage, edge case handling, naming conventions, and evidence completeness. Produces ADEQUATE/INCOMPLETE/MISSING verdict per story. Run before QA sign-off or on demand.

  • Pre release version validation script

    kjuhwa/skills-hub/skills/release/pre-release-version-validation-script Skill

    0★ repo

    Pre-release script validates: tag matches pyproject version, copyright headers exist on all source files, package metadata fields complete, type checker passes.

  • Version bump inference from commit subjects

    kjuhwa/skills-hub/skills/release/version-bump-inference-from-commit-subjects Skill

    0★ repo

    Infer semantic version bump (major/minor/patch) from commit subjects since last release

  • Detached update check with local cache

    kjuhwa/skills-hub/skills/reliability/detached-update-check-with-local-cache Skill

    0★ repo

    Check for package updates in a detached child subprocess with a 24h local cache so startup stays fast, notification is fresh, and network failure never blocks the user.

  • Process singleton guard with lockfile

    kjuhwa/skills-hub/skills/resilience/process-singleton-guard-with-lockfile Skill

    0★ repo

    Prevent multiple daemon instances using exclusive lockfile creation and PID validation

  • Interface contract validation

    kjuhwa/skills-hub/skills/safety/interface-contract-validation Skill

    0★ repo

    Define and validate interface contracts for wrapper compatibility before breaking changes

  • Output guardrail check

    kjuhwa/skills-hub/skills/safety/output-guardrail-check Skill

    0★ repo

    Validate or block agent output before returning it to the user using @output_guardrail.

  • Cso

    kjuhwa/skills-hub/skills/security/cso Skill

    0★ repo

    Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".

  • Guard

    kjuhwa/skills-hub/skills/security/guard Skill

    0★ repo

    Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

  • Sha256 download verification pipeline

    kjuhwa/skills-hub/skills/security/sha256-download-verification-pipeline Skill

    0★ repo

    Download a binary and verify it against an expected SHA-256 checksum before use. Supports per-architecture checksums, optional verification skip when hash is empty (with warning), and clear error messages with both expected and actual values.

  • Validation command allowlist gate

    kjuhwa/skills-hub/skills/security/validation-command-allowlist-gate Skill

    0★ repo

    Before executing an "arbitrary" validation command supplied by data (plugin config, ingested asset, user rule), pass it through a layered allowlist that rejects anything outside a known-prefix whitelist, substitution syntax, or shell operators, and then run it scoped and time-bound.

  • Validation command whitelist gate

    kjuhwa/skills-hub/skills/security/validation-command-whitelist-gate Skill

    0★ repo

    Before executing any user-supplied "validation" shell command, filter it through a binary prefix whitelist, reject all command-substitution forms, reject shell operators after stripping quoted regions, and enforce a hard per-command timeout and fixed cwd — so that even a fully attacker-controlled config string cannot escape to arbitrary command execution.

  • Browse

    kjuhwa/skills-hub/skills/testing/browse Skill

    0★ repo

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)

  • Deterministic coverage verification

    kjuhwa/skills-hub/skills/testing/deterministic-coverage-verification Skill

    0★ repo

    Run LLVM-instrumented tests multiple times and verify identical coverage reports — catches compiler/env non-determinism that can mask real bugs.

  • Devex review

    kjuhwa/skills-hub/skills/testing/devex-review Skill

    0★ repo

    Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".

  • Gstack qa only

    kjuhwa/skills-hub/skills/testing/gstack-qa-only Skill

    0★ repo

    Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".

  • Health

    kjuhwa/skills-hub/skills/testing/health Skill

    0★ repo

    Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the codebase", "run all checks", "quality score". (gstack)

  • Test suite validation with env isolation

    kjuhwa/skills-hub/skills/testing/test-suite-validation-with-env-isolation Skill

    0★ repo

    Run test suite with isolated environment (NODE_ENV=test, specific env vars, no bridge)

  • Branded git path types

    kjuhwa/skills-hub/skills/typescript/branded-git-path-types Skill

    0★ repo

    Use branded string types (`RepoPath`, `WorktreePath`, `BranchName`) with constructor helpers to prevent accidentally passing one string primitive where another is expected.

  • Typed websocket rpc boundary validation

    kjuhwa/skills-hub/skills/websocket/typed-websocket-rpc-boundary-validation Skill

    0★ repo

    Enforce strict schema validation at the WebSocket transport layer to catch contract breakages early

  • Canary

    kjuhwa/skills-hub/skills/workflow/canary Skill

    0★ repo

    Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)

  • Grill me

    kjuhwa/skills-hub/skills/workflow/grill-me Skill

    0★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

  • Health check data simulation

    kjuhwa/skills-hub/skills/workflow/health-check-data-simulation Skill

    0★ repo

    Generate realistic health-check sample streams with correlated failures, flapping, and recovery curves for demos and tests

  • Heuristic scan iterative tuning

    kjuhwa/skills-hub/skills/workflow/heuristic-scan-iterative-tuning Skill

    0★ repo

    When writing a new heuristic scanner over a corpus (dedup, archive, compress, lint), expect the first run to be wrong in predictable ways. Run → inspect false positives → add one guard → re-run. Tighten the spec and the scan script in lockstep so the shipped version reflects real-world calibration, not guessed thresholds.

  • Plan ceo review

    kjuhwa/skills-hub/skills/workflow/plan-ceo-review Skill

    0★ repo

    CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger. (gstack)

  • Plan devex review

    kjuhwa/skills-hub/skills/workflow/plan-devex-review Skill

    0★ repo

    Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to "DX review", "developer experience audit", "devex review", or "API design review". Proactively suggest when the user has a plan for developer-facing products (APIs, CLIs, SDKs, libraries, platforms, docs). (gstack) Voice triggers (speech-to-text aliases): "dx review", "developer experience review", "devex review", "devex audit", "API design review", "onboarding review".

  • Plan eng review

    kjuhwa/skills-hub/skills/workflow/plan-eng-review Skill

    0★ repo

    Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".

  • Review

    kjuhwa/skills-hub/skills/workflow/review Skill

    0★ repo

    Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)