Loading...
Loading...
Found 149 Skills
Post-mortem diagnostic analysis of failed or stuck workflows. Detects stuck loops, missing artifacts, abandoned work, scope drift, and crash/interruption patterns through git history and plan file analysis. Produces a structured diagnostic report with anomaly confidence levels, root cause hypotheses, and recommended remediation. READ-ONLY: never modifies files. Use for "forensics", "what went wrong", "why did this fail", "stuck loop", "diagnose workflow", "post-mortem", "workflow failure", or "session crashed". Do NOT use for debugging code bugs (use systematic-debugging), reviewing code quality (use systematic-code-review), or fixing issues (forensics only diagnoses).
Run Python (ruff) and JavaScript (Biome) linting, formatting, and code quality checks with auto-fix support. Use when code needs linting, formatting, or style checking before commits. Use for "lint", "format", "ruff", "biome", "code style", or "check quality". Do NOT use for comprehensive code review (use systematic-code-review).
Deterministic 4-phase documentation drift detector: Scan, Cross-Reference, Detect, Report. Use when skills/agents/commands are added, removed, or renamed, when README files seem outdated, or before committing documentation changes. Use for "check docs", "sync README", "documentation audit", or "stale entries". Do NOT use for writing documentation content, improving descriptions, or generating new README files.
Go error handling patterns: wrapping with context, sentinel errors, custom error types, errors.Is/As chains, and HTTP error mapping. Use when implementing error returns, defining package-level errors, creating custom error types, wrapping errors with fmt.Errorf, or checking errors with errors.Is/As. Use for "error handling", "fmt.Errorf", "errors.Is", "errors.As", "sentinel error", "custom error", or "%w". Do NOT use for general Go development, debugging runtime panics, or logging strategy.
Validate-then-fix workflow for PR review comments: Fetch, Validate, Plan, Fix, Commit. Use when user wants to address PR feedback, fix review comments, or resolve reviewer requests. Use for "fix PR comments", "address review", "pr-fix", or "resolve feedback". Do NOT use for creating PRs, reviewing code without fixing, or general debugging unrelated to PR comments.
Statistical rule discovery through measurement of Go codebases: Count patterns, derive confidence-scored rules, produce Style Vector fingerprint. Use when analyzing codebase conventions, extracting implicit coding rules, profiling a repo before onboarding or PR automation. Use for "analyze codebase", "find coding patterns", "what conventions does this repo use", "extract rules", or "codebase DNA". Do NOT use for code review, bug fixes, refactoring, or performance optimization.
Go testing patterns and methodology: table-driven tests, t.Run subtests, t.Helper helpers, mocking interfaces, benchmarks, race detection, and synctest. Use when writing new Go tests, modifying existing tests, adding coverage, fixing failing tests, writing benchmarks, or creating mocks. Triggered by "go test", "_test.go", "table-driven", "t.Run", "benchmark", "mock", "race detection", "test coverage". Do NOT use for non-Go testing (use test-driven-development instead), debugging test failures (use systematic-debugging), or general Go development without test focus (use golang-general-engineer directly).
Deterministic API endpoint validation with structured pass/fail reporting. Use when endpoints need smoke testing, health checks are required before deployment, or CI/CD pipelines need HTTP validation gates. Use for "validate endpoints", "check api health", "api smoke test", or "are endpoints working". Do NOT use for load testing, browser testing, full integration suites, or OAuth/complex authentication flows.
First-time Perses setup pipeline: discover or deploy server, configure MCP connection, create initial project, add datasources, and verify connectivity. 4-phase pipeline: DISCOVER, CONNECT, CONFIGURE, VALIDATE. Use when setting up Perses for the first time, connecting Claude Code to an existing Perses instance, or onboarding a new team to Perses. Use for "perses onboard", "setup perses", "connect to perses", "perses getting started". Do NOT use for dashboard creation (use perses-dashboard-create) or server deployment details (use perses-deploy).
Fresh-subagent-per-task execution with two-stage review (ADR compliance + code quality). Use when an implementation plan exists with mostly independent tasks and you want quality gates between each. Use for "execute plan", "subagent", "dispatch tasks", or multi-task implementation runs. Do NOT use for single simple tasks, tightly coupled work needing shared context, or when the user wants manual review after each task.
Deterministic plan lifecycle management via scripts/plan-manager.py: create, track, check, complete, and abandon task plans. Use when user says "/plans", needs to create a multi-phase plan, track progress on active plans, or manage plan lifecycle (complete, abandon, audit). Do NOT use for one-off tasks that need no tracking, feature implementation, or debugging workflows.
Question-only debugging mode that guides users to find root causes themselves through structured questioning. Never gives answers directly. Escalates to systematic-debugging after 12 questions if no progress. Use when: "rubber duck", "help me think through this bug", "debug with me", "walk me through debugging", "socratic debug", "think through this issue"