[UDS] Reverse engineer code to Specs, BDD, or TDD coverage
Rosetta skill to reverse-engineer existing code to a specification, to extract a behavior, distill domain logic from implementation, or produce a clean system-level description…
Reverse Factoring Lieferantenfinanzierung und Abgrenzung Kreditgeschäft: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen.
Diagnoses how consuming external AI forces you to reveal proprietary knowledge — your 'intelligence exhaust' (prompts, tool calls, corrections, evals) — to whoever controls the…
Reverse Factoring Lieferantenfinanzierung und Abgrenzung Kreditgeschäft: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen.
Reverse-engineer published books into structured scene-by-scene outlines for study. Use when analyzing craft, learning story structure from masters, or creating teaching materials…
Configure nginx and Traefik as reverse proxies. Implement SSL termination and routing. Use when setting up application gateways.
Orchestrate the full reverse engineering pipeline: Extract provisional spec from existing code, refine through dialogue to uncover the true spec, then reconcile code with the…
Janus and reversible languages: run programs backwards, time-symmetric computation.
Know when to move fast and when to move carefully. Master Jeff Bezos' framework for distinguishing high-stakes irreversible decisions from low-stakes reversible ones.
Reverts previous work using git-aware analysis
Detect when an AI-authored PR is reverted and trigger a Reflection session for RCA. Monitors revert commits, matches to AI PRs, and initiates analysis. Scheduled to run hourly.
Read a contract someone sent you and tell you what''s in it. Pick how deep: a quick verdict on whether it''s safe to sign, a fast NDA check, or a clause-by-clause map without a…
Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.
Review whether an existing or proposed CakePHP abstraction choice is correct — decision units, rejected alternatives, and project conventions.
Run a periodic IAM access review — lists all users, permissions, activity, and flags issues. Required quarterly for SOC 2.
Challenge a design, plan, or artifact by actively looking for weaknesses, risks, and blind spots. Use when the user says 'challenge this design', 'red team this', 'steelman the…
Use Hunk to keep a live terminal review UI open for agent-authored code changes, with Git, Jujutsu, Sapling, patch input, watch mode, and inline agent annotations.
Preferred agent harness patterns when not otherwise specified by the project. TRIGGER when you notice you or another agent had trouble completing work quickly and correctly and…
Review recent Claude Code and Codex sessions for the current project and propose improvements to the global and project AGENTS.md files, plus cleanup of Claude's auto memory.
Detect agentic coding infrastructure in a project: CLAUDE.md, AGENTS.md, installed skills, MCP servers, hooks, and cross-tool compatibility (Claude Code and Codex CLI).
Review the AGENTS.md file to ensure all rules are up-to-date, removing any redundant or overly vague rules and updating deterministic guardrails as needed.
Guidance on combining findings from multiple review agents into actionable recommendations
Aggregate and analyze product and business reviews from Google Maps, Amazon, Akta, and Xiaohongshu. Cross-platform review intelligence including rating patterns, common themes,…
Pick the next unchecked Bloomburrow card from the AI advisor checklist, evaluate if it needs an advisor, create one if needed, and check it off.
AI-agent compatibility audit. Use when evaluating whether code changes are safely readable, analyzable, and modifiable by AI agents.
Use DiffX to review local git changes in a PR-style browser UI, leave inline comments, and hand structured feedback back to a coding agent for repair.
Open a GitHub-style local diff, collect inline review comments, then hand unresolved threads back to a coding agent for fixes.
Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments.
Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agree — from…
Deep analysis and iterative fixing of a Rust source file. Finds logic errors, lock/concurrency issues, and simplification opportunities, then fixes them one by one until the file…
Session ending protocol, HANDOFF document format, seamless continuation between sessions
Yapılan işleri Repo kuralları, dark-first premium tasarım, yetki güvenliği, schema bütünlüğü ve obvious regresyon açısından denetleyen tam stack gözetmen.
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR. — from susomejias/rembric
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes.
Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agree — from…
Iteratively refine code via N rounds of parallel subagent review and orchestrator-applied fixes. Use when the user says "let's do three rounds", "fix/review loop", "back-and-forth…
\"Review API calls, responses, and network traffic. 審API調用響應網絡流量. Use when: inspect API calls, review network requests, check API responses, analyze request payload, debug API…
Interactive architectural review workflow. Analyzes codebase organization via noun analysis, produces a target blueprint, then collaborates with the user to decide what to…
[Code Quality] Use when you need to review artifact quality (PBI, user story, test spec, design spec) before handoff. Supports --type={pbi|story|spec-tests|design}.
Use when reviewing a technical analysis, design document, or specification from a business analyst perspective - checking requirements completeness, user workflows, edge — from…
Production-readiness audit for authentication. Use when auth code changes or when auth feels fragile, unclear, or unsafe.
Review CakePHP Authentication setup for correctness and AuthZ non-contamination.
Use when reviewing anything that authenticates users, checks permissions, or exposes objects by id — broken access control is the #1 web risk; verify authz is enforced server-side…
Review combined Authentication + Authorization setup for clear identity vs permission boundaries.
Use when running or scheduling periodic repository review cycles that must dispatch the correct reviewer, aggregate findings, and escalate outcomes into reports, issues, or…
Display and review the most recent ad creative batch for a client. Shows strategy, concepts, copy, and images. Allows approve, reject, or revise.
Use BEFORE opening a PR (the pre-PR review gate) to dispatch the local review battery — not before every push. Post-PR review is owned by claude-review, not this battery.
Use when about to commit or asked to commit changes, so an independent review runs and converges before anything lands.
Forces a <50-word plan before any file edit or destructive command. Use for any task that would touch 2+ files, delete/move files, modify infra/CI config, or run a migration.
Für Review: Behörden-, Gerichts- oder Registerweg: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Einreichungsplan mit Form- und Nachweischeck.
Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agree — from…
Weekly manual review of contacts with 3+ bounce events. Decide whether to delete or attempt recovery for each flagged contact.
Look for opportunities to optimize the approach and/or implementation of the solution to a problem you see on the current branch (relative to its base branch).
Review-3 (FULL) — final adversarial review of the BUILT product via a multi-agent fan-out assuming every feature is broken until a re-run check proves it (reconciliation,…
Use when a lawyer, investor, or founder needs a systematic mathematical and structural review of a capitalization table — verifying share totals, pre/post-money math,…
Review a proposed or completed change specifically for documentation drift, missing tests, and stale knowledge-base entries.
Code review of current git changes, compare to related plan if exists, identify bad engineering, over-engineering, or suboptimal solutions.
나노바나나 치트시트 이미지를 Gemini Vision으로 분석하여 해당 kr md 파일의 내용과 일치하는지 검증합니다. 기술적/문맥적 오류, 잘못된 텍스트/그래프/그림을 찾아냅니다. 사용: /review-cheatsheet week1/slug/chapter
Use when reviewing a pull request to enforce team conventions. Triggers on "review this PR", "check the PR", "code review", "PR review checklist".