Loading...
Loading...
Found 920 Skills
Run a comprehensive Go-to-Market and launch readiness review for a project phase. Combines marketing content audit, code quality review, performance audit, accessibility audit, infrastructure readiness, and business review with council evaluation. Use before phase launches or when GTM review issues are ready.
RED-GREEN-REFACTOR cycle with strict phase gates. Write failing test first, implement minimum code to pass, then refactor while keeping tests green. Use when implementing new features, fixing bugs with test-first approach, improving test coverage, or when user mentions TDD. Use for "TDD", "test first", "red green refactor", "write tests", or "implement with tests". Do NOT use for debugging existing failures (use systematic-debugging) or for refactoring without new tests (use systematic-refactoring).
Use when any is unavoidable. Use when working with untyped libraries. Use when silencing specific type errors.
Run Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with targeted edits or user decisions.
Full delivery pipeline: plan, build, ship, settle. Covers: shape/spec/design, TDD build, commit, PR creation, PR fix (CI/reviews/conflicts), PR polish, simplify, test coverage, verify ACs, walkthrough, issue management. Use when: shipping features, fixing PRs, creating PRs, building issues, simplifying code, checking quality, writing commits, managing issues. Trigger: /autopilot, /build, /shape, /commit, /issue, /check-quality, /test-coverage, /verify-ac, /pr-walkthrough.
AST-based semantic code search skill for AI agents. Teaches agents to use sqry's 34 MCP tools for finding symbols by structure (functions, classes, types), tracing relationships (callers, callees, imports, inheritance), analyzing dependencies, and detecting code quality issues. Unlike embedding-based search, sqry parses code like a compiler. Supports 37 languages. Uses tiered discovery: start with Quick Tool Selection below, load reference files only when you need parameter details or advanced workflows.
**Mandatory** before any commit or push. Run Definition-of-Done checks from change scope and report exact pass/fail per command.
Use the harem hierarchical code review system to output structured review conclusions based on the division of labor among the Empress, Four Consorts, and Nine Imperial Concubines
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent delegates a code task with 'MODE: MORE_EFFORT', the user selects 'More Effort' code generation mode, or the task explicitly requests iterative refinement for higher code quality. Do NOT use for single-pass code generation (Lite mode), experiment pipeline orchestration (use experiment-pipeline), or diagnosing a specific experiment failure (use experiment-craft).
Generate context-aware code review checklists from PR diffs — tailored to language, codebase patterns, and team standards. Identifies what reviewers should focus on. NOT for automated code fixing, test generation, or security auditing.
Launch an isolated Claude reviewer for the current branch, a specific commit, or uncommitted changes. Uses Claude's agent runtime with worktree isolation so the review has an independent read-only view of the code before findings are reported back.
Follow this sub-process when fixing bugs — turn the verbal description of "problem found" into a closed loop from verification to repair, leaving three documents: problem report, root cause analysis, and repair record. This process adds a buffer between "seeing the problem" and "starting to modify code" to avoid common pitfalls: the problem description in your mind disappears after the fix, you only fix the surface without analyzing the root cause, the scope of repair expands and cannot be traced, and you don't know if the fix is correct without verification after modification. This skill only acts as a router, deciding which of report / analyze / fix to proceed with based on existing artifacts. For simple problems that can be identified at a glance, a fast track will be taken, skipping the two middle steps and only retaining the fix-note.