Skip to content
Agentmart
Submit a tool

candango-wrap-up

Candango Wrap-Up.

Skill by lucasbayma

IndexedMIT
Write a review

Chalk Labs

Need help deploying candango-wrap-up?

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/lucasbayma-candango-wrap-up

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

Candango Wrap-Up. Wraps completed feature work into a clean pull request with caveman summary, UAT status, validation evidence, and temporary dashboard cleanup. Use when the user asks to wrap up, finalize, prepare PR, create PR, ship feature work, or clean temporary feature dashboard files.

Use cases: data

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/candango-wrap-up

What's inside

Skill name
candango-wrap-up
Description
Candango Wrap-Up. Wraps completed feature work into a clean pull request with caveman summary, UAT status, validation evidence, and temporary dashboard cleanup. Use when the user asks to wrap up, finalize, prepare PR, create PR, ship feature work, or clean temporary feature dashboard files.
License
MIT
Instructions
97 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Candango Wrap-Up

Finalize feature work and create a PR.

All user-facing communication and PR text must use `$caveman`.

## Inputs

Read:

- `docs/features/<feature-slug>/plan.md`
- `issues.md`, `uat.md`
- dashboard state when present
- current git branch, diff, commits, and remote
- validation commands from repo docs or CI config

If feature folder or PR target branch is ambiguous, ask once.

## Workflow

### 1. Clean Temporary Files

Remove generated dashboard runtime files that should not ship:

- `docs/features/<feature-slug>/index.html`
- `docs/features/<feature-slug>/state.json`
- `docs/features/<feature-slug>/state.json.lock`
- hidden temp files matching dashboard atomic-write leftovers

Do not remove plan/issues/UAT/design artifacts unless user asks.

### 2. Verify

Run:

- focused tests touched by implementation
- final validation command when known
- lint/typecheck when cheap and relevant
- UAT status check from `uat.md`

If UATs exist:

- list checked UATs as `[x]`
- list missing/unconfirmed UATs as `[ ]`
- do not claim UAT complete unless all required scenarios are checked

### 3. Classify PR

- `[bugfix]` for defect fixes, regressions, failed UAT fixes, or production bug work
- `[chore]` for docs, tooling, tests-only, dependency, cleanup, or internal maintenance
- `[feat]` for user-visible product behavior or new capability

Title format: `[feat|chore|bugfix] <clear implementation title>`. Use implementation-specific title, not generic feature folder name.

### 4. Commit

Before staging:

- inspect `git status -sb`
- inspect diff
- stage only intended files
- never stage unrelated user changes silently

Commit message should be terse and match the PR scope.

### 5. Create PR

Use GitHub CLI or configured connector. PR description must use caveman style:

```md
## Summary
- <what changed>
- <why>

## UAT
- [x] UAT-001 <short title/evidence>
- [ ] UAT-002 <reason unmarked>

## Validation
- <command>: pass/fail/not run

## Cleanup
- removed temporary dashboard files: yes/no
```

Default to draft PR when validation or required UAT is missing. Mark ready only when user asks or all required checks are complete.

## Stop Conditions

Pause before PR when:

- unrelated worktree changes are mixed with feature changes
- final validation fails
- required UATs remain unconfirmed and user asked for ready PR
- branch/remote/auth is missing

From lucasbayma/skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 25, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from lucasbayma

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 candango-wrap-up 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 candango-wrap-up?

CallGet help
Cite this page

candango-wrap-up skill. Agent Mart. https://agentmart.dev/skills/lucasbayma-candango-wrap-up (last updated 2026-10-24)