repo-maintainer
Audit and repair repository hygiene across artifacts, dependencies, CI, docs, Git state, and code-quality signals. Use for repository maintenance, cleanup,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Testing & quality
13,117 results
uiverify-triage-visual-changes
Triage a UI Verify visual regression build from your coding agent over MCP: sort changed screenshots into regressions, intended changes and noise, then accept…
memory-debug
Diagnose and fix Signet memory issues (daemon health, embeddings, search quality, and data integrity).
remember
[Internal] Save something to persistent memory with auto-embedding. Hidden from users — the automatic pipeline handles memory capture. Use for debug/dev only.
qa-flow-report
Drive a UI flow with chrome-devtools, capture a screenshot per step, then render a self-contained HTML report (report.html) showing each step with status…
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants…
test-pruning
Remove, fold or consolidate redundant tests in unifi-mcp without losing a check. Use when asked to trim, prune, shrink or deduplicate the test suite, to fold…
ai-code-review
Review local Git changes with Greptile and CodeRabbit CLI, synthesize their findings, and optionally fix important issues. Use when the user asks for AI code…
skill-support
Operate the Skill Recordings support CLI. Use when working in the support repo, triaging customer conversations, debugging pipelines, running evals, checking…
patchright-skill
Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take…
code-quality
Code quality advisor for a repo: one bun script behind git hooks and Claude Code, Codex, Grok, pi, omp, and OpenCode adapters. Never blocks: raises loud RED…
blog-audit
Full-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness.…
health-grader
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to cocotrace/health-grader without registered…
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify…
meter-benchmark
Measure per-stage success probability before iterating on CocoFlow templates. Supports `$meter benchmark --flow <template>`.
quality-off
Disable the Code Quality Advisor. Automatic SQL review stops. Existing findings are preserved.
quality-run
Run the Code Quality Advisor on demand against a specified file or all SQL files. Usage: $quality run [file-path] or $quality run (for all .sql files). Finds…
review
Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate.…
secondeye-history
List all SecondEye review reports for this project. Shows review date, artifact reviewed, finding counts, and acknowledgment status.
sentinel
CocoSentinel — eight-dimension artifact quality gate. Dimension G evidence pre-gate runs first (deterministic, <50ms); if PASS, spawns A1–H in parallel.…
sketch-validate
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to cocosketch/sketch-validate without registered…
status-envelope-check
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to cococonverge/status-envelope-check without…
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in…
wisdom-insights
CocoWisdom insights — invokes Haiku synthesis to produce a structured analysis of project rejection patterns. Carries forward prior thesis and extends it…