agentleFS
imsovikdeimsovikde/souvik-skills/AGENTS.md

souvik-skills

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

This is the agent guide for Souvik Skills. Before creating or changing a skill, read guidance.md and NAMING.md. Do not create context.md.

  • Commits and pushes

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

44 rules. About 1 is common, 20 are distinctive, and 23 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈20

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 23

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before creating or changing a skill, read guidance.md and NAMING.md.

    line 5
  2. Distinctive:

    Keep every skill folder self-contained and installable.

    line 20
  3. Very specific:

    Keep SKILL.md concise and procedural.

    line 21
  4. Very specific:

    Use only name and description in SKILL.md frontmatter.

    line 22
  5. Very specific:

    Put detailed optional material in references/ and mention when to read it.

    line 24
  6. Very specific:

    Put deterministic automation in scripts/.

    line 25
  7. Very specific:

    Put reusable output assets in assets/.

    line 26
  8. Very specific:

    Keep agents/openai.yaml aligned with SKILL.md.

    line 27
  9. Very specific:

    Ensure interface.default_prompt mentions the skill as $skill-name.

    line 28
  10. Very specific:

    Keep the README catalog and cross-agent NPX install matrix aligned with the skills/ directory.

    line 29
  11. Distinctive:

    After creating or updating a skill for local Codex use, reinstall the updated skill into Codex and remind the user to restart Codex.

    line 30
  12. Common:

    Do not add private traces, generated caches, local logs, or secrets.

    line 31
  13. Distinctive:

    Do not commit changes unless the user explicitly asks.

    line 32
  14. Distinctive:

    When the user explicitly asks to sync GitHub, update NPM/NPX, publish, release, or make the change globally available, follow the GitHub …

    line 33
  15. Very specific:

    Before changing frontend routes, layouts, cards, install modules, copy buttons, logo assets, typography, animation, theme behavior, or …

    line 38
  16. Very specific:

    Update DESIGN.md in the same change when the frontend visual language, typography, layout rules, color system, component styling, or …

    line 39
  17. Very specific:

    Update MOTION.md in the same change when animation tokens, interaction feedback, route transitions, copy feedback, theme motion, …

    line 40
  18. Distinctive:

    Do not hard-code current public skill names as the source of truth for site routing or catalog generation.

    line 42
  19. Very specific:

    After adding, removing, renaming, publishing, or materially updating any public skill, inspect and update the marketplace frontend where …

    line 43
  20. Very specific:

    Keep frontend catalog data derived from skills/, SKILL.md, and agents/openai.yaml.

    line 44
  21. Very specific:

    Keep the install UI aligned with the Project, Global, and Try once command structure in guidance.md and README.md.

    line 46
  22. Distinctive:

    Verify zero horizontal overflow at 360px, 390px, 430px, tablet, desktop, and wide desktop before finishing frontend work.

    line 47
  23. Distinctive:

    After any public skill is added, removed, renamed, published, or materially updated, deploy the rebuilt marketplace to both production …

    line 48
  24. Very specific:

    Run npm run validate:skills and npm run build after landing page or skill catalog updates.

    line 52
  25. Distinctive:

    Add only resources the skill actually needs.

    line 59
  26. Very specific:

    Update README.md with the skill catalog row, project install, global install, try-once command, and example $skill-name prompt.

    line 60
  27. Distinctive:

    Check the frontend marketplace data and pages.

    line 61
  28. Very specific:

    Run npm run build when the new skill changes the public marketplace output.

    line 68
  29. Distinctive:

    Add tests or examples when the skill includes scripts or deterministic behavior.

    line 70
  30. Distinctive:

    When changing a skill:

    line 74
  31. Distinctive:

    Update README.md if the public catalog, install commands, or usage prompts change.

    line 77
  32. Distinctive:

    Update the frontend helpers or pages if the skill update changes categories, resources, commands, public copy, routing, or install behavior.

    line 78
  33. Very specific:

    Update package.json only when package metadata or CLI behavior changes.

    line 79
  34. Distinctive:

    Run validation before finishing.

    line 82
  35. Distinctive:

    Use this protocol when the user explicitly asks to commit, push, sync GitHub, publish, release, update NPM, update NPX, or make a skill …

    line 86
  36. Distinctive:

    Keep the worktree scoped. Do not stage unrelated user files or untracked skill folders unless they are part of the request.

    line 90
  37. Distinctive:

    Run the relevant checks before publishing:

    line 91
  38. Distinctive:

    Run any relevant skill-specific audit or script, such as:

    line 100
  39. Distinctive:

    If the change is meant for immediate local Codex use, reinstall the changed skill and remind the user to restart Codex:

    line 107
  40. Distinctive:

    Create a signed Conventional Commit when signing is configured, verify the local signature, then push to main.

    line 113
  41. Very specific:

    After pushing, open or inspect the GitHub commit and confirm GitHub marks it as verified.

    line 121
  42. Very specific:

    When the user has asked for NPM/NPX/package sync, merge the clean Release Please PR after checks pass.

    line 123
  43. Very specific:

    If the package changed but Release Please does not open a release PR, check the commit type.

    line 137
  44. Very specific:

    Do not commit NPM, GitHub, Vercel, Cloudflare, or other secrets.

    line 141

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS

This is the agent guide for Souvik Skills.

Before creating or changing a skill, read guidance.md and NAMING.md. Do not create context.md.

Repository Facts

  • Brand: Souvik Skills
  • Owner: Souvik Dey
  • GitHub owner: imsovikde
  • Repository: imsovikde/souvik-skills
  • NPM package: @imsovikde/skills
  • License: MIT
  • Current public skill names are derived from the skills/ directory, not hard-coded in this guide.

Agent Rules

  1. Before creating, updating, publishing, or deploying a public skill, read this entire AGENTS.md, then read the repository Markdown guidance that applies to the change: root-level *.md, docs/**/*.md, the changed skill's SKILL.md, and any changed or referenced skill references/**/*.md or assets/**/*.md templates. For broad catalog or deployment work, also inspect all public skills/**/SKILL.md files so the catalog remains coherent.
  2. Keep every skill folder self-contained and installable.
  3. Keep SKILL.md concise and procedural.
  4. Use only name and description in SKILL.md frontmatter.
  5. Make the skill folder name exactly match the frontmatter name.
  6. Put detailed optional material in references/ and mention when to read it.
  7. Put deterministic automation in scripts/.
  8. Put reusable output assets in assets/.
  9. Keep agents/openai.yaml aligned with SKILL.md.
  10. Ensure interface.default_prompt mentions the skill as $skill-name.
  11. Keep the README catalog and cross-agent NPX install matrix aligned with the skills/ directory.
  12. After creating or updating a skill for local Codex use, reinstall the updated skill into Codex and remind the user to restart Codex.
  13. Do not add private traces, generated caches, local logs, or secrets.
  14. Do not commit changes unless the user explicitly asks.
  15. When the user explicitly asks to sync GitHub, update NPM/NPX, publish, release, or make the change globally available, follow the GitHub And NPM Sync Protocol end to end instead of stopping after local edits.
  16. Every repository commit must be verified before reporting completion: create a signed commit when signing is configured, confirm git log -1 --show-signature locally, confirm the GitHub commit page shows a verified signature after push, and confirm the pushed branch contains the intended tree. Do not substitute unsigned API commits for signed local commits when the user asks for verified commits.

Landing Page Maintenance

  • Before changing frontend routes, layouts, cards, install modules, copy buttons, logo assets, typography, animation, theme behavior, or responsive behavior, read DESIGN.md and MOTION.md completely and treat them as the implementation contract. If a user says notion.md while discussing site motion, read and update MOTION.md.
  • Update DESIGN.md in the same change when the frontend visual language, typography, layout rules, color system, component styling, or responsive behavior materially changes.
  • Update MOTION.md in the same change when animation tokens, interaction feedback, route transitions, copy feedback, theme motion, reduced-motion behavior, or motion QA rules materially change.
  • The Next.js marketplace derives public skill pages from the skills/ directory at build time.
  • Do not hard-code current public skill names as the source of truth for site routing or catalog generation.
  • After adding, removing, renaming, publishing, or materially updating any public skill, inspect and update the marketplace frontend where needed so /, /skills, /skills/<skill-name>, /install, and /docs reflect the current skills/ content and install model.
  • Keep frontend catalog data derived from skills/, SKILL.md, and agents/openai.yaml; add or adjust shared inference/helpers when a new skill domain, resource shape, or install surface is introduced.
  • Preserve independent pages for /, /skills, /skills/<skill-name>, /install, /docs, and /motion.
  • Keep the install UI aligned with the Project, Global, and Try once command structure in guidance.md and README.md.
  • Verify zero horizontal overflow at 360px, 390px, 430px, tablet, desktop, and wide desktop before finishing frontend work.
  • After any public skill is added, removed, renamed, published, or materially updated, deploy the rebuilt marketplace to both production targets and verify the changed skill appears on Vercel and Cloudflare Pages:
    • Vercel: https://souvik-skills.vercel.app
    • Cloudflare Pages: https://souvik-skills.pages.dev
    • Required routes: /, /skills, /skills/<skill-name>, /install, and /docs.
  • Run npm run validate:skills and npm run build after landing page or skill catalog updates.

Creating A New Skill

  1. Choose a name using NAMING.md.
  2. Create skills/<skill-name>/SKILL.md.
  3. Create skills/<skill-name>/agents/openai.yaml.
  4. Add only resources the skill actually needs.
  5. Update README.md with the skill catalog row, project install, global install, try-once command, and example $skill-name prompt.
  6. Check the frontend marketplace data and pages. Update shared frontend helpers when the new skill adds a category, nested resources, install behavior, or public content shape not already represented.
  7. Run:
npm run validate:skills
  1. Run npm run build when the new skill changes the public marketplace output.
  2. Deploy and verify both hosted sites when the skill is public: Vercel and Cloudflare Pages must show the new skill before the task is done.
  3. Add tests or examples when the skill includes scripts or deterministic behavior.

Updating Existing Skills

When changing a skill:

  • Preserve its public install name unless the user explicitly approves a rename.
  • Update README.md if the public catalog, install commands, or usage prompts change.
  • Update the frontend helpers or pages if the skill update changes categories, resources, commands, public copy, routing, or install behavior.
  • Update package.json only when package metadata or CLI behavior changes.
  • Reinstall the updated skill into Codex when the change is meant for immediate local use.
  • Redeploy and verify both hosted sites when the update changes public skill content or marketplace pages.
  • Run validation before finishing.

GitHub And NPM Sync Protocol

Use this protocol when the user explicitly asks to commit, push, sync GitHub, publish, release, update NPM, update NPX, or make a skill globally available.

This is a professional release workflow, not a memory-only habit. Future agents must use it whenever package sync is requested so GitHub, GitHub Releases, NPM, GitHub Packages, NPX install paths, and the local Codex copy stay aligned.

  1. Keep the worktree scoped. Do not stage unrelated user files or untracked skill folders unless they are part of the request.
  2. Run the relevant checks before publishing:
npm run validate:skills
npm test
npm run build
npm pack --dry-run
  1. Run any relevant skill-specific audit or script, such as:
npm run audit:gh-ready
npm run audit:motioncraft
  1. If the change is meant for immediate local Codex use, reinstall the changed skill and remind the user to restart Codex:
node bin/souvik-skills.cjs install <skill-name> --force
  1. Create a signed Conventional Commit when signing is configured, verify the local signature, then push to main. Example:
git commit -m "feat: upgrade <skill-name> ..."
git log -1 --show-signature
git push origin main
  1. After pushing, open or inspect the GitHub commit and confirm GitHub marks it as verified. Then verify GitHub Actions for CI, CodeQL, and Release Please.
  2. Release Please opens or updates a release PR. Inspect it before merging. It should only contain release metadata such as package.json, package-lock.json, .release-please-manifest.json, and CHANGELOG.md.
  3. When the user has asked for NPM/NPX/package sync, merge the clean Release Please PR after checks pass. Resolve generated changelog conflicts carefully and keep one clean release entry.
  4. Confirm the release automation publishes successfully to NPM and GitHub Packages. Verify with:
npm view @imsovikde/skills version
npx -y @imsovikde/skills@latest list
  1. Smoke-test the published package when a skill changed:
npx -y @imsovikde/skills@latest install <skill-name> --dest <temp-dir> --force
  1. If the package changed but Release Please does not open a release PR, check the commit type. Use a release-triggering Conventional Commit such as feat: or fix: when the package contents must reach NPM/NPX.
  2. Deploy the current main build to Vercel and Cloudflare Pages when public frontend or skill catalog output changed. Manually verify both hosted domains include the changed skill on /, /skills, /skills/<skill-name>, /install, and /docs; use a browser or HTTP fetch against the live domains, not only local build output.
  3. Finish only after reporting the signed GitHub commit and verification status, release PR or release URL, NPM version, package publish status, Vercel deployment status, Cloudflare Pages deployment status, local Codex reinstall status, and any check that could not be run.

Do not commit NPM, GitHub, Vercel, Cloudflare, or other secrets. Use the existing GitHub Actions release automation; manual npm publish is only a fallback when the user explicitly asks and automation cannot complete.

Release Readiness

A change is release-ready only when:

  • Skill validation passes.
  • Relevant tests pass.
  • Install commands still work.
  • Documentation reflects the current skill names.
  • Vercel and Cloudflare Pages show the current public skill catalog when frontend or skill content changed.
  • License and ownership information remain intact.
  • Release Please and package publishing are verified when the user requested NPM/NPX sync.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.