review-loop SKILL.md skillA
review-loop from parcha-ai/parcha-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add parcha-ai/parcha-skills/review-loop@git:20261003.22b7ecfPins git:20261003.22b7ecf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- parcha-ai/parcha-skills
- Path
review-loop/skills/review-loop/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261003.22b7ecf, committed Oct 3, 2026
- First version recorded
- Sep 15, 2026
- Size
- 11,783 bytes
- Repository stars
- 65
- License
- MIT
Drive every reviewer thread on a GitHub pull request to zero unresolved, iterating until the exit criterion is met. Covers bot reviewers such as Greptile and Devin and human reviewers. Fetches every inline comment, review, and issue comment, fixes what is actionable, replies, resolves bot threads through GraphQL, re-requests review once per push, and ends with a fixed-format report. Use when the user says "review loop", "address the review comments", "get this PR to zero unresolved…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Review loop This skill has one job: take a GitHub PR with open review threads and drive every thread, from every reviewer, to zero unresolved, iterating until the target is met, then report what it did in a fixed format. It does not QA the running application; that is `autoqa`'s job. It does not decide whether the diff is safe beyond what reviewers raised; that is `blast-radius`'s job. It does not merge, and it does not mint credentials. ## Inputs | Input | Required | Default | |---|---|---| | Repository (`owner/repo`) | no | The `origin` remote of the current checkout | | PR number | no | The PR for the current branch (`gh pr view`) | | Target (`open-for-review`, `review-clean`, or `merge-ready`) | no | `review-clean` | | Trigger comment text | no | `@greptile-apps review` | | `--max-iterations N` | no | None (no cap). Set only when the caller wants a hard stop | | Gate command | no | None. The caller or the repository supplies the command that runs tests and lint (for example the repo's `make check`); the skill only says where in the loop it runs | | Base-branch sync | no | None. The caller or repository supplies the rebase or merge policy; the skill says where it runs | …
Read the whole file at its exact version.
How to install
mdr add parcha-ai/parcha-skills/review-loop@sha256:313bb9fbc5dce0e1The line at the top of this page pins the label git:20261003.22b7ecf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2emjrzgkmjqzwn3b)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 15, 2026 and Oct 3, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.22b7ecf latest | 2026-10-03 | 22b7ecf | 11,783 B | A | view · diff |
| git:20260927.79c5082 | 2026-09-27 | 79c5082 | 11,181 B | A | view · diff |
| git:20260927.0a701f0 | 2026-09-27 | 0a701f0 | 11,069 B | A | view · diff |
| git:20260915.b0f7211 | 2026-09-15 | b0f7211 | 10,276 B | A | view · diff |
| git:20260915.c1df904 | 2026-09-15 | c1df904 | 9,698 B | A | view · diff |
| git:20260915.b301182 | 2026-09-15 | b301182 | 9,631 B | A | view · diff |
| git:20260915.032c2e8 | 2026-09-15 | 032c2e8 | 8,147 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11783 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
parcha-ai/parcha-skills · 65 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2emjrzgkmjqzwn3b GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/parcha-skills/review-loop GET https://markdownregistry.com/api/v1/blob/313bb9fbc5dce0e1d1b406a2d6ee5ee07021935958ed1e8f899661b84a50a6e0
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from parcha-ai/parcha-skills
Every file in parcha-ai/parcha-skills