account-research
Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect…
Triage and address GitHub PR review comments systematically—classify, respond, fix or defer with rationale. Use when a PR has review feedback, requested changes, or unresolved threads.
Claude Code
$ npx -y skills add charlieviettq/awesome-agent-skill --skill github-comment-triage --agent claude-code
Codex
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a codex -y
Cursor
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a cursor -y
Gemini CLI
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a gemini-cli -y
GitHub Copilot
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a github-copilot -y
OpenCode
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a opencode -y
Windsurf
$ npx skills add charlieviettq/awesome-agent-skill --skill github-comment-triage -a windsurf -y
name: github-comment-triage description: "Triage and address GitHub PR review comments systematically—classify, respond, fix or defer with rationale. Use when a PR has review feedback, requested changes, or unresolved threads." allowed-tools: Read, Glob, Grep
1. **Collect** all open review threads and inline comments (not just summary). 2. **Classify** each item:
3. **Order** must-fix first, then should-fix, then discuss. 4. **Implement** with minimal scoped changes; one logical commit per theme when possible. 5. **Reply** on each thread: what changed, where, or why deferred (link issue if deferred). 6. **Re-verify** tests/lint before requesting re-review.
Fixed in abc123 — [brief what changed]
Deferred: tracked in #NNN — [reason and scope boundary]
Checklist table: comment | action | status | note.
Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).
Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect…
Evaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when…
Design agent tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining…
\"Implement and select ad bidding strategies from manual CPC to automated target-CPA and target-ROAS. Use this skill when the…
\"Optimize advertising budget allocation across campaigns using marginal returns analysis. Use this skill when the user needs to…
\"Build CTR prediction models for estimating ad click-through rates from features. Use this skill when the user needs to predict…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.