agentsclimarketplace
Sign in

Project intake audit

Skill codezelat/codezela-web-skills/skills/project-intake-audit

Use when starting work in an unfamiliar repo, broad production-readiness task, risky feature, deployment check, admin/CMS setup, or when the user asks to inspect, audit, check everything, or understand before edits.From its SKILL.md

Install
npx -y skills add codezelat/codezela-web-skills --skill project-intake-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.6 KB, 500 tokens by cl100k_base, as published. Nobody here has run it

Project Intake Audit

Use this before implementation when wrong assumptions could create churn. The goal is to find the real path, not to produce a generic plan.

Non-Negotiables

  • Inspect the current repo before writing code.
  • Read repo instructions first: AGENTS.md, README.md, .env.example, package scripts, framework config, and relevant local skills/docs.
  • Check dirty worktree state and never overwrite unrelated user changes.
  • Preserve current architecture, data layer, and UI patterns unless the user explicitly asks for redesign/refactor.
  • If Figma, screenshots, live URLs, or brand assets are provided, identify the exact source of truth and how to access it before UI implementation.
  • If a tool/framework/provider is version-sensitive, read local bundled docs or current official docs before editing.
  • If content, imagery, provider settings, or current best practice is uncertain, identify what needs research before implementation.
  • Do not treat memory, another repo, or an older project as confirmed-current fact.

Workflow

  1. Check pwd, git status --short, branch, package manager, and dirty files.
  2. Read project instructions, package scripts, framework config, env examples, route structure, and deployment config.
  3. Identify stack: framework version, UI system, design source, auth, database, storage, email, captcha, analytics, deploy target.
  4. Map existing patterns: data access, validation, forms, server/client boundaries, layouts, components, scripts, docs, and testing.
  5. Identify exact user intent and scope: public site, admin, DB, media, forms, SEO, performance, security, deploy, or verification.
  6. List risks: secrets, migrations, live data, deploy env, provider dashboards, content/image rights, cache/crawler behavior, dirty unrelated work.
  7. Choose the next specialist skill sequence.

Output

  • Current stack, design source, and version-sensitive docs that matter.
  • Relevant route/data/component map.
  • Existing patterns to preserve.
  • Risks, blocked facts, and env/provider dependencies.
  • Proposed skill sequence and immediate next action.

Do Not

  • Start coding before this audit when the user asks for "fully", "prod ready", "check everything", or gives a large brief.
  • Assume a previous repo's schema, env, route names, or provider setup still applies.
  • Say something is ready before the relevant real path has been verified.

What ships with it: 1 file

306 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.