Skip to content
Agentmart
Submit a tool

deliver

Prepare a reviewable PR from a verified candidate.

Skill by douglasjarquin

IndexedMIT
Write a review

Chalk Labs

Need help deploying deliver?

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/douglasjarquin-deliver

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

Prepare a reviewable PR from a verified candidate. Use after coordinator verification, never to merge.

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 and code. Checked Nov 2, 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/deliver

What's inside

Skill name
deliver
Description
Prepare a reviewable PR from a verified candidate. Use after coordinator verification, never to merge.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deliver

## When to use it

The worker reported a candidate and your distinct verification run is recorded.
Use this to open or update a PR.
Do not use it to merge.

## Required inputs and access

The task brief, report, and `/workspace/sum/tasks/<id>/verification.md`.
GitHub access for the named repository.
The user merges.

## Sequence of work

1. Confirm verification.md is your run for this candidate, not the worker's claim.
   Before push or opening a pull request, append `intended` to `/workspace/sum/action-log.md`, then append `done` or `failed` after.
   Do not send, publish, or merge.
2. Default to a fresh independent review with the Compound Engineering review skills before opening or updating the PR.
   The worker Bot cannot review its own candidate.
   Treat any added code comment or edit to an existing code comment in the candidate diff as a blocking finding. This covers line and block comments, docblocks and doc comments, and comment text in fixtures and configuration files. Do not flag comments left unchanged while surrounding code changes. Commit messages, PR descriptions and report text are not code comments. Lines or comments required for a tool or format to work are allowed, including shebangs, repository-required license headers, build tags, lint-disable pragmas, and directives such as `// @ts-expect-error`; a directive may be added only when the code cannot work without it and must include no explanatory prose.
   Treat any added or expanded test, and any deleted, rewritten, skipped or disabled existing test, in the candidate diff as a blocking finding, unless the user explicitly asked for that test in this task. Do not flag a candidate because existing tests still run.
   If that review did not happen, say so if skipped.
   Before `reviewer launch`, append `intended` to `/workspace/sum/action-log.md` with the task and candidate SHA as the target, then append `done` or `failed` after; the same candidate inside six hours is `skipped-duplicate` unless the user asked again.
   When sum launches the reviewer, use the helper's `reviewer launch TASK_ID`: it creates a `reviewer` tab in the task workspace at the task checkout, records that pane as the reviewer endpoint, and prompts it once to review the current candidate (with `--policy-reviewed` guidance when the candidate changed verification policy). Never split the worker pane for a reviewer. Explicit `--harness/--model/--reasoning/--preset` flags win, then a saved `reviewer.preset` supplies its harness and argv, otherwise the coordinator's harness is used. Run it again for a new candidate: a live recorded reviewer pane is prompted instead of a second tab, never duplicated; a reviewer proven gone (recorded closed, `pane_not_found`, or `agent_not_found` with no occupant) gets a fresh `reviewer` tab, a rebind recorded with the `bind --reviewer-pane` stop proof, and the kickoff prompt (`action: relaunched`); a gone worker workspace is refused with `herdr worktree open --path CHECKOUT --no-focus`.
3. Push the recorded branch without force.
4. Open a PR or adopt the one GitHub already has for that branch.
   Do not open a new PR when the only pull requests for the branch are closed, unless the user says to.
5. Show the user the full PR URL and that the merge decision is still theirs.
6. After the user says it merged, clean up only the worker Bot and files you can prove are finished.
   Leave unfinished work in place.

## How to validate the result

The PR head matches the verified candidate.
verification.md still names that candidate.
The Bot did not merge.

## What to return

The PR URL, what you verified, and that the user still decides the merge.

## What requires approval

Merge.
Force-push.
Deleting unfinished work.
Waiving a failing required check.

From douglasjarquin/sum, MIT.

More from douglasjarquin/sum

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
Oct 15, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from douglasjarquin

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 deliver 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 deliver?

CallGet help
Cite this page

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