← all publishers

taylorleese

@taylorleese source repo

Report this profile Claim this profile

• 3 skills
• 0 followers
• 1 week ago last updated

1. ▌
   Ask LLM · taylorleese bundle

   Get a second opinion from a non-Claude frontier model — Codex (OpenAI's coding agent), Antigravity (Google's coding agent), or DeepSeek. Use when the user says "ask Codex", "ask Antigravity", "ask agy", "ask DeepSeek", "get a second opinion", "what would another model say", "sanity-check this with another model", or wants cross-model consensus on code, an architecture decision, or an implementation plan.
   0 installs
2. ▌
   All Docs Improver · taylorleese bundle

   Audit and improve CLAUDE.md, README.md, and docs/**/*.md across a repo. Use when the user asks to audit, check, score, improve, or fix the project's documentation as a whole — not just CLAUDE.md. Scans all doc files, scores each against type-appropriate rubrics, outputs a unified quality report, then makes targeted updates after approval. Delegates CLAUDE.md audits to the `claude-md-management:claude-md-improver` skill.
   0 installs
3. ▌
   Resolve Github Alerts · taylorleese

   Resolve GitHub security alerts — Dependabot, code scanning, and secret scanning — across pip / pip-tools / poetry / uv / npm / yarn / pnpm / cargo / go-modules / Docker / GitHub Actions ecosystems. Use when the user asks to fix, triage, resolve, or clean up security alerts, vulnerable dependencies, CVEs, or failing Dependabot PRs in a repository. Creates a branch and opens a pull request, so invoke it only on a clear request to actually remediate — not when the user is merely asking what the alerts are, or discussing them.
   0 installs