Skip to content
Agentmart
Submit a tool

implement

Execute a validated issue or plan — write code against acceptance criteria, run tests continuously, cross-check ACs, self-review, and commit.

Skill by atalariq

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying implement?

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/atalariq-implement

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

Execute a validated issue or plan — write code against acceptance criteria, run tests continuously, cross-check ACs, self-review, and commit. Use when you have an issue from write-todo or a plan from write-prd and are ready to implement. Triggered by /implement.

Use cases: writing, productivity

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/implement

What's inside

Skill name
implement
Description
Execute a validated issue or plan — write code against acceptance criteria, run tests continuously, cross-check ACs, self-review, and commit. Use when you have an issue from write-todo or a plan from write-prd and are ready to implement. Triggered by /implement.
License
MIT
Instructions
68 lines in SKILL.md · view on GitHub

Files (4)

  • SKILL.md
  • batch-git-operations.md · references/
  • error-handling.md · references/
  • verification.md · references/

SKILL.md (first lines)

# Implement — Execute an Issue

Take a validated issue from the pipeline and implement it.

## Process

### 0. Confirm

Read the issue body, acceptance criteria, and any related spec. Present a summary to the user and wait for confirmation before proceeding.

### 1. Set up workspace

Use the `worktree` skill to create an isolated branch:
```bash
git worktree add ../<project>-<feature> -b feat/<feature>
cd ../<project>-<feature>
```

### 2. Execute tasks

Work through each task continuously:

- Implement one task at a time — follow the acceptance criteria, write minimal code
- Run the project's test suite after each task (e.g., `go test`, `vitest`, `pytest`)
- Fix any failures before continuing
- Mark tasks complete with `[x]` as you go

**Keep it minimal.** Implement the criteria, nothing more. No speculative features.

**Follow conventions.** Read neighboring files, check package manifests, reuse existing utilities. Do not introduce new dependencies without checking first.

### 3. Self-review

After all tasks are done, run a quick self-review (see [verification.md](references/verification.md)):

- Cross-check each acceptance criterion against the implemented code
- Scan for speculative code outside the issue scope
- Verify commit messages follow conventional commit format

### 4. Commit

```bash
git add -A
git commit -m "feat: <summary of what was implemented>"
```

## When to Stop

Stop execution and ask the user when:
- A test failure persists after 3 fix attempts
- You need clarification (ambiguous AC, missing context, conflicting requirements)
- A dependency is missing or cannot be resolved

See [error-handling.md](references/error-handling.md) for the full retry and escalation strategy.

## Next Steps

After committing, suggest the next step:
- **`code-review`** — formal review of the implementation
- **`context-sync`** — if new domain terms or conventions emerged

## Tips

- The `tdd` skill is available for stricter test-first discipline — load it if the project uses a test framework and you want red-green-refactor cycles
- Convention rules live in the project's `CONTEXT.md`, not in this skill — read it when working in an unfamiliar codebase
- For bulk file renames/reorganizations across a repo, see [batch-git-operations.md](references/batch-git-operations.md) — use `execute_code` with Python, not shell loops

From atalariq/skills, MIT.

More from atalariq/skills

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jun 10, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from atalariq

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 implement 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 implement?

CallGet help
Cite this page

implement skill. Agent Mart. https://agentmart.dev/skills/atalariq-implement (last updated 2026-10-24)