agentsclimarketplace

Review & quality

19,181 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Product launch legal review

    findscripter/everything-skills/09-verticals/product-launch-legal-review Skill

    no license11★ repo

    当需要对一次产品/功能上线(PRD、上线工单、Drive 文档)做逐类目法律审查、判定能否发布时使用;做按团队审查框架走查(合同/隐私/安全/IP/第三方/监管/营销/AI 治理)+ 行业叠加 + 风险校准,产出「特权审查备忘录 + 可贴工单的脱敏结论」双输出;不适用于替代律师批准发布、撰写营销创意、出具正式法律意见。触发词:审查这次上线、上线法律审查、这个能发吗、功能法律风险、PRD 法务过一遍、launch review、can we ship this

  • Saas subscription agreement review

    findscripter/everything-skills/09-verticals/saas-subscription-agreement-review Skill

    no license11★ repo

    当审查 SaaS/订阅协议、需对自动续约、涨价、数据可携出、SLA、子处理者、AI 训练权与责任上限做专项把关并准备红线时使用;产出含双重严重度(法律风险×业务摩擦)的 SaaS 专项发现、续约登记字段移交与红线建议;不适用于通用合同评审(用 contract-playbook-review)、NDA 速审(nda-triage-reviewer)、DPA 专项(dpa-clause-reviewer)、出具正式法律意见;触发词:SaaS 审查、订阅协议、自动续约、auto-renewal、涨价条款、SLA、子处理者、数据可携出、AI 训练权

  • Vendor agreement redline review

    findscripter/everything-skills/09-verticals/vendor-agreement-redline-review Skill

    no license11★ repo

    当收到对方发来的供应商协议(MSA/SaaS订阅/服务协议/采购合同)需在签署前依据团队 playbook 做条款审查时使用;做的是:定位合同类型与本方立场、先查致命条款、逐条比对 playbook 偏离并按双轴严重度分级、给出外科手术式红线语言与升级路由、产出一次可执行的审查备忘录;不适用于起草合同、谈判让步决策、DPA 深审(转 dpa-clause-reviewer)、并购数据室批量尽调;触发词:供应商协议、MSA、服务协议、SaaS、合同审查、红线、vendor agreement、redline、采购合同、责任上限

  • Vendor agreement status checker

    findscripter/everything-skills/09-verticals/vendor-agreement-status-checker Skill

    no license11★ repo

    当为某供应商做入驻/续约、需跨 CLM/CRM/邮件/文档/IM 汇总「已签什么、缺什么、何时到期」时使用;做的是跨系统检索该供应商全部协议、按类型/状态/到期/自动续约编表、做覆盖度缺口分析(NDA/MSA/DPA/SOW/SLA/保险),并标注 90 天内到期与存续义务,产出合并状态报告;不适用于起草/谈判/审条款、出具法律意见、单份合同逐条审查。触发词:供应商协议、vendor agreement、协议状态、合同到期、自动续约、MSA、DPA、缺口分析、续约核查

  • Slack message formatter

    findscripter/everything-skills/10-platform/slack-message-formatter Skill

    no license11★ repo

    当撰写、起草或代写一条 Slack 消息/公告/Canvas 时使用;做一份合规 mrkdwn 排版的消息(首句点题、要点列表、关键信息加粗、thread/频道分流);不适用于标准 Markdown 文档、邮件/飞书等非 Slack 渠道、或用 Bolt 编写机器人代码;触发词:slack 消息、mrkdwn、slack 排版、slack 公告、slack 加粗、thread 回复、slack canvas

  • Code review

    bostonaholic/team/skills/code-review Skill

    11★ repo

    Generator-evaluator separation and review methodology — loaded by review agents to enforce fresh-context review discipline and gate verdicts; findings from the code, security, and docs reviewers are formatted per the conventional-comments skill. Trigger on "review this diff", "review these changes", "code review this", or "/code-review".

  • Conventional comments

    bostonaholic/team/skills/conventional-comments Skill

    11★ repo

    The Conventional Comments format for review findings — label and decoration syntax, code-directed comment style, and the issue/suggestion/nitpick comment types with literal examples. Load when writing, formatting, or labeling review comments, PR feedback, or reviewer findings.

  • Eng design doc review

    bostonaholic/team/skills/eng-design-doc-review Skill

    11★ repo

    Adversarially review a technical design document with fresh context. Dispatches the built-in read-only `Explore` subagent (clean context, no shared history with the design-author) against `docs/plans/<id>/design.md` and presents its verdict — APPROVE, REQUEST CHANGES, or COMMENT. The Review brief doubles as the pipeline's DESIGN review gate; standalone use remains. Trigger on "review the design doc", "audit design.md", "is this design ready", or `/eng-design-doc-review`.

  • Git commit

    bostonaholic/team/skills/git-commit Skill

    11★ repo

    Git commit discipline — the Conventional Commits subject format, the 50/72 rule, and atomic single-purpose commits. Load when writing a commit message, committing an implementation slice, or preparing commits for a pull request.

  • Review severity tiers

    bostonaholic/team/skills/review-severity-tiers Skill

    11★ repo

    Orchestrates specialized agents to autonomously implement entire features end-to-end

  • Shipit

    bostonaholic/team/skills/shipit Skill

    11★ repo

    Land a reviewed pull request: discover the open PR for the current branch, push any unpushed commits, wait for CI to go green, then squash-merge it so the PR title (which may carry a version) lands as the commit subject. Handles a PR that has fallen behind its base (rebase + force-with-lease) and surfaces branch-protection rejections verbatim. Project-agnostic — it knows nothing about how any project versions itself. Invoke ONLY on explicit ship intent — the user says "ship it", "land the PR", "land this", or runs "/shipit". Landing merges, which is irreversible: never infer ship intent from a PR merely being approved, green, or finished.

  • Team pr

    bostonaholic/team/skills/team-pr Skill

    11★ repo

    Open the pull request after verification passes. Updates the changelog, optionally surfaces the tracking ticket, and closes out the topic. Trigger on "open the PR", "open a draft PR", or "/team-pr". To land/merge a reviewed PR (wait for CI, then squash-merge) use the separate /shipit skill — "ship it", "land the PR", and "land this" trigger /shipit, not this skill.

  • Aios review

    ArchSightLabs/archsight-aios/skills/aios-review Skill

    11★ repo

    代码审查和风险评审工作流。用于审查 diff、PR、AI 生成代码、安全敏感改动、Prompt/Tool/Runtime 变更、依赖更新、性能风险、测试缺口和发布准备度。

  • Write page

    GabrielAmz/web-anatomy/skills/write-page Skill

    11★ repo

    The Fix-altitude executor in Web Anatomy. Improve an existing landing page, homepage, pricing page, persona page, feature page, comparator page, or individual section using Web Anatomy benchmarks, or build a new page or section from a chosen structure and direction. Use when the user asks what can you do to improve my LP, what can you do to improve my landing page, improve my site, critique, audit, redesign brief, section improvement, CRO review, why is this page weak, compare my page to best practices, write the rework, apply the fixes, or build this page or section. Runs in improve mode (captures current reality, gaps it against benchmarks) or build mode (no current page; writes the sections from the chosen spec). Consumes a prior audit-page, research-best-practices, or find-examples handoff when present, and writes a report under `.webanatomy/write-page/`.

  • Golang code style

    alexastrum/skl/.agents/skills/golang-code-style Skill

    11★ repo

    Golang code style conventions — line length and breaking, variable declarations, control flow clarity, when comments help vs hurt. Use when writing or reviewing Go code, asking about style or clarity, or establishing project coding standards. Not for naming conventions (→ See `samber/cc-skills-golang@golang-naming` skill), linter configuration (→ See `samber/cc-skills-golang@golang-lint` skill), or doc comments (→ See `samber/cc-skills-golang@golang-documentation` skill).

    The same file is in 2 other repositories

  • Golang lint

    alexastrum/skl/.agents/skills/golang-lint Skill

    11★ repo

    Linting best practices and golangci-lint configuration for Golang projects — running linters, configuring .golangci.yml, suppressing warnings with nolint directives, interpreting lint output, and selecting linters. Use when configuring golangci-lint, asking about lint warnings or nolint suppressions, setting up code quality tooling, or choosing linters. Also use when the user mentions golangci-lint, go vet, staticcheck, or revive.

  • Fable verify

    ahmdd4vd/Fable5res/skills/fable-verify Skill

    no license11★ repo

    Verify like Fable 5 — obsessive, systematic, evidence-based quality assurance woven into your reasoning. Use this skill when you have just written or modified code, need to confirm something works, are running tests, or need to validate output against requirements.

  • Domain validator

    jpantsjoha/ai-native-developer-experience/.agents/skills/domain-validator Skill

    11★ repo

    Validate agent output against declared domain rules and ground truth before trusting it downstream. Trigger after any agent produces output that will be used in a decision, stored persistently, or passed to another agent.

  • Pr reviewer

    jpantsjoha/ai-native-developer-experience/.agents/skills/pr-reviewer Skill

    11★ repo

    Review gate for correctness, reuse, and simplification. Produces a structured verdict with actionable findings. Trigger on any PR before merge, or on any agent-generated code before it is committed.

  • Speccrew deploy startup

    charlesmu99/speccrew/.speccrew/skills/speccrew-deploy-startup Skill

    11★ repo

    Starts the application in local/development environment and performs health check verification. Reports service URL and health status.

  • Speccrew dev review backend

    charlesmu99/speccrew/.speccrew/skills/speccrew-dev-review-backend Skill

    11★ repo

    SpecCrew Backend Code Review Skill. Reviews backend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.

  • Speccrew dev review desktop

    charlesmu99/speccrew/.speccrew/skills/speccrew-dev-review-desktop Skill

    11★ repo

    SpecCrew Desktop Code Review Skill. Reviews desktop app implementation code (Electron/Tauri) against system design documents and security standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.

  • Speccrew dev review frontend

    charlesmu99/speccrew/.speccrew/skills/speccrew-dev-review-frontend Skill

    11★ repo

    SpecCrew Frontend Code Review Skill. Reviews web frontend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.

  • Speccrew dev review mobile

    charlesmu99/speccrew/.speccrew/skills/speccrew-dev-review-mobile Skill

    11★ repo

    SpecCrew Mobile Code Review Skill. Reviews mobile app implementation code against system design documents, API contracts, and platform-specific standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.

  • Speccrew knowledge techs generate quality

    charlesmu99/speccrew/.speccrew/skills/speccrew-knowledge-techs-generate-quality Skill

    11★ repo

    Quality assurance for generated tech documentation using XML workflow blocks. Performs cross-validation, consistency checks, completeness verification, and generates quality reports.

  • Speccrew pm phase1 knowledge check

    charlesmu99/speccrew/.speccrew/skills/speccrew-pm-phase1-knowledge-check Skill

    11★ repo

    SpecCrew PM Phase 1 Knowledge Base Availability Check Skill. Detects knowledge base status and initializes business knowledge as needed. Supports three-path routing with Path B deep initialization sequence.

  • Speccrew pm phase6 verify confirm

    charlesmu99/speccrew/.speccrew/skills/speccrew-pm-phase6-verify-confirm Skill

    11★ repo

    SpecCrew PM Phase 6 Verification & Confirmation Skill. Performs file integrity validation, feature list completeness check, user review gate, and finalization.

  • Design review

    codybrom/clairvoyance/skills/design-review Skill

    11★ repo

    Orchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep. Use when reviewing a file, module, or PR for overall design quality and you want a comprehensive, prioritized assessment. Not for applying one specific lens (use that skill directly) or analyzing how code changed over time (use code-evolution).

  • Pome verify seed

    pome-sh/digital-twins/skills/pome-verify-seed Skill

    11★ repo

    Verifies a Pome task's seed is a fair exam before any run — verify_seed plus guard-aware triage of already-passing criteria, a state-diff review, an evaluate_criteria dry-run, and opt-in read-only probes on a live twin session. Use when the user has authored or adapted a task and wants to check the seed, asks "is my seed right / is this a fair exam?", or is about to run a task for the first time.

  • Generate pr description

    Flexonze/claude-init/.claude/skills/generate-pr-description Skill

    10★ repo

    Generate PR title and description

  • Update changelog

    Flexonze/claude-init/.claude/skills/update-changelog Skill

    10★ repo

    Update the changelog based on commits in the current git branch

  • Audit security

    JHostalek/dotclaude/skills/audit-security Skill

    10★ repo

    Use when auditing and fixing security in a scope — injection (SQL, shell, template), auth/authz gaps, secrets in code or logs, weak crypto, missing validation at trust boundaries, XSS, SSRF, path traversal. Triggers on "audit security", "security review", "fix vulnerabilities", "OWASP check". Performs a comprehensive, architecture-led review; named weakness classes are a minimum, never an exhaustive boundary.

  • Commit

    JHostalek/dotclaude/skills/commit Skill

    10★ repo

    Use when the user asks to commit, create a git commit, checkpoint changes, save work to git, or write a commit message.

  • Pr

    JHostalek/dotclaude/skills/pr Skill

    10★ repo

    Use when the user asks to create or update a pull request for the current branch.

  • Rebase

    JHostalek/dotclaude/skills/rebase Skill

    10★ repo

    Use when the user asks to rebase the current branch onto another branch or update branch history without merging.

  • Python architecture review

    keez97/claude-architecture-skills/skills/python-architecture-review Skill

    10★ repo

    Expert-level architecture review and design guidance for Python backends, with deep knowledge of FastAPI, PostgreSQL, async patterns, and modern Python project structure. Use this skill whenever the user asks you to review Python code architecture, design a new Python backend, evaluate project structure, assess API design, review database schemas, audit security posture, or discuss scalability of a Python service. Also trigger when the user shares Python backend code and asks "what do you think", "is this structured well", "how should I organize this", or describes a new feature/service they're planning to build in Python. Even if they don't say "architecture" explicitly — if they're asking about how to structure a FastAPI app, design their models, or whether their approach will scale, this skill applies.

  • Review

    tercel/spec-forge/skills/review Skill

    10★ repo

    Review spec-forge generated documents (tech-design + feature specs) for quality, completeness, and internal consistency. Finds issues like incomplete sections, contradictions, missing traceability, and vague specs, then optionally auto-fixes them. Supports iterative review-fix cycles that run until the review converges — passing, or a round with no net reduction in findings — typically 1–2 rounds.

  • Architecture review

    yugash007/edu-agent-skills/skills/projects/architecture-review Skill

    10★ repo

    Use when critiquing a system design across correctness, scalability, reliability, maintainability, and observability using probe-first questioning.

  • Project review

    yugash007/edu-agent-skills/skills/projects/project-review Skill

    10★ repo

    Use when evaluating a completed or in-progress project across scope, correctness, quality, testing, and learning outcomes using structured Praise-Critique-Grow feedback.

  • Test review

    akovalion/paranoid-qa/ru/skills/test-review Skill

    10★ repo

    Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.

  • Test review

    akovalion/paranoid-qa/skills/test-review Skill

    10★ repo

    Review of just-written or modified autotests against TypeScript + Playwright best practices (per official documentation) and your project's conventions. Use via /test-review or after writing/editing any test (UI E2E, API, UI+API, mocks, visual, mobile) or a Page Object/fixture/constants — before commit. Produces a prioritized list of findings with severity, line references, and ready-made fixes.

  • Review scheduler

    X-RayLuan/awesome-ceo-stack/ceo-skill/Openclaw-Study-Coach/.claude/skills/review-scheduler Skill

    no license10★ repo

    给小学阶段制定可坚持的 7 天复习节奏。根据薄弱点清单或当前 review_queue 错题,生成周计划和每日清单,并落盘到 data/plans/。当孩子或家长说"安排下周复习"、"接下来几天怎么练"、"做什么复习"时使用。

  • Literature review

    Marazii/research-co-pilot/skills/literature-review Skill

    10★ repo

    Conduct rigorous, fact-checked academic literature reviews. Synthesizes sources, traces citation chains, flags weak claims, and produces structured outputs (narrative, systematic, scoping, or thematic). Trigger when: user asks for a "literature review", "lit review", "background research", "state of the field", "what does the research say about…", "summarize the literature on…", "find sources on…", or runs /lit-review. Works from sources the user provides (PDFs, links, citations) AND from web/database search when allowed.

  • Peer review

    Marazii/research-co-pilot/skills/peer-review Skill

    10★ repo

    Rigorous academic peer review in the voice of a seasoned professor. Two verdict modes (paper, homework), five alternative workflows (committee panel, fact-check audit, plagiarism-check, draft thinking-partner, presentation feedback), plus iterate mode for post-review dialogue. Auto-detects Hebrew or English and the work's academic domain (any field) and applies rigor criteria for that field. Annotates source documents at the relevant text / shape / page locations and returns a reviewed file: .docx (inline comments + tracked changes), .pdf (sticky notes + highlights), .pptx (native comments on slides / shapes), .tex (LaTeX reviewer comments). Use this skill when the user invokes /peer-review, asks to review, critique, evaluate, or give feedback on a paper, thesis, essay, dissertation chapter, problem set, course assignment, conference talk, or slide deck. Also for panel-style review, fact-check or plagiarism audit, generative feedback on unfinished work, presentation feedback, or continuing a prior review.

  • Reviewer response

    Marazii/research-co-pilot/skills/reviewer-response Skill

    10★ repo

    Draft a rigorous, polite, point-by-point response to reviewer comments on a journal or conference submission (R1 / R2 / R3 letters), plus the corresponding manuscript revisions. Categorizes each comment as concession / pushback / clarification needed / minor fix, drafts the response and the revision for each, and assembles a cover letter. Composes with `peer-review` (consume comments from a review output) and `manuscript-drafter` (revise prose using the manuscript's voice profile and academic register rules). Won't concede a point the data doesn't support; preserves framing where the reviewer misread; addresses every point. Trigger when: user mentions "respond to reviewers", "R1 response", "R2 response", "rebuttal", "address reviewer comments", "reviewer-response letter", "point-by-point response", "revision and resubmission", "response to reviewer 2", "cover letter to editor", or runs /respond.

  • Lit verify

    qiaomiaojoe/ai-academic-workflow/skills/lit-verify Skill

    no license10★ repo

    文献验真(乔淼PhD · AI学术训练营 · AI学术工作流)。对任意来源的文献清单(检索结果 / AI 生成的参考文献 / 论文引文列表 / BibTeX)逐条实查:DOI 解析核对题录、CNKI 详情页核对、采集被引数;无法实查或字段对不上的一律标可疑剔除,零容忍防捏造。独立可用——特别适合"检查这些参考文献是不是真的"。Trigger on:"验真这些文献"、"检查这些参考文献是不是编的"、"核实这份文献清单"、"verify these citations"、"check if these references are real / hallucinated"。

  • Review blueprint

    qiaomiaojoe/ai-academic-workflow/skills/review-blueprint Skill

    no license10★ repo

    综述蓝图(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。把知识模块清单编排成综述的逻辑结构:每个 Section 的标题 + 核心 argument + 模块出场序列 + 模块间逻辑(前置依赖/并列对照/对话张力)+ 段落写作提示,并渲染成自包含 HTML 可视化自动打开。Section 3 的 gap 内容由 research-gap-scan 填入。Trigger on:"帮我编综述蓝图"、"把知识模块编排成综述结构"、"review blueprint"、"organize my modules into a review outline"。

  • Review draft assembly

    qiaomiaojoe/ai-academic-workflow/skills/review-draft-assembly Skill

    no license10★ repo

    综述初稿组装(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。按综述蓝图把知识模块组装成综述初稿:三 Section 组装规则 + 深读张力句并入 + 逐条引用核验(对照 Zotero/清单出独立报告)+ 参考文献表 + 反 AI 味写作要求 + 初稿纯净交付(零模块编号零 Zotero key)+ 转 docx。Trigger on:"组装综述初稿"、"把模块拼成综述"、"综述成稿"、"assemble my literature review draft"。

  • Review draft

    qiaomiaojoe/ai-academic-workflow/skills/review-draft Skill

    no license10★ repo

    AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库:选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿,30 个 skills 拆到步骤颗粒度,单个可独立运行、可自由组合(Claude Code / Codex)

  • Topic review integrative

    qiaomiaojoe/ai-academic-workflow/skills/topic-review-integrative Skill

    no license10★ repo

    AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库:选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿,30 个 skills 拆到步骤颗粒度,单个可独立运行、可自由组合(Claude Code / Codex)

  • Topic review semisystematic

    qiaomiaojoe/ai-academic-workflow/skills/topic-review-semisystematic Skill

    no license10★ repo

    AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库:选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿,30 个 skills 拆到步骤颗粒度,单个可独立运行、可自由组合(Claude Code / Codex)

  • Topic review systematic

    qiaomiaojoe/ai-academic-workflow/skills/topic-review-systematic Skill

    no license10★ repo

    AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库:选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿,30 个 skills 拆到步骤颗粒度,单个可独立运行、可自由组合(Claude Code / Codex)

  • Persona experiments

    ananas-agency/B2B-GTM-Suite/4 Persona Experiments/persona-experiments Skill

    no license10★ repo

    Designing experiments that validate the buyer persona and value propositions in the Ananas-Agency model. Use this skill when the user wants to: validate a buyer persona, test value propositions on real customers, check whether customers' problems are real, design tests of sales hypotheses, create a segment validation plan. Trigger: "experiments", "persona validation", "test the persona", "are the problems real", "hypothesis testing", "value validation", "check the segment", "test plan", "buyer persona experiments".

  • Plan review skill

    smith-horn/product-builder-starter/skills/plan-review-skill Skill

    no license10★ repo

    Multi-perspective plan review with VP Product, VP Engineering, and VP Design. Use when reviewing implementation plans, design docs, architecture proposals, or wave plans for blockers, anti-patterns, conflicts, and regressions.

  • Pdlc lint

    kanfu-panda/pdlc-skills/skills/pdlc-lint Skill

    10★ repo

    代码质量检查与自动修复

  • Pdlc review

    kanfu-panda/pdlc-skills/skills/pdlc-review Skill

    10★ repo

    38 slash commands that turn Claude Code into a real PDLC workflow — PRD → TDD → implement → review → ship. Hard contracts force AI to persist artifacts, write failing tests first, and run self-checks. No more "looks done" in chat.

  • 190 gamedev code review

    FluxonLab/Skillry/community/Donchitos-Claude-Code-Game-Studios/skills/190-gamedev-code-review Skill

    no license10★ repo

    Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.

  • 198 gamedev design review

    FluxonLab/Skillry/community/Donchitos-Claude-Code-Game-Studios/skills/198-gamedev-design-review Skill

    no license10★ repo

    Reviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.

  • 219 gamedev release checklist

    FluxonLab/Skillry/community/Donchitos-Claude-Code-Game-Studios/skills/219-gamedev-release-checklist Skill

    no license10★ repo

    Generates a comprehensive pre-release validation checklist covering build verification, certification requirements, store metadata, and launch readiness.

  • 250 gamedev ux review

    FluxonLab/Skillry/community/Donchitos-Claude-Code-Game-Studios/skills/250-gamedev-ux-review Skill

    no license10★ repo

    Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.