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.
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.
About
Use cases: data
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/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.
More from lucasbayma/skills
- 0.479score
candango-uat
lucasbayma
Candango UAT.
SkillCFreshness: CClaude Code +9 - 0.479score
candango-executor
lucasbayma
Candango Executor.
SkillCFreshness: CClaude Code +9 - 0.479score
candango-setup
lucasbayma
Candango Setup.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-discover
lucasbayma
Candango Discover.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-issues
lucasbayma
Candango Issues.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-uat-runner
lucasbayma
Candango UAT Runner.
SkillCFreshness: CClaude Code +9 - 0.474score
check-pr-comments
lucasbayma
Check PR Comments.
SkillCFreshness: CClaude Code +9 - 0.474score
spec-aware-pr-review
lucasbayma
Perform a pull request review grounded in code quality and the full history of related specifications.
SkillCFreshness: CClaude Code +9 - 0.474score
fix-pr-checks
lucasbayma
Monitors GitHub PR checks every 60 seconds, fixes failing checks, and reports failures and fixes in Caveman-style tables.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-design
lucasbayma
Candango Design.
SkillCFreshness: CClaude Code +9 - 0.469score
candango-plan
lucasbayma
Candango Plan.
SkillCFreshness: CClaude Code +9
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
- Repository
- github.com/lucasbayma/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lucasbayma
- 0.479score
candango-uat
lucasbayma
Candango UAT.
SkillCFreshness: CClaude Code +9 - 0.479score
candango-executor
lucasbayma
Candango Executor.
SkillCFreshness: CClaude Code +9 - 0.479score
candango-setup
lucasbayma
Candango Setup.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-discover
lucasbayma
Candango Discover.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-issues
lucasbayma
Candango Issues.
SkillCFreshness: CClaude Code +9 - 0.474score
candango-uat-runner
lucasbayma
Candango UAT Runner.
SkillCFreshness: CClaude 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 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.
Cite this page
candango-wrap-up skill. Agent Mart. https://agentmart.dev/skills/lucasbayma-candango-wrap-up (last updated 2026-10-24)