Skip to content
Skills Library
Programming · Automation

fix-pr

/fix-pr

Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports.

Licence
MIT
Last repository change
19.10.2026

Assessment and security

96/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content31 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 19.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports.

Original author description

Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports.

How it works

SKILL.md has no level-two headings · 41 lines, 271 words

SKILL.md preview
---
name: fix-pr
description: Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports.
metadata:
  category: workflows
---

# fix-pr

Thin launcher. The canonical workflow — phases, roles, consent gates, verification
gates, artifact contracts — lives in [references/workflow.md](references/workflow.md).
Read it completely before acting and follow it exactly; this file only adapts it to this
surface. Do not redefine flags, phases, ownership, or gates here.

Treat the text after `$fix-pr` as the raw workflow arguments:

```text
$fix-pr [PR_NUMBER_OR_SEARCH] [--local] [--resume] [--full-validation]
```

Hard rules restated from the canonical workflow (they cannot be skipped on any surface):

- Determine the PR first, then ask about push/post mode unless `--local` is set.
- No edit before the user-approved fix plan file exists; fix only what it lists.
- Never push while a verification gate is red.
- Never read full review reports into the main context; use the short handoff files.

Surface adapters:

- **Claude Code**: also read
  [references/claude-launcher.md](references/claude-launcher.md) — it maps canonical
  roles to this plugin's agent types and the workflow's abstract operations to Claude
  Code mechanics.
- **Codex**: use the delegation mapping below.

Delegation mapping (when subagent use is available and authorized):

- Map every role in the canonical Roles table to a `worker` when it edits files or
  writes reports, or an `explorer` for read-only codebase questions.
- Pass concrete `RUN_ROOT`, `WORKTREE_ID`, and `PREFIX` values and the role's task spec
  from the canonical workflow to every subagent; name the role's skills explicitly in
  the subagent prompt.
- Respect the canonical ownership table — no worker edits outside its assigned files;
  only the fix-pusher role commits or pushes.
- If subagents are unavailable or not authorized, execute the roles directly in phase
  order, preserving the same handoff files and gates.
Files in this package (3)
  • SKILL.md 2 KB
  • references/claude-launcher.md 3 KB
  • references/workflow.md 19 KB

Versions

RepositoryScoreLicence
This page · PolicyEngine/policyengine-claude96MIT
codagent-ai/agent-skills100MIT
sgomez/developer-skills100AGPL-3.0
Weaverse/.agents96MIT
griffinwork40/agent-framework90Apache-2.0
heyAyushh/stacc90MIT
prathamdby/skills85MIT

Database snapshot: 13.11.2026 · package version 23047d8b6b31 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 96review-program
    ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.
  • 100fix-review
    When the user asks to fix, address, or work on PR review comments — fetch review comments from a GitHub pull request and apply fixes to the local codebase. Requires gh CLI.
  • 96encode-policy-v2
    Use when the user invokes $encode-policy-v2 or asks Codex or Claude Code to implement a new PolicyEngine-US state benefit program or a new structural program component from official rules. Covers existing-program routing, source collection and selective PDF inspection,…
  • 100autofix
    Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings, PR feedback, and code review issues with validation evidence. Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback.
  • 100pr-fix
    Apply fixes for findings in an existing `pr-review` report (`report-<source>-<target>.md`). Verifies each finding against the current code, proposes one concrete fix at a time, and edits code only after the user explicitly approves that specific fix. Use this skill when the user…
  • 100fix-pr-review
    Use when the user asks to fix PR review feedback, address Claude Code Action review comments, resolve unresolved review threads, handle inline review suggestions, or work through review issues tagged CRITICAL/HIGH/MEDIUM/LOW on the current PR. Covers both GraphQL review threads…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.