Skip to content
Agentmart
Submit a tool

ae-work

Implement a concrete request or plan.

Skill by AndreaCatalucci

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ae-work?

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.

Book a call

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/andreacatalucci-ae-work

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.

We use your email only for this newsletter. Privacy

About

Implement a concrete request or plan. Use for building or changing code; use ae-debug when the main problem is discovering why something fails.

No 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/ae-work

What's inside

Skill name
ae-work
Description
Implement a concrete request or plan. Use for building or changing code; use ae-debug when the main problem is discovering why something fails.
License
MIT
Instructions
25 lines in SKILL.md · view on GitHub

Files (7)

  • SKILL.md
  • autonomous.md · recipes/
  • dogfood.md · recipes/
  • optimize.md · recipes/
  • polish.md · recipes/
  • simplify.md · recipes/
  • worktree.md · recipes/

SKILL.md (first lines)

# Work

1. Read the request or plan and inspect the affected code. Reuse relevant project lessons and current evidence. Preserve unrelated user changes.
2. If a missing product decision would materially change the result, ask. Otherwise make the smallest reasonable assumption and state it briefly.
3. Implement the complete requested behavior using existing patterns. Remove complexity when that is simpler than extending it.
4. When architecture changes, update or create every affected current-state C4 artifact under `docs/architecture/`. Each view is one Markdown file with its scope, verification basis at a named implementation revision, and one Mermaid block. The basis names inspected code, configuration, or checks.
5. Verify the changed acceptance behavior. Reuse existing coverage; where it is missing, add the smallest meaningful test or direct check that would detect an incorrect result. Run required repository checks and check affected architecture artifacts. Repeat only after relevant changes or conflicting evidence.
6. If an Implementation Plan guided this work, mark only criteria supported by that evidence complete and record the architecture result. Leave unverified criteria open with the missing check named.
7. Report what changed, what was checked, which architecture artifacts changed, and any real limitation.
8. Follow the request's review disposition. If it has none, run `ae-review` only when a named material risk remains after the direct checks: a trust or security boundary, irreversible data change, concurrency, a public compatibility contract, a broad cross-module refactor, or conflicting evidence. Skip review for low-risk, well-covered changes.

The user's request defines which adjacent actions—planning, review, browser work, and Git operations—join implementation. A trajectory change is a lesson.

Load at most one matching file from `recipes/` before acting:

- [`autonomous.md`](recipes/autonomous.md) for explicitly hands-off delivery;
- [`optimize.md`](recipes/optimize.md) for measurable improvement;
- [`simplify.md`](recipes/simplify.md) for behavior-preserving cleanup;
- [`polish.md`](recipes/polish.md) for interactive UI refinement;
- [`dogfood.md`](recipes/dogfood.md) for real-flow product use;
- [`worktree.md`](recipes/worktree.md) for isolation.

Load another recipe only when the request actually crosses that boundary.

From AndreaCatalucci/andrea-engineering, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 6, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from AndreaCatalucci

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 ae-work 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ae-work?

CallGet help
Cite this page

ae-work skill. Agent Mart. https://agentmart.dev/skills/andreacatalucci-ae-work (last updated 2026-10-24)