Skip to content

oprogramadorreal/optimus-claude / skills/pr

Creates or updates a pull request (GitHub) or merge request (GitLab) for the current branch in the Conventional PR format — intent, summary, changes, rationale, and test plan. Pushes the branch if needed (asks before any force-push) and captures the implementation conversation's intent into the PR description. Use when a feature branch is ready for review or to refresh an existing PR/MR description.

FileKindSize
README.mdmarkdown3.9 KB
SKILL.mdskill md10.7 KB
agents/openai.yamlconfig198 B
references/default-branch-detection.mdmarkdown709 B
references/platform-detection.mdmarkdown1.5 KB
references/pr-template.mdmarkdown2.6 KB

references/pr-template.md

View on GitHub
# Conventional PR Format

A structured PR/MR body format inspired by [Conventional Commits](https://www.conventionalcommits.org/), with a top-of-body `## Intent` section.

## Title

Conventional Commit format: `type(scope): description` — imperative mood, lowercase, no period. Example: `feat(auth): add password reset endpoint`.

## Body Sections (in order)

### `## Intent` (optional — only when intent context is available)

Author intent captured from the implementation conversation (or preserved from the existing PR body during an update). This is the primary anchor `/optimus:code-review` reads to check whether the implementation delivers what was supposed to be built.

Omit the section entirely (no stub, no placeholder) when no intent context exists. **Never invent intent from commit messages or the diff alone** — a fabricated Intent produces false intent-vs-implementation findings downstream.

Sub-fields (each optional — include only the ones the source actually answers):

- **Problem** — what was broken, missing, or worth changing (the motivation, not the diff).
- **Scope** — what this PR delivers.
- **Non-goals** — what was intentionally excluded.
- **Key decisions** — trade-offs accepted, alternatives considered and rejected.

Example:

```
## Intent

- **Problem:** Password reset endpoint was missing; locked-out users had no self-service path.
- **Scope:** New POST /auth/reset-password endpoint with email-link flow; rate-limited to 3 requests/hour per email.
- **Non-goals:** Multi-factor reset (next sprint); SMS-based reset.
- **Key decisions:** Time-limited token in URL rather than session cookie (stateless reset); 30-min expiry chosen over 24h to limit the attack window.
```

**Detection rule.** An existing body has an Intent section when a line outside fenced code blocks and blockquotes matches:

```regex
^##[ \t]+[Ii]ntent[ \t]*(?:\{[^}]*\}|[^\w\s]+)?[ \t]*$
```

That accepts `## Intent`, `## Intent:`, and a trailing anchor such as `## Intent {#intent}`; it rejects `## Intentional rollback`, `## Intents`, `## Intent and scope`, `###`-level headings, and any `## Intent` that is indented or quoted.

### `## Summary`

2–4 sentences: what the PR does and why. The diff shows the how.

### `## Changes`

Bulleted list of changed files (or cohesive groups), each with a brief description of what the change accomplishes.

### `## Rationale` (optional)

Key design decisions and trade-offs. **Omit the section entirely** when the changes are straightforward and the Summary already covers the reasoning.

### `## Test plan`

Checklist (`- [ ]`) of verification steps: automated test commands, manual checks, edge cases.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall