devclarityai
- 33 skills
- 0 followers
- 5 hours ago last updated
- ▌ Refactor 2 · devclarityaiRefactor legacy code toward a stated goal, with safety. Use when improving readability, adopting patterns, or reducing coupling while preserving behavior.
- ▌ Code Review 2 · devclarityaiReview a PR diff with focused, actionable feedback. Use when reviewing pull requests, code changes, or when the user asks for a code review.
- ▌ Test Writer 2 · devclarityaiGenerate thorough tests for a function or module. Use when writing tests, adding test coverage, or creating test suites.
- ▌ File Cleaner 2 · devclarityaiImprove readability of a single source file without changing behavior. Use when the user wants to clean up, refactor for readability, or improve code style.
- ▌ Implement It 2 · devclarityaiTurn a user story into a concrete plan, skeletons, and tests. Use when implementing features from user stories, acceptance criteria, or product requirements.
- ▌ Task Creator 2 · devclarityaiBreak a feature spec into sprint-ready engineering tasks. Use when planning features, creating work breakdowns, or splitting work into deliverables.
- ▌
- ▌ Code Explainer 2 · devclarityaiExplain code at a high level and surface gotchas. Use when the user wants to understand what code does, its flow, dependencies, risks, or edge cases.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Create Directory List 2 · devclarityaiInteractively discover monorepo directories and create a JSON list for CLAUDE.md generation
- ▌ Generate Instructions 2 · devclarityaiAnalyze a monorepo directory and generate a CLAUDE.md file with context for Claude Code
- ▌ Create Directory List 3 · devclarityaiDiscover directories and create the tracking JSON for instruction generation.
- ▌ Process Directory List 2 · devclarityaiBatch-process directory-instructions.json to generate CLAUDE.md files in parallel
- ▌ Skill Improver · devclarityai bundleUse when reviewing, grading, critiquing, or improving an existing Claude Code skill or SKILL.md — checks name/scope, invocation description, structure, leanness, and surfaces concrete opportunities to add references, scripts, and determinism.
- ▌ Context Coverage · devclarityai bundleAudit how agent context (CLAUDE.md / AGENTS.md / rules / skills) lines up with the code across a set of repositories and generate a self-contained HTML report — a short list of specific "things to check" (context behind the code, thin coverage for the codebase, oversized files, no per-area context), plus per-repo raw metrics and a folder tree comparing folder LOC to context coverage. Use when the user wants to audit context coverage across repos, "which repos are missing CLAUDE.md", "where is our agent context thin or stale", "context coverage across my org / projects folder", or "/context-coverage". Works on a local folder of clones, a whole GitHub org via the gh CLI, or a single monorepo scoped to just the areas one team owns.
- ▌ Skill Eval Builder · devclarityai bundleUse when the user wants to measure or set up evals/checks for one of their skills — how fast it is, whether its output is valid, whether it fires when expected, or whether its opening classification/routing gate labels inputs correctly.
- ▌ Finding Skill Opportunities · devclarityai bundleUse when asked to find skill opportunities in a codebase, audit a repo for automatable workflows, decide what skills to write, or mine git history, existing automation, and recent Claude Code session transcripts for recurring multi-step procedures worth turning into Claude Code skills.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Create Directory List · devclarityaiInteractively discover monorepo directories and create a JSON list for AGENTS.md generation
- ▌ Generate Instructions · devclarityaiAnalyze a monorepo directory and generate an AGENTS.md file with context for Codex
- ▌ Process Directory List · devclarityaiBatch-process directory-instructions.json to generate AGENTS.md files in parallel