Skip to content
cccskills
FreePublished on GitHub

feature-publish

Commit a completed feature and prepare a pull request describing its design, tests, and demos. Follow the selected publication mode, and for direct publication, work through automated checks and review feedback before requesting maintainer review.

OriginalShow the original description

Commit the feature, write the PR body, publish in the selected mode, and drive the PR.

See how to install

Good for

  • Commit a completed feature using repository conventions
  • Prepare a pull request with tests and demos
  • Address automated checks and review feedback after publication

Files included (1)

  • SKILL.md3.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Publish and drive the PR

Commit

Commit the implementation and its tests on the working branch with the repository's conventions, signed off (git commit -s). Stage paths explicitly and check git diff --cached --stat: never commit recordings/ or .omnigent/ files. Read the staged diff for redundant comments. If a commit hook changed tested files, rerun their checks. If the checkout has .github/scripts/pr-template/hygiene.py, run it with --base origin/main.

Choose the publication mode

  • Local-only (skip_push: true): stop after committing. Report the branch in pushed_branch and leave pr_url empty; do not prepare a PR or drive one. The outcome is partially_implemented, with publishing and the PR loop in remaining_work.
  • Workflow-owned (a CI publisher contract is appended to your instructions): do not push or make any gh write. Write and validate .omnigent/pr-body.md (below), write the final handoff, and stop. The workflow publishes the PR and runs the PR loop.
  • Direct (no publisher contract): push the branch, open the PR, then drive it (below).

When .omnigent/pr-gate.json exists, make every PR write (create, edit, comment, review, ready) with the pr.py helper CI supplies, at the path given in the publisher contract. Keep Git pushes on the supplied credential. Never decode, search for, or export another token, and never change credential configuration.

The PR is always ready for review, never a draft, including when a recording is blocked.

PR body

Copy .github/pull_request_template.md to .omnigent/pr-body.md and fill it in, keeping every heading and checkbox row:

  • First lines: Implements <feature_url> and <!-- omnigent-feature-managed -->. Do not use a closing keyword against a Linear URL.
  • Summary: a 1–2 sentence plain-language description of what users can now do, then subsections Design, Alternatives considered, CUJs covered, and CUJs not covered (and why).
  • Test Plan: each covered CUJ with the tests that exercise it, plus the impact-assessment checks, as short bullets.
  • Demo: the recordings for each covered CUJ, labelled by CUJ ID. Upload them as GitHub attachments when your environment can, otherwise link where they live (the CI artifact bundle). For a CUJ with a blocked recording, give the blocker and the manual test steps instead. When a Linear key is available, also attach the recordings to the ticket (GraphQL fileUpload + attachmentCreate).
  • Check Feature, plus UI / frontend change when the UI changes.

Aim for fewer than 800 visible words. If the checkout has .github/scripts/pr-template/validate.py, run it with PR_BODY="$(cat .omnigent/pr-body.md)" and fix every error. Then publish with gh pr create --body-file .omnigent/pr-body.md, or the helper in checked mode.

Drive the PR (direct publication)

Stay on the PR until CI is green and both reviews are settled:

  1. Load the shared otto-drive-pr skill. Follow ci.md to keep the branch mergeable and CI green, and preview.md to label ui-preview. Skip its live-validation prompt and validation_surface steps; the Demo section and the CUJ steps serve that purpose.
  2. Load the shared otto-pr-review-loop skill and run Polly and OCR until every finding is addressed or answered with a reason. Request both again after every push. Run its live gate before claiming implemented.
  3. Refresh otto-impact-assessment after every change in this loop.
  4. Request review from a maintainer: the ticket's assignee or the owners of the main changed files. Never approve or merge.

If a concrete blocker or deadline prevents finishing, leave the PR open and report partially_implemented with the remaining work.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Test Omnigent’s native Antigravity integration with a live local server and the real agy CLI. Verify messages traveling between the web interface and terminal, mirrored replies, permission requests, interruption, session resumption, and process cleanup.

  • Testing message delivery from the web interface to agy
  • Checking terminal output against mirrored session replies
  • Verifying permission requests and interruption
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.

  • Test authentication and real Gemini responses
  • Verify tool connections and sub-agent delegation
  • Investigate model selection failures
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

api-docs

FreeSummary

Create reference documentation directly from source code for public functions, classes, command-line commands, and endpoints. Organize parameters, defaults, return values, errors, and runnable examples, then check that the documentation matches the implementation.

  • Writing reference docs for a public module
  • Documenting command-line arguments and defaults
  • Adding minimal usage examples for an API
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

build-omnigent

FreeSummary

Create an Omnigent agent directory using validated templates for configuration and instructions. Choose how the agent runs, then add web search, shell access, external tool connections, or subagents only when the task requires them.

  • Creating a minimal Omnigent agent
  • Configuring an agent with web search
  • Adding shell access or MCP tool connections
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

changelog

FreeSummary

Turn a selected range of commits or merged pull requests into release notes grouped by change type. Describe user-visible effects, link to supporting changes, and highlight breaking changes so readers can assess an upgrade.

  • Write release notes covering changes since the last tag
  • Summarize pull requests merged during a selected period
  • Highlight breaking changes before an upgrade
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

cli-setup-verify

FreeSummary

Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.

  • Reproducing a first-run setup problem
  • Inspecting menus in a narrow terminal
  • Checking help text and command visibility
omnigent-ai/omnigent10.9KUpdated Oct 18, 2026

See all skills by omnigent-ai

Report a problem with this skill