Skip to content
cccskills
FreePublished on GitHub

create-repo-skill

Create or update skills using OpenSEO's repository conventions. Keep one canonical source, distinguish internal and public workflows, maintain Claude Code links, and register public skills in documentation, the in-app agent, and plugin bundles.

OriginalShow the original description

Create or update a skill in this repository the right way — canonical home in .agents/skills, internal-vs-public marking, symlink mirroring into .claude/skills, and public docs registration for product skills. Use whenever adding a new skill, converting a workflow into a skill, or when .claude/skills and .agents/skills look out of sync.

See how to install

Good for

  • Add a new skill to the OpenSEO repository
  • Turn a development workflow into an internal skill
  • Repair drift between skill directories
  • Register a public skill in docs and plugins

Files included (1)

  • SKILL.md5.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Create a repo skill

The layout (invariants)

  • .agents/skills/<kebab-name>/SKILL.md is the only canonical home for every skill — public product skills (SEO workflows customers install) and internal repo skills (agent workflows like merge-ready, papercuts, this one) alike. Users install from this tree via npx skills add every-app/open-seo.
  • .claude/skills/ contains only symlinks into .agents/skills/ — one per skill that Claude Code agents working in this repo should auto-load. Never copy files: .agents/skills/ is prettier-ignored (vendored skills are hash-pinned) while .claude/skills/ is not, so a copy gets reformatted on the .claude side and the trees drift — this happened to three skills before symlinks became the rule. prettier --check . does not descend into the symlinks, so a symlink stays byte-identical to its canonical source by construction.
  • Vendored skills (external origin) are hash-pinned in skills-lock.json (created by the skills CLI on first vendor). Never hand-edit a vendored skill's content; re-vendor with the skills CLI so the lock hash stays valid.
  • .agents/skills/** is part of the review control plane (see AGENTS.md): changes require explicit maintainer review via CODEOWNERS. Make the change on a branch and call it out in the PR — never treat skill edits as incidental.

Creating a skill

  1. mkdir .agents/skills/<kebab-name> and write SKILL.md with frontmatter:

    ---
    name: <kebab-name>            # must match the directory name
    description: <what it does + explicit "use when ..." triggers>
    metadata:
      internal: true              # ONLY for internal repo skills — omit for product skills
    ---
    
  2. Decide which kind it is:

    • Internal repo skill (agent/dev workflow): set metadata.internal: true. Do NOT register it on any public surface. If repo agents should auto-load it, add the mirror symlink:

      ln -s ../../.agents/skills/<name> .claude/skills/<name>
      
    • Public product skill (a customer-facing SEO workflow): no internal flag, usually no .claude/skills symlink (repo agents don't need customer workflows). A public skill is auto-served to SAM, the live in-app agent — the marking is fail-open, so a missing internal: true ships repo-dev instructions to end users. Give it the standard "Project context" preamble (copy a sibling like seo-audit) with the skill's required sections, and register it everywhere users discover skills:

      • src/server/features/sam/samSkills.test.ts — add the name to the pinned public roster (the test fails otherwise; that failure is the guard)
      • web/content/docs/skills/<name>.mdx — docs page (mirror a sibling like competitor-analysis.mdx: what it does, when to use it, what you get back, how to get the best result)
      • web/content/docs/skills/index.md — bullet in the right workflow section
      • web/content/docs/skills/meta.json — nav entry
      • src/routes/_app/ai.tsx — SKILL_NAMES
      • .agents/skills/seo-coach/SKILL.md — one line in the "What each workflow does" roster
      • plugins/openseo/skills/<name> — add the skill to the skills list in scripts/sync-plugin-skills.mjs, then run pnpm sync-plugin-skills (this directory holds real copies, not symlinks — the Claude Code and Codex plugins bundle from here, and Codex's installer silently skips symlinked files, so a symlink would ship a skill-less plugin). pnpm ci:check re-runs the sync and fails on drift, so a missed update here is caught, but the skill count and roster below are prose and aren't checked — update them by hand: both plugins/openseo/*/plugin.json description fields, the Codex manifest's interface.longDescription, and the skill lists in web/content/docs/claude-code-plugin.md and web/content/docs/codex-plugin.md
      • Optional: web/src/lib/feature-pages.ts and web/content/docs/skills/setup.md if it deserves marketing/setup placement
  3. If the skill references MCP tools, use exact tool names and keep them in sync with src/server/mcp/server.ts — the tool names in skills are load-bearing for agents following them. For public skills also check src/server/features/sam/samChatTools.ts: SAM's toolset is a curated subset, and a skill step that names a tool SAM lacks dead-ends in the in-app agent.

  4. pnpm format:write (covers the docs pages; .agents/skills itself is intentionally untouched), then commit. Skill prose follows openseo-review-web-content standards when public.

Sync check (run when in doubt, and after any skill change)

for d in .claude/skills/*/; do n=$(basename "$d")
  [ -L "${d%/}" ] || echo "DRIFT RISK — not a symlink: $n"
  [ -e ".agents/skills/$n" ] || echo "BROKEN — no canonical source: $n"
done

Anything flagged: move the canonical content to .agents/skills/<name>/ (reconciling differences deliberately — diff both sides first, newest intent wins), delete the .claude copy, and replace it with the symlink.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Research questions about a market, examine recorded ChatGPT answers and cited websites, and identify themes where a brand appears or is missing. Receive ranked prompt groups and suggested questions for future tracking.

  • Finding question themes related to a product category
  • Checking brand mentions and cited websites
  • Identifying themes with limited brand visibility
every-app/open-seo24.1KUpdated Oct 14, 2026

Audit how a brand appears in AI answers by examining mentions, website citations, competitors, and cited pages. Receive one to three evidence-based priorities, such as improving a page, seeking inclusion in a relevant source, or fixing access barriers.

  • Investigate why AI answers recommend competitors
  • Check brand mentions and website citations
  • Prioritize pages to improve or create
every-app/open-seo24.1KUpdated Oct 14, 2026

Compare several competitors to see which sites lead a search market, what content earns rankings, and where opportunities remain. The report covers keyword reach, links from other sites, and practical next steps.

  • Identifying leading sites in a search market
  • Comparing competitors' successful content themes
  • Finding underserved topics to target
every-app/open-seo24.1KUpdated Oct 14, 2026

Analyze a named competitor's unpaid search traffic, ranking keywords, content themes, and links from other websites. Identify strengths, weaknesses, and relevant opportunities, with an optional comparison to your own site and a report of recommended actions.

  • Investigate a specific competitor's SEO strengths
  • Find pages and keywords worth targeting
  • Compare a competitor with your own site
every-app/open-seo24.1KUpdated Oct 14, 2026

deslop

FreeSummary

Edit blog posts, documentation, marketing copy, and PR descriptions to remove formulaic AI writing patterns. Replace filler, vague claims, and staged emphasis with plain statements while preserving concrete details and the writer's voice.

  • Editing AI-drafted blog posts
  • Removing wordy introductions from documentation
  • Toning down exaggerated marketing copy
every-app/open-seo24.1KUpdated Oct 14, 2026

evaluate-skill

FreeSummary

Evaluate changes to OpenSEO skills by running fresh Codex sessions against a local backend. Compare saved reports using weighted criteria, then inspect tool logs to understand failures and check whether revised instructions improve output.

  • Comparing report quality before and after skill edits
  • Checking revised instructions across different websites
  • Scoring SEO audit reports against defined criteria
every-app/open-seo24.1KUpdated Oct 14, 2026

See all skills by every-app

Report a problem with this skill