Review & quality
19,016 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
fredhead88/do-it/skills/rev Skill
0★ repoBoot a session into the REVIEWER role for the Albert Scott repo. Use when the user says 'rev', '/rev', 'be the reviewer', 'start the review session', 'this is the rev session', or opens a session whose job is to drive the verification loop, watch what's awaiting prod-verification, spot-check the rendered product, write per-criterion verdicts, and file correctives back to the orchestrator. rev is the standing review twin of orc — one builds, one reviews. It runs on Opus, self-relays on a context ceiling exactly like orc (its OWN relay, never orc's), never touches the build tree, never commits, never authors specs. Invoke at the START of a reviewer session.
fredhead88/do-it/skills/verification-loop Skill
0★ repoUse when verifying shipped work on prod, standing up the autonomous verifier, running the verification loop, confirming a spec is actually done end-to-end, or checking whether shipped criteria are hollow. Trigger phrases include "verify shipped work", "stand up the verifier", "run the verification loop", "is this actually done on prod", "check for hollow specs", "autonomous post-ship review".
lm203688/china-compliance-skills-mirror/skills/cn-compliance-guard Skill
0★ repoScan Chinese text for 200+ banned words across 6 legal categories (广告法/消费者权益保护法), check SEO compliance for 5 platforms (百度/小红书/抖音/淘宝/京东), and provide safe replacement suggestions. Detects 绝对化用语, 医疗效果承诺, 虚假宣传, 金融承诺, 诱导消费, 比较广告. Use when: checking Chinese marketing copy for legal compliance, reviewing product descriptions for advertising law violations, auditing content before publishing on Chinese platforms, replacing banned words with safe alternatives. RUN: ./check.sh '你的文案' --platform douyin for instant scan.
fabioc-aloha/Alex_ACT_Edition/.github/skills/code-review Skill
0★ repoSystematic code review for correctness, security, and growth — not just style enforcement
fabioc-aloha/Alex_ACT_Edition/.github/skills/deep-review Skill
0★ repoAdversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive tension. Use for high-stakes PRs, architectural changes, or when single-pass review would miss issues. Surfaces findings through disagreement, not consensus.
fabioc-aloha/Alex_ACT_Edition/.github/skills/git-workflow Skill
0★ repoApply consistent git practices for branch hygiene, safe commits, and recovery from common mishaps (lost commits, bad merges, accidental pushes). Use when authoring or reviewing a git workflow, recovering broken local state, or sequencing a commit/push that needs explicit user approval before destructive steps.
fabioc-aloha/Alex_ACT_Edition/.github/skills/instruction-review Skill
0★ repoAudits a candidate instruction (.instructions.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence) plus optional Gate 6 (token budget for always-on instructions). Use when reviewing a new instruction draft before commit, evaluating a Mall instruction or store instruction for adoption, or re-auditing existing instructions on a periodic cadence.
fabioc-aloha/Alex_ACT_Edition/.github/skills/lint-clean-markdown Skill
0★ repoWrite markdown that passes markdownlint on first attempt — encode the most common rules as muscle memory
fabioc-aloha/Alex_ACT_Edition/.github/skills/prompt-review Skill
0★ repoAudits a candidate prompt (.prompt.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence). Use when reviewing a new prompt draft before commit, evaluating a Mall prompt or store prompt for adoption, or re-auditing existing prompts on a periodic cadence.
fabioc-aloha/Alex_ACT_Edition/.github/skills/skill-review Skill
0★ repoAudits a candidate skill (.github/skills/<name>/SKILL.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence). Use when reviewing a new skill draft before commit, evaluating a Mall unit or store skill for adoption, or re-auditing existing skills on a periodic cadence. For instructions, prompts, agents — use the matching per-type review skill.
felixhennequin-gif/claude-code-config-template/.claude/skills/core/git-workflow Skill
0★ repoGit branching, commit, and PR conventions. Activates when creating a branch, writing a commit message, opening a pull request, resolving merge conflicts, or reviewing git history.
felixhennequin-gif/claude-code-config-template/cli/template-files/claude/skills/core/code-review Skill
0★ repoStructured workflow for acting on an external code review — triage findings by severity and effort, write a prioritized roadmap to /tmp/roadmap.md, then hand execution prompts to Claude Code batch by batch. Activates when the user receives a review, audit, or critique of their repo and wants to act on it. Also triggers on "triage this review", "make a roadmap from this feedback", "act on these findings", "we have a list of issues to fix".
felixhennequin-gif/claude-code-config-template/cli/template-files/claude/skills/core/git-workflow Skill
0★ repoGit branching, commit, and PR conventions. Activates when creating a branch, writing a commit message, opening a pull request, resolving merge conflicts, or reviewing git history.
juncoding/nextjs-fullstack-starter/skills/nfs-review-project Skill
0★ repoReview an existing project scaffolded with nextjs-fullstack-starter against the architectural invariants and patterns. Use this whenever the user wants to audit project conventions, asks 'does this follow our patterns', wants a pre-PR architecture check, suspects drift, is onboarding a new contributor, or invokes /nfs-review-project. Runs a mechanical check script for fast objective violations (missing server-only, DB queries in src/app/, missing requirePermission on mutations, missing audit, wrong cache primitives, tRPC imports from the wrong stack), then samples files for judgment calls, then produces a categorized report grouped by severity (must fix / should fix / notes / passing).
rokurokulab/dotai/claude/plugins/dotai-base/skills/commit-message Skill
0★ repoGenerate a Conventional Commits message from staged or unstaged changes. Use when the user asks for a commit message, says "commit this", or wants help writing the subject/body for changes already in the working tree.
rokurokulab/dotai/codex/skills/code-review Skill
0★ repoReview a diff (staged, branch, or PR) for correctness, hidden state changes, missing tests, and convention drift. Use this when the user asks for a review, second opinion, or sanity check on changes they're about to commit or merge.
rokurokulab/dotai/codex/skills/commit-message Skill
0★ repoGenerate a Conventional Commits message from staged or unstaged changes. Use when the user asks for a commit message, says "commit this", or wants help writing the subject/body for changes already in the working tree.
rokurokulab/dotai/shared/skills/code-review Skill
0★ repoReview a diff (staged, branch, or PR) for correctness, hidden state changes, missing tests, and convention drift. Use this when the user asks for a review, second opinion, or sanity check on changes they're about to commit or merge.
rokurokulab/dotai/shared/skills/commit-message Skill
0★ repoGenerate a Conventional Commits message from staged or unstaged changes. Use when the user asks for a commit message, says "commit this", or wants help writing the subject/body for changes already in the working tree.
marzun9620/agent_skills/planning/skills/grill-me Skill
no license0★ repoInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
The same file is in 23 other repositories
marzun9620/agent_skills/planning/skills/grill-with-docs Skill
no license0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
The same file is in 8 other repositories
marzun9620/agent_skills/workflow/skills/workflow-codex-plan-review Skill
no license0★ repoDelegate plan review to Codex CLI. Detects critical issues before showing the plan to the user. Iterative Initial Review + Re-review (resume --last) pattern; up to 5 loops. Triggers: /plan review, Codex plan review, plan quality check.
marzun9620/agent_skills/workflow/skills/workflow-codex-review Skill
no license0★ repoDelegate code review to Codex CLI in a read-only sandbox. Mode A: per-task review (git diff HEAD~1). Mode B: PR review (gh pr diff). Triggers: /run review, /review, Codex review delegation, code review.
marzun9620/agent_skills/workflow/skills/workflow-pr-create Skill
no license0★ repoPR creation flow. Verify all task checks pass, then create the PR with `gh pr create`. If the plan has a Linear ID, update Linear too. Triggers: PR creation, pull request, ship, gh pr create, merge request, code review request.
BTN101/claude-skill-pack/skills/engineering/security-review Skill
0★ repoUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
The same file is in 3 other repositories
BTN101/claude-skill-pack/skills/layers/design-layer Skill
0★ repoActivate this skill group for any UI, UX, visual design, or interface quality task. Triggers include: the UI looks generic, this looks like AI slop, redesign this, audit this interface, add animations, add micro-interactions, make this feel more polished, Framer Motion, motion design, design review, critique this layout, improve the visual hierarchy, it feels flat, the onboarding is bad, empty state, loading state looks ugly, make it feel premium, and any request where the goal is improving how something looks or feels rather than how it works. Also triggers when Seb shares a screenshot and asks for feedback on the visual design.
BTN101/claude-skill-pack/skills/security/code-review Skill
0★ repoPerform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.
The same file is in 4 other repositories
BTN101/claude-skill-pack/skills/security/gha-security-review Skill
0★ repoGitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks. Exploitation-focused with concrete PoC scenarios.
vdk888/bubble-skills/fund-source-verification Skill
0★ repoSource-tier classification + independent-verification rubric for any external signal (news, Substack, paywalled wires, sentiment trackers). Load whenever you're about to act on a third-party claim or write "<outlet> reports X" in a memo.
l4ci/hv-skills/hv-learn Skill
0★ repoExtract durable session learnings (gotchas, conventions, constraints) into .hv/KNOWLEDGE.md grouped by topic, and update the CLAUDE.md topic index. Use at end of a session that surfaced reusable knowledge, after a correction-rich debugging arc, or on "save what we learned", "capture this learning", "/hv-learn". Opus verification is on by default via learn.verify in config.json; set to false for fast/cheap mode.
l4ci/hv-skills/hv-pause Skill
0★ repoGracefully pause mid-session — writes a handoff note (current hypothesis, next planned step, mid-edit files, uncommitted work strategy) to .hv/handoff/<branch>.md so /hv-next in a fresh session can pick up with full context, not just git state. Use when the session is approaching a context limit, you need to hand off, or you want to stop a long /hv-work cycle cleanly.
l4ci/hv-skills/hv-review Skill
0★ repoStaff-engineer review of a feature branch before merge or PR — reads commits, diff, referenced item IDs, and matching KNOWLEDGE.md topics; dispatches an Opus reviewer that checks intent match, convention compliance, and quality. Returns PASS / CONCERNS / FAIL. Use on "review this", "check before I ship", "look over the branch", or implicitly from /hv-ship.
l4ci/hv-skills/hv-spike Skill
0★ repoThrowaway feasibility experiment on a dedicated git branch — answers a specific question without polluting main or the backlog. Creates spike/<name> branch and .hv/spikes/<name>.md for question + findings + decision. Branch is never merged; only findings come back. Use when you need to try X before committing to it ("can we use SSE?", "does this library handle our scale?").
aksheyw/claude-code-learned-skills/skills/prompting-qwen3-coder Skill
0★ repoHow to prompt and run Qwen3-Coder (qwen3-coder:30b via Ollama) — a NON-thinking model with no deliberation channel, optimised as an agentic patch-writer (though it CAN critique — measured). Covers the official sampling params, tool calling as the vendor's structured path, the 256K/YaRN context story, and the "silent or flooding" failure signature — including the measured finding that a reviewer prompt's own suppression clauses, NOT grammar-forced JSON, silence it. Use when prompting Qwen3-Coder, wiring it into a local council/review seat, debugging an empty or fabricating seat, tuning sampling, or deciding whether it is the right model for a job.
3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-check-todos Skill
0★ repoList pending todos and select one to work on
The same file is in 1 other repository
3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-pr-branch Skill
0★ repoCreate a clean PR branch by filtering out .planning/ commits — ready for code review
The same file is in 1 other repository
3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-review-backlog Skill
0★ repoReview and promote backlog items to active milestone
The same file is in 1 other repository
3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-review Skill
0★ repoRequest cross-AI peer review of phase plans from external AI CLIs
The same file is in 1 other repository
3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-ui-review Skill
0★ repoRetroactive 6-pillar visual audit of implemented frontend code
The same file is in 1 other repository
SkillMedev/engineering-manager-toolkit/skills/performance-review-writer Skill
0★ repoWrites fair, specific, evidence-based performance reviews and ratings. Use when drafting or preparing for calibration to reduce recency bias and vague praise or criticism.
The same file is in 1 other repository
SkillMedev/engineering-manager-toolkit/skills/team-health-check Skill
0★ repoAssesses a team's health across three independent dimensions - delivery, morale, and clarity - using observable signals from the last 8 weeks, then maps each red or yellow signal to one manager action with a 2-week horizon. Use when a manager asks "is my team okay", "how do I tell if morale is slipping", "we keep missing sprints and I don't know why", or wants a quarterly team health review. Do NOT use for facilitating a single sprint retrospective - use sprint-retro-facilitator instead - for structuring individual 1:1s - use 1on1-agenda - or for defining how a new team works together - use team-charter instead.
The same file is in 1 other repository
Uhudsavasindankacanokcu2/ecommerce-skills-for-claude/review-analyzer Skill
no license0★ repoAnalyze product reviews (yours or a competitor's) to extract what customers love, what they complain about, and concrete product/listing improvements. Produces themed sentiment breakdown, top complaints ranked by frequency, and an action list. Use when the user pastes reviews, wants to understand customer feedback, do competitor research, or find why a product is/isn't selling.
vermapragya/analytics-skill/skills/sql-correctness-review Skill
0★ repoAudits a SQL query's logic for wrong-results bugs — duplicate rows, join fanout, wrong join types, NULL handling traps, and CASE branch issues — with evidence queries that prove or clear each suspicion. Use when the user says "numbers look wrong", "double counting", "rows are duplicated", "this join is exploding", "check my query logic", or when totals don't reconcile.
vermapragya/analytics-skill/skills/sql-query-review Skill
0★ repoStatic review of a SQL query — finds anti-patterns, structural problems, and performance issues from the query text alone, then proposes an optimized rewrite with a verification plan. Use when the user says "review this query", "check my SQL", "is this query okay", "clean up this query", or "optimize this" without runtime profile data.
Srltas/claude-skills/commit Skill
0★ repoCommit staged changes with a clean, single-line Conventional Commit subject in plain developer English. Use when the user wants to commit changes, write a commit message, or wrap up work with a conventional-commit title. Generates a `type(scope): summary` subject from the staged diff and commits it. Triggers on phrases like 'commit this', 'make a commit', 'write a commit message', 'git commit', 'commit my changes'.
Srltas/claude-skills/cubrid-manual Skill
0★ repoLook up CUBRID engine behavior in the official online manual: SQL syntax, built-in functions, data types, identifiers and reserved keywords, configuration parameters, and JDBC/driver APIs. Fetches the version-pinned manual at www.cubrid.org/manual. Use when you need to verify CUBRID SQL semantics, a function signature, a data type's range, whether a word is reserved, or a config parameter before writing dialect or JDBC code. For CUBRID Migration Toolkit (CMT) questions, use the cmt-manual skill instead. Triggers on phrases like 'how does X work in CUBRID', 'CUBRID syntax for', 'is X a reserved word in CUBRID', 'what functions does CUBRID have', 'check the CUBRID manual'.
Srltas/claude-skills/hhh-dialect-verify-report Skill
0★ repoOne-shot CUBRID dialect verification + report. Runs the hibernate-core test suite against one or ALL CUBRID versions, diffs pass/fail vs a baseline (a prior run's JSON, results dir, or .tgz), and ALWAYS produces a Korean Word (.docx) 비교 분석 report. Use when you want the full 'verify → measure → report' pipeline for a CUBRIDDialect change in one go, or to test across all CUBRID versions. Composes the hhh-dialect-verify and report skills. Triggers on phrases like 'dialect 검증하고 리포트까지', 'CUBRID 전체 버전 테스트 + 보고서', 'verify the dialect and write the report', 'run all CUBRID versions and report'.
Srltas/claude-skills/hhh-dialect-verify Skill
0★ repoRun the Hibernate ORM test suite against CUBRID and measure a dialect change's impact: total failures, +N recovered / −N regressed vs a baseline, and failures grouped by signature/family. Use when verifying a CUBRIDDialect change, an auto_quote or capability-flag toggle, or any Hibernate-vs-CUBRID compatibility measurement. Pairs with the report skill (verify → numbers → 비교 분석 보고서). Triggers on phrases like 'dialect 검증', 'CUBRID 테스트 돌려', 'hibernate 스위트 실행', 'pass/fail 델타 측정', 'run the hibernate suite against CUBRID', 'measure dialect change'.
Srltas/claude-skills/jdbc-ctp-verify-report Skill
0★ repoOne-shot CUBRID JDBC driver verification + report. Builds the CUBRID JDBC driver, runs the CTP JDBC test suite against CUBRID, diffs pass/fail vs a baseline (a prior run's JSON, CTP result dir, or test-jdbc.xml), classifies broken cases (VerifyError, conversion, broker/env, …), and ALWAYS produces a Korean Word (.docx) 비교 분석 report. Use to verify a JDBC driver change or a Java-version/build-target change (e.g. v50 1.6 vs v52 1.8) end to end. Composes parse_ctp.py + the report skill. Triggers on phrases like 'JDBC 드라이버 검증', 'CTP 돌려', 'ctp jdbc 실행하고 리포트', 'verify the JDBC driver with CTP', 'build driver and run CTP'.
Srltas/claude-skills/pr-draft Skill
0★ repoDraft a pull request (title + body) from the current branch's commits and diff. The title is [XXX-0000] plus a concise, easy-to-understand English summary (the key is taken from the branch name); the body is Korean in three sections: Purpose (required, why this PR exists), Implementation (optional, how it was built), Remarks (optional, notes). Optional sections become N/A when empty. Produces a copy-paste draft only; it does not create the PR. Triggers on phrases like 'PR 초안 작성', 'pr-draft', '이 브랜치 PR로 정리', 'draft a PR', 'PR 제목이랑 본문 만들어줘'.
Srltas/claude-skills/review-triage Skill
0★ repoTriage the review comments on your pull request. Fetches a PR's reviews (inline code comments, review summaries, and PR-level comments, from humans and bots) and, for each, gives an easy Korean summary, judges whether it is valid by checking the actual code, then either drafts a fix plan (if valid) or a reasoned reply explaining why not (if not). Analysis and drafts only: it does not post replies or change code. Use when your PR has review feedback you want to understand and respond to. Triggers on phrases like 'PR 리뷰 정리해줘', '리뷰 코멘트 타당한지 봐줘', '리뷰 대응', 'triage my PR reviews', 'help me respond to PR review'.
Punpun1643/claude-skills/git-commit Skill
no license0★ repoWrite clear, well-structured git commit messages that follow the Conventional Commits specification. Use this whenever you are about to commit staged or unstaged changes, write or rewrite a commit message, amend or squash commits, or are asked to "commit this", "write a commit message", or "clean up the history" — even when the user never says the words "conventional commits". Also use when configuring commit linting (commitlint/husky), generating a CHANGELOG, or reasoning about which semantic-version bump a set of changes implies.
NeuralMedic-DE/claude-skills/healthcare-data-interop Skill
0★ repoBuild and validate healthcare-data pipelines and de-identify PHI, gated by checks that actually run — structural FHIR R4 validation, HL7 v2.x parsing, a Safe-Harbor PHI regex scan, and pydicom-based DICOM header de-identification with a re-read verify step. Use when the user works with DICOM, HL7 v2, or FHIR data; needs to ingest/transform/map clinical data; wants to de-identify or anonymize PHI; checks interoperability conformance; or builds a healthcare data pipeline. Triggers: "DICOM", "HL7", "FHIR", "de-identify PHI", "anonymize patient data", "healthcare data pipeline", "interoperability", "Safe Harbor", "US Core", "IHE".
NeuralMedic-DE/claude-skills/iac-compliance-review Skill
0★ repoReview Terraform / infrastructure-as-code for security and compliance gaps and EU data residency, gated by a check that actually runs over the plan — it parses `terraform show -json` output, applies a policy catalog (public storage, unencrypted data, open security groups, wildcard IAM, missing logging, non-EU regions, missing tags, public IPs), maps each finding to ISO 27001 Annex A / SOC 2 TSC / GDPR articles, and fails the build on blocking-severity findings. Use when the user wants an IaC security or compliance review, a cloud-config audit, a data-residency check, or to gate Terraform in CI. Triggers: "Terraform", "infrastructure as code", "IaC security", "cloud compliance", "data residency", "ISO 27001", "SOC 2", "GDPR", "encryption", "IAM".
NeuralMedic-DE/claude-skills/odoo-addon-publisher Skill
0★ repoProduce sale-ready Odoo addons/modules that follow the Odoo Apps Store vendor guidelines for Odoo 18.0 and 19.0, gated by a validator that runs. Scaffolds a guideline-compliant module (manifest, company/vendor info, OPL-1 licensing, static/description/index.html, icon, cover image and screenshots) and verifies any addon against the rules. Use when the user wants to build, package, publish or submit an Odoo app/module/addon, fix a __manifest__.py, prepare an App Store listing, add a cover image/icon/screenshots, or check Odoo Apps compliance. Triggers: "Odoo module/addon/app", "publish to Odoo Apps", "__manifest__.py", "OPL-1", "Odoo App Store", "Odoo 18 / 19 module".
jaballer/react-claude-skills/react-forms-validation Skill
0★ repoComprehensive form patterns for React 19 / Next 15 — Zod schemas with type inference, Server Actions + useFormStatus + useActionState, useOptimistic for instant feedback, react-hook-form when Server Actions aren't on the table, multi-step forms with useReducer + persistence, async validation, file upload with progress, error messages with full a11y wiring (aria-invalid, aria-describedby, role=alert, focus management on errors). Use for any form-heavy interview build — newsletter signup, contact form, login, signup, multi-step onboarding, settings page, file upload. Triggers on "form", "validation", "zod", "react-hook-form", "Server Action", "useFormStatus", "useActionState", "useOptimistic", "controlled vs uncontrolled", "multi-step form", "file upload", "form a11y", "form errors", "newsletter signup".
jaballer/react-claude-skills/react-interview-async-slack Skill
0★ repoNavigate the async-with-Slack-access technical interview format (Netlify and similar). The engineers will explicitly invite frequent questions and proactively check in — but the senior calibration is to ask ORGANICALLY when it makes sense, not on a schedule and not to perform engagement. Includes the ask-vs-commit decision matrix, Slack message templates (clarifying question, idea sanity check, stuck moment, response to check-in, submission), professional async tone, what makes a question senior vs. needy, the "I'm going with X, flag if wrong" pattern. Use during any time-boxed coding interview that includes a chat channel with the hiring engineers. Triggers on "Slack interview", "async interview", "ask vs commit", "clarifying question", "interview communication", "Netlify interview", "technical project", "during the build", "Slack channel", "async build".
0jg/skills/hooks Skill
no license0★ repoConfigures Claude Code hooks for a project. Use this skill at project initialisation time to write .claude/settings.json with pre-commit gates. Also use when the user asks to set up hooks, enforce commit standards, or add pre-commit checks. The hook blocks any git commit that fails ruff, ty, or pytest — no exceptions.
samulee003/agentic-ppt-skills/skills/presentation-product-grill Skill
0★ repoTurns a source inventory into a presentation brief by resolving audience, problem, outcome, promise, constraints, and success decisions through one-question-at-a-time product grilling. Use when the product-grill gate is current for a presentation project or when a router asks for the presentation brief and consequential decision log.
samulee003/agentic-ppt-skills/skills/presentation-stage-grill Skill
0★ repoTests a live prototype or deck as a talk by grilling actual renders, current notes, timing, transitions, and audience challenges, then produces a speaker script. Use when the stage-grill gate is current for a presentation project or when a router asks for speakability, trimming, audience-risk review, and `SPEAKER-SCRIPT.md`.