Skip to content

Instruction-only agent skills

2,929 instruction-only agent skills, out of 3,419 agent skills listed. These skills contain instructions and reference files but no scripts, so they run no code of their own. Each one lists the tools it asks for and how to install it in Claude Code, Codex, Cursor and other agents.

Showing 2,851–2,880 of 2,929

  1. Rules for structuring Vue 3 components so humans can read and maintain them

    • Open source
    • 28 GitHub stars
  2. Server state and data fetching in Vue 3

    • Open source
    • 28 GitHub stars
  3. Debug Vue 3 apps

    • Open source
    • 28 GitHub stars
  4. Forms and validation in Vue 3

    • Open source
    • 28 GitHub stars
  5. Diagnose and fix Vue 3 performance problems

    • Open source
    • 28 GitHub stars
  6. Review Vue and Nuxt code changes

    • Open source
    • 28 GitHub stars
  7. Build Vue interfaces with component libraries

    • Open source
    • 28 GitHub stars
  8. Upgrade Vue projects across major versions

    • Open source
    • 28 GitHub stars
  9. Check planned AI coding actions and patches against explicit project constraints through SpecLock MCP tools

    • Open source
    • 26 GitHub stars
  10. Check planned AI coding actions and patches against explicit project constraints with SpecLock

    • Open source
    • 26 GitHub stars
  11. Detect, activate, or deactivate bundled knowledge patches.

    • Open source
    • 25 GitHub stars
  12. Report bundled patch versions, activation state, age, and missing artifacts.

    • Open source
    • 25 GitHub stars
  13. Route technology work to matching bundled knowledge patches.

    • Open source
    • 25 GitHub stars
  14. Two-layer AI-tell audit of any text — deterministic scanner (lexicon, constructions, stylometry with line numbers) plus a blind semantic jud

    • Open source
    • 25 GitHub stars
  15. One brief, N posts, N genuinely different people — voice-isolated writers, cross-post overlap detection, per-post verification receipts

    • Open source
    • 25 GitHub stars
    • Marketing and SEO
  16. Rewrite existing text so it reads human — either scrubbed-and-souled in its own register, or fully re-voiced as one of the roster's people

    • Open source
    • 25 GitHub stars
  17. Front door and router for the idiolect voice engine

    • Open source
    • 25 GitHub stars
  18. Build and maintain the user's OWN voice profile from continuously captured writing plus explicit samples — status, build/refresh, add sample

    • Open source
    • 25 GitHub stars
  19. Create a new voice profile — from a writing corpus (measured, not vibed), or invented to fill a gap in the roster

    • Open source
    • 25 GitHub stars
  20. Write a social post in one of the roster's voices (or the user's own `self` voice) — platform-native, craft-floored, scanner-verified

    • Open source
    • 25 GitHub stars
  21. Creates and manages isolated cloud sandboxes (secure code execution environments with dedicated runtimes) on the Daytona platform, through t

    • Open source
    • 23 GitHub stars
  22. Run builds, tests, and other tooling inside a reproducible, containerized dev environment via the `ilo` CLI instead of on the host

    • Open source
    • 21 GitHub stars
  23. LOG-UFPB's internal quick reference (group conventions, recommended tools, solvers and caveats from the group's own experience)

    • Open source
    • 21 GitHub stars
  24. Use when items need categorical triage (critical/warning/ok), not numeric scoring

    • Open source
    • 14 GitHub stars
  25. Use when you want to stress-test a proposal, plan, or findings before acting on them

    • Open source
    • 14 GitHub stars
  26. Use when a goal is too large to tackle as one unit

    • Open source
    • 14 GitHub stars
  27. Use when deciding between two approaches and you need a structured tradeoff comparison

    • Open source
    • 14 GitHub stars
  28. Use when you want to browse available skills or find the right pipeline for a workflow

    • Open source
    • 14 GitHub stars