Skip to content

Arnie016/codex-prompt-templates / skills/auto-skill-trend-github-discovery-radar

auto-skill-trend-github-discovery-radar

Verified

Verify current GitHub and agent-skill ecosystem evidence before using trend, popularity, star, topic, or public-discoverability claims in Codex skill and plugin work. Use when an automation asks for trend evidence, GitHub discovery, repo stars/forks/activity, launch topics, marketplace positioning, or latest agent-skill/MCP ecosystem claims. Skip when the task only needs local source synthesis or a single trusted repo brief.

GitHub Discovery Radar

Generated by: Codex Supercharge maintenance automation.

Goal: keep public launch, trend, and popularity claims dated, source-backed, and separate from local source-pattern synthesis.

Workflow

  1. State the claim before searching: repo exists, topic is discoverable, project is popular, ecosystem trend is current, or README wording is justified.

  2. Check official docs first for stable mechanics such as skill format, topic discovery, and repository search qualifiers.

  3. Check exact repositories with GitHub API or GitHub pages before using star, fork, issue, license, pushed, or updated numbers.

  4. For this pack's public repository evidence, refresh the dated radar entry:

    make -C plugins/codex-supercharge refresh-discovery-radar
    
  5. Run at least one narrow topic/query search and one exact-name or exact-phrase search; broad GitHub searches are noisy and must not become ranking claims.

  6. Classify each finding as verified, unverified, noisy, or inspiration-only.

  7. For any fresh repo, installer, MCP server, downloaded binary, hook, or account tool, stop at read-only evidence and route through $sandbox-source-intake and $mcp-safety-review before execution.

  8. Write durable dated findings to plugins/codex-supercharge/references/github-discovery-radar.md.

Commands

python3 plugins/codex-supercharge/scripts/refresh_github_discovery_radar.py \
  --plugin-root plugins/codex-supercharge \
  --write

curl -sS -H 'Accept: application/vnd.github+json' \
  https://api.github.com/repos/OWNER/REPO

curl -sS -G -H 'Accept: application/vnd.github+json' \
  --data-urlencode 'q=topic:agent-skills codex' \
  --data-urlencode 'sort=stars' \
  --data-urlencode 'order=desc' \
  --data-urlencode 'per_page=10' \
  https://api.github.com/search/repositories

Use python3 -m json.tool or a tiny Python one-liner to inspect JSON without installing dependencies.

Skip When

  • The request only compares already-cloned local repos; use $auto-skill-build-source-pattern-synthesis.
  • The request is a one-repo architecture/setup brief; use $repo-intelligence-brief.
  • The user is asking to publish or sync a known repo, not verify current trend evidence; use $auto-skill-ops-supercharge-maintenance-pass.

References

  • plugins/codex-supercharge/references/github-discovery-radar.md
  • plugins/codex-supercharge/DISCOVERY.md
  • Official Codex skills docs: https://developers.openai.com/codex/skills
  • GitHub repository topics docs: https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/classifying-your-repository-with-topics
  • GitHub repository search docs: https://github.com/github/docs/blob/main/content/search-github/searching-on-github/searching-for-repositories.md

Validation

python3 "$HOME/.codex/skills/.system/skill-creator/scripts/quick_validate.py" plugins/codex-supercharge/skills/auto-skill-trend-github-discovery-radar
plugins/codex-supercharge/scripts/skill_audit.sh --strict plugins/codex-supercharge/skills
python3 plugins/codex-supercharge/scripts/refresh_github_discovery_radar.py --plugin-root plugins/codex-supercharge

Every trend-backed note must include the retrieval date, source URL, exact query or repo checked, and a claim classification.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall