🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills with bunx/npx skills.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: apply SOLID principles to make object-oriented code flexible and maintainable.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: write or review correct, set-based SQL with safe parameters and sensible indexing.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: choose and structure client state so data stays consistent and predictable.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: emit structured, queryable logs with the right levels, context, and no sensitive data.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: orchestrate specialized subagents to handle distinct parts of one larger task.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: write or review idiomatic Swift with value types, optionals, and safe concurrency.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: a bug is unclear and you need a hypothesis-driven loop instead of random edits.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: implement a design system in Tailwind with tokens, variants, and consistent components.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: explain code or a concept at the right depth for the asker, not a generic lecture.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: implement a change with a TDD loop — failing test first, minimal fix, verify, refactor.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: systematically identify threats to a system and decide how to mitigate them.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: break a plan, spec, or PRD into independently grabbable implementation issues.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: turn current conversation and repo context into a PRD for an issue tracker.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: configure a Turborepo monorepo with task pipelines, caching, and affected-only runs.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: model complex APIs with discriminated unions, conditional, and template literal types.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: write or review TypeScript that maximizes type safety without fighting the compiler.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: onboard onto an unfamiliar or large codebase by mapping its structure, dependencies, and business logic before editing.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: starting feature work that should be isolated from the current checkout or branch.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: design composable React component APIs that scale without boolean prop sprawl.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: write or review React/Next.js code for performance — waterfalls, re-renders, bundle size.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: about to claim work is complete, fixed, passing, or ready for commit or PR.
kimtth/agent-skill-100-lines-or-less
Skill Claude CodeCodex
Use when: answer questions about a video URL or local file by seeing its frames and reading its transcript.
kimtth/agent-skill-100-lines-or-less
Skill Claude Code
Use when: review UI code, audit accessibility, check UX, or compare a site against current Web Interface Guidelines.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: