project-review
Run an independent, system-aware review of an exact candidate revision before serious work is called finished or ready to ship.
Skill by executiveusa
Chalk Labs
Need help deploying project-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/executiveusa-project-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/project-review
What's inside
- Skill name
project-review- Description
- Run an independent, system-aware review of an exact candidate revision before serious work is called finished or ready to ship.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Project Review Use this after implementation and before proof/release for consequential work. ## Why The builder should not be the only reviewer. Vibe Engineering uses `executiveusa/open-code-review`, derived from Alibaba OpenCodeReview (Apache-2.0), as the preferred deterministic review engine when it is available. Vibe adds system-impact review, stop-slop, taste, proof, ownership, rollback, and explicit release authority. ## Procedure 1. Identify the exact candidate revision, diff range, or files being reviewed. 2. Run the repository review engine when available. Prefer the Vibe-enabled `executiveusa/open-code-review` integration rather than an improvised generic review. 3. Review beyond isolated lines of code: callers, contracts, authentication/security, data/state, user journeys, tests, deployments, and connected repositories. 4. Keep reviewer context independent from the builder whenever practical. 5. Resolve, explicitly accept, or escalate material findings. Never silently drop unresolved findings. 6. Pass the reviewed candidate into Stop Slop, Taste, Proof, and the authorized release decision. ## Completion rule Project Review can report findings and evidence. It cannot authorize production release. `SHIP` or `HOLD` remains with the Vibe Judge, owner, or other explicitly authorized human. ## Attribution Review engine: `executiveusa/open-code-review`, forked from `alibaba/open-code-review` under Apache-2.0. Vibe-specific governance, system-impact, proof, and release boundaries are authored by Vibe Engineering.
From executiveusa/vibe-engineering, MIT.
More from executiveusa/vibe-engineering
- 0.592score
loop-engineering
executiveusa
ICM-based zero-to-verified engineering workflow.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
vibe-engineering
executiveusa
Govern product and software work with V.I.B.E.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
icmr-universal-compiler
executiveusa
Detect and compile any role, project, workflow, organization, knowledge domain, record system, or existing repository into a reusable ICM Runtime…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
icm-architect
executiveusa
Design any process, idea, problem, or body of knowledge into an ICM (Interpretable Context Methodology) workspace — folder structure as agent architecture —…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
multiverse-proof
executiveusa
Antithesis-style deterministic simulation testing for the vibe factory, free-tier build.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
mobile-first-site-proof
executiveusa
Final mobile-first, motion, truth, accessibility, browser, deployment and proof gate for an existing website, web app, portfolio, campaign or dashboard.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
refero-design
executiveusa
Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
vibe
executiveusa
Route work through Vibe Engineering.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
setup-vibe
executiveusa
Configure a repository so Vibe Engineering skills know where project context, decisions, issues, proof, and release rules live.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
starnet-refero-research
executiveusa
House wrapper for the vendored refero-design skill.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
human-voice
executiveusa
Rewrite robotic AI copy into clear human language without changing facts or inventing details.
SkillBFreshness: B★ 1Claude Code +9 - 0.536score
proof
executiveusa
Verify important claims against the exact candidate revision before calling work done.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 7
- Last commit (this folder)
- Sep 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/executiveusa/vibe-engineering
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from executiveusa
- 0.592score
loop-engineering
executiveusa
ICM-based zero-to-verified engineering workflow.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
vibe-engineering
executiveusa
Govern product and software work with V.I.B.E.
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
bookee
executiveusa
Make an ebook from an interview.
SkillAFreshness: AClaude Code +9 - 0.559score
nonprofit-audit
executiveusa
Run a full per-organization website trust, legal-basics and funding-readiness audit for a nonprofit or social-purpose company, then produce the report and…
SkillAFreshness: AClaude Code +9 - 0.552score
icmr-universal-compiler
executiveusa
Detect and compile any role, project, workflow, organization, knowledge domain, record system, or existing repository into a reusable ICM Runtime…
SkillBFreshness: B★ 1Claude Code +9 - 0.551score
legal-basics-review
executiveusa
Identify missing or inconsistent legal basics on a nonprofit site (privacy, donor wording, registration, children's data, consent, accessibility).
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get project-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
project-review skill. Agent Mart. https://agentmart.dev/skills/executiveusa-project-review (last updated 2026-10-24)