Loading...
Loading...
Found 141 Skills
Deterministic 3-phase GitHub PR review comment extraction: Authenticate, Mine, Validate. Use when mining tribal knowledge from PR reviews, extracting coding standards from review history, or building datasets for the Code Archaeologist agent. Use for "mine PRs", "extract review comments", "tribal knowledge", or "PR review history". Do NOT use for analyzing patterns, generating rules, or interpreting comments — that is the Code Archaeologist agent's responsibility.
Collaborative coding with enforced micro-steps: announce, show diff, wait for confirmation, apply, verify. User controls pace with commands. Works with any domain agent as the executor. Use when: "pair program", "pair with me", "let's code together", "step by step coding", "walk me through implementing", "code with me"
Create structural blueprints for blog posts before writing. Analyzes topic briefs, selects structure templates, generates outlines with word counts and section summaries. Use when planning a new post, brainstorming structure, or deciding scope before drafting. Use for "outline", "plan post", "structure this topic", "how should I organize". Do NOT use for writing actual post content, editing existing posts, or SEO keyword planning.
Run TypeScript type checking with tsc --noEmit and parse errors into actionable, file-grouped output. Use when validating TypeScript code before commits, after refactors, or when checking for type regressions. Use for "type check", "tsc", "TypeScript errors", "type validation", or pre-commit TypeScript verification. Do NOT use for linting, test execution, runtime errors, or JavaScript-only projects without tsconfig.json.
Perses-aware code review: check Go backend against Perses patterns, React components against Perses UI conventions, CUE schemas against plugin spec, and dashboard definitions against best practices. Dispatches appropriate sub-reviewers. Use for "review perses", "perses pr", "perses code review". Do NOT use for general Go/React review without Perses context.
RED-GREEN-REFACTOR testing for agents: dispatch subagents with known inputs, capture verbatim outputs, verify against expectations. Use when creating, modifying, or validating agents and skills. Use for "test agent", "validate agent", "verify agent works", or pre-deployment checks. Do NOT use for feature requests, simple prompt edits without behavioral impact, or agents with no structured output to verify.
Analyze and optimize blog post SEO: keywords, titles, meta descriptions, headers, and internal linking. Use when user says "check seo", "optimize for search", "improve search visibility", or when publishing a new post that needs search optimization. Do NOT use for writing new content, major content edits, or site-wide technical SEO (robots.txt, sitemaps).
Systematic 4-phase codebase exploration: Detect, Explore, Map, Summarize. Use when starting work on an unfamiliar codebase, onboarding to a new project, reviewing a repository for the first time, or building context before debugging or code review. Use for "explore codebase", "what does this project do", "understand architecture", or "onboard me". Do NOT use for modifying files, running applications, performance optimization, or deep domain analysis.
Run Go quality checks via make check with intelligent error categorization and actionable fix suggestions. Use when user requests "run quality checks", "check PR quality", "verify code quality", or "run make check". Use before creating commits or during PR review. Do NOT use for non-Go repositories, repositories without a Makefile, or manual linter invocation.
Perses project lifecycle management: create, list, switch, and configure projects. Manage RBAC with roles and role bindings per project. Uses MCP tools when available, percli CLI as fallback. Use for "perses project", "create project", "perses rbac", "perses roles", "perses permissions". Do NOT use for dashboard creation (use perses-dashboard-create).
Restore session state from handoff artifacts and route to the next action. Priority cascade: HANDOFF.json (highest) > .continue-here.md > incomplete task_plan.md > git log. Presents a status dashboard, then executes the next action. Use for "resume", "continue", "pick up where I left off", "what was I doing", "continue work". Do NOT use for starting new tasks (use /do), reviewing past sessions (use /retro), or reading task plans (read task_plan.md directly).
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).