Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration) and cross-model external reviewers (GPT, Gemini, Grok) until convergence, then produce a comprehensive ELI10 convergence report. Output is a spec tagged review-convergence — one of the two tags /instar-dev requires before it will touch instar source. NOT user-invocable; run by the instar-developing agent before any spec-driven /instar-dev work.
**Version / slug:** `instar-dev-skill`
**Version / slug:** `pr-gate-phase-a-commit-6-rollback-skill`
B2B/B2C marketing operating system for AI startups. Covers onboarding, customer segmentation, competitor boards, X/Twitter growth, cold email, content planning, and weekly KPI review.
Implements Syncfusion .NET MAUI Rating (SfRating) control. Use when implementing star ratings, review systems, feedback mechanisms, or product ratings in MAUI apps. Covers rating control configuration, star rating, half-star rating, custom rating shapes, rating precision, and rating events.
Reads and analyzes source code files or project structures, identifies bugs, and suggests structural architectural or security improvements.
Take a spec produced by `brainstorm-beagle` and close its remaining gaps — both the explicit Open Questions and the latent ones the self-review missed — by researching, proposing answers, and rewritin
Turn a sharp research question into cited, gap-flagged findings by delegating to parallel web-search subagents.
Optimize prompts for code-related tasks following Claude best practices. Use when refining prompts for implementation, debugging, refactoring, code review, or testing.
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
Respond to review comments on a PR after evaluation and fixes
Schema for tracking code review outcomes to enable feedback-driven skill improvement. Use when logging review results or analyzing review quality.
Detects common LLM coding agent artifacts by spawning 4 parallel subagents
Review implementation plans for parallelization, TDD, types, libraries, and security before execution
Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.
Support for both regular and beta releases.
Expert guidance for GitHub CLI (gh) operations and workflows. Use this skill for command-line GitHub operations including pull request management, issue tracking, repository operations, workflow autom
Combined simplification and review pipeline. This skill orchestrates two sub-skills in sequence:
Find high-impact defects in changed code with evidence. Prioritize security, correctness, and regressions over style nits.
Fetch and analyze CodeRabbit review comments from a GitHub PR, or run a local CodeRabbit CLI review. Default mode fetches from the remote PR. Use `--local` to run the CLI against local diffs.
Use OpenAI Codex CLI as a **read-only oracle** — planning, review, and analysis only. Codex provides its perspective; you synthesize and present results to the user.
**Deal Parameters**
- **Announcement type:** Product launch
**Product:** AI-powered code review tool for developers
Build a Personal Productivity System: weekly timebox plan, capture system, daily/weekly review rituals.
Run blameless post-mortems and retrospectives: timeline, root causes, action tracker.
- **Review type:** Incident (Production Outage)
**Incident ID:** INC-2026-0316-001
Run a decision process end-to-end: RAPID/DACI roles, options matrix, decision log, comms.
Run high-signal design reviews: brief, feedback log, decision record, follow-up plan.
**Project / feature:** Web Onboarding Flow -- New First-Time Admin Setup Experience
**Review Type:** Live Design Review (45 minutes)
> Produced using the `running-effective-meetings` skill pack.
**Problem:** The current weekly product review devolves into status updates, consistently runs over 60 minutes, and fails to produce clear decisions or unblock teams.
**Company:** Seed-stage B2B SaaS (API monitoring tool)
Set aligned OKRs/goals: objectives, key results, guardrails, review cadence.
Plan product launch/release: rollout/rollback plan, comms, monitoring, post-launch review. See also: launch-marketing (marketing side).
- **Focal decision/problem:** Engineering on-call page volume has tripled over 6 months (5 to 15 pages/week per team), causing burnout, declining code review rigor, and suspected rising incident rates
**Presenting problem:** On-call page volume has tripled over 6 months (5 to 15 pages/week per team), causing burnout, degraded code review quality, and a suspected increase in production incidents ---
> Produced using the `writing-job-descriptions` skill pack.
**Company:** [Stealth AI Startup] -- AI-Powered Contract Review for Legal Teams
Use when you need to test a skill with non-string values in the metadata map.
>-
코드 리뷰. 작업 후 변경사항을 Z.AI 모델로 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다. /rr 또는 'GLM 리뷰' 요청 시 사용.
GLM-5 코드 리뷰. /rr의 상위 버전으로 더 강한 모델로 변경사항을 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다.
>
You are the night shift. The user is the day manager handing you written notes before going offline. Your job is to execute plan-driven work autonomously, batch by batch, with testing, review, and doc
Build, preview, and update the VitePress documentation site in docs-site/
Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.
Review actual code implementations (Python, JavaScript, TypeScript, React) for correctness, maintainability, security hygiene, and adherence to project patterns. Use when reviewing pull requests to ensure code quality, proper error handling, adequate test coverage mapped to acceptance criteria, and alignment with architecture boundaries and review standards.