Чеклист и формат code review: severity levels (CRITICAL/MAJOR/MINOR/NIT), формат вердикта (APPROVED/CHANGES_REQUESTED/BLOCKED), Django anti-patterns, N+1 detection, dbt checks,…
Use when CI is slow (>10 min), flaky, or the user asks to optimize GitHub Actions for a frontend project.
Read indemnity leakage, LAE, and cycle time as managed metrics, not minimized payout, to find the controllable gap. Reach for this on a claims-cost question.
Produce and continuously maintain ONE living review document for a multi-item session — a cockpit header (Progress checklist, Working folder, Context) plus per-item review cards…
Provides a structured workflow for planning and executing code reviews like a senior engineer. Use when asked to review code, PRs, or plan a code review task.
Run a comprehensive code review using parallel agents, then synthesize findings. TRIGGER when the user asks you to review a particular part of the codebase.
Review implementation fidelity against `PLAN.md` and `AMENDMENTS.md`; emit `PS#` findings and validation-fact gaps into the task packet.
Revisión profunda de base de código en múltiples fases con clasificaciones de gravedad y resultados estructurados.
Deep Review codebase ครบทุกมิติ ผ่าน group orchestrators และ category workflows พร้อม validate issues
PR에 달린 리뷰 코멘트를 검토하고, 필요한 작업을 수행한 후, 각 코멘트에 reply를 달고 resolve합니다. PR 번호를 인자로 전달하거나 생략하면 현재 브랜치의 PR을 사용합니다.
Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies,…
Run an AI code reviewer against the task's git diff, fix must_fix issues, and defer or dismiss suggestions
Jetpack Compose 성능 및 패턴 검사. Recomposition 최적화, State 관리, Side Effect 사용법 분석.
Runs the applicable review battery after changes to CLAUDE.md or skills. Triggers on "revisa config", "review config files", "check my CLAUDE.md", "valida as regras", or…
Comprehensive multi-domain code reviewer that covers all review concerns in a single pass
Reviews a contract in plain English, surfaces red flags with severity ratings, and produces a marked-up docx/PDF with suggested redlines.
Revisa um contrato contra o playbook de negociação da organização — sinaliza desvios, gera redlines, fornece análise de impacto no negócio.
Review an executed-or-draft B2B contract (MSA, SOW, SaaS agreement, DPA, license, partnership, contractor IP assignment, reseller agreement) against the organization's negotiation…
Use when a lawyer or party needs a contract reviewed with proposed track-change-style edits and written rationale per change — covering clause-by-clause analysis, risk flagging,…
Use Claude Legal Skill to guide an agent through contract risk review, CUAD-style clause checks, market benchmarks, and lawyer-ready redline suggestions.
Contrôler, auditer, RESTITUER et intégrer proprement le commit/la branche/la PR d'un collaborateur (souvent depuis un fork) avant merge dans main.
Reusable scaffolding for review workflows with context establishment, evidence capture, and structured output.
Criteria for reviewing Codex worker outputs across 5 dimensions. Use when reviewing code submitted by workers before approval.
Use when a drafter or reviewer needs to verify that all internal cross-references in a contract are correct — checking section references, defined term usage, schedule/exhibit…
Review the current slice against the active task, definition of done, and UX scorecard, then write a strict pass/fail review file.
Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-based (path patterns), or fix mode.
Check FeedbackPulse performance and peer review progress. Use when someone asks how a review cycle is going, which departments are behind, who has not started or is overdue, or…
Review one DAGrail review or decision node using bounded evidence. Use when assigned semantic review, cold review, actual-artifact inspection, finding classification, or a closed…
Review code base from the viewpoint of Domain Driven Design (DDD) specialist. Evaluate how core business logics are well organized in terms of DDD principle.
Review generated pseudocode or disassembly without presenting it as original source. Use when Codex must interpret, compare, annotate, validate, or summarize output from Cutter,…
Use when a drafter or reviewer needs to verify that all defined terms in a contract are used consistently with their definitions — checking for term drift, singular/plural…
Evaluate an existing product or technical design document for comprehension, consistency, risk coverage, and implementation readiness.
Read all open GitHub Discussions, summarize them, respond to pending ones, and create issues from actionable feature requests
Review all project documentation for correctness, completeness, and freshness. Spawns a doc-maintainer agent to audit and fix docs.
Schema for tracking code review outcomes to enable feedback-driven skill improvement. Use when logging review results or analyzing review quality.
Find files approaching context limits and evaluate whether coupling-aware splits are worthwhile
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification.
Automated review-fix loop that spawns 8 reviewers in parallel, fixes quick-fix items automatically, and accumulates strategic items for user decision.
Grill the current changes — fan out parallel review subagents over the working-tree + branch-vs-base diff, resolve each confirmed finding with multiple architectural solutions,…
Autonomous review-fix cycle that continuously reviews code using background-reviewer, fixes issues, and repeats until all findings are resolved.
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex,…
Address, respond to, or resolve PR review comments / review threads. Use when asked to handle reviewer feedback on a pull request.
Generate a forecast review with risk analysis, recommendation posture, and change detection using CRM truth, pasted or exported pipeline context, account notes, and optional…
Scores the authenticity of a product's review corpus using a five-signal ensemble (velocity, verified-purchase ratio, rating distribution, account patterns, cross-product…
Review Gate を実施し、実装の仕様準拠・品質・セキュリティを 6 観点でレビューする。Use when: 実装完了後にレビューをしたい時。「Review Gate を通したい」「コードレビューをして」「実装の品質確認をしたい」「severity を確認したい」。
Pack trusted context and review memory writes before long OpenClaw sessions drift or accumulate low-quality memory.
GitHub PR code review - fetches the diff, runs automated checks, launches 3 parallel review agents (correctness, convention compliance, efficiency) to analyze changes, validates…
Use repository-settings when an operator wants GitHub repository configuration changes reviewed as code before branch protection, labels, teams, or other settings are applied.
Use to review Go diffs/PRs for distributed failures in transactions, brokers, retries, leases, or effects. Do not use for fintech.
Use as lead for fintech Go diff/PR review: money, payments, settlement, payment data, and audit. Do not use for general work.
Use when a contract''s choice-of-law clause and forum-selection clause need to be reviewed for validity, internal consistency, and practical enforceability — particularly in…
Review GroovyDoc accuracy across modules and subworkflows using bactopia-lint. Checks @output/@input field matching, @modules/@subworkflows lists, citation keys, tag ordering, and…
Review the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step.
First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a reference class, helping the user decide where to engage,…
How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR…
The general blind-spot check for PostHog Review, the final sweep that runs after every enabled review perspective has reviewed a chunk.
The Performance & Reliability review perspective for PostHog Review. Verifies that changed code will perform and hold up in production: resource efficiency, error handling and…
The resolution criteria for PostHog Review's resolution stage: the bar for deciding, per unresolved review thread, whether the ask is worth implementing and safe to implement…
Gaps fix profile for PostHog Review's resolution stage: the default resolution criteria, narrowed to fix only real gaps.
Small fix profile for PostHog Review's resolution stage: the default resolution criteria, narrowed to fix only small, contained issues.