ai-diff-reviewer-address-review SKILL.md skillA
ai-diff-reviewer-address-review from dailybothq/deepworkplan-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dailybothq/deepworkplan-skill/ai-diff-reviewer-address-review@v3.3.15Pins v3.3.15 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dailybothq/deepworkplan-skill
- Path
.agents/skills/ai-diff-reviewer/address-review/SKILL.md- Versions recorded
- 12
- Latest version
- v3.3.15, committed Oct 14, 2026
- First version recorded
- Sep 25, 2026
- Size
- 26,124 bytes
- Repository stars
- 23
- License
- MIT
Close the review loop in one invocation — a bare invocation on a fresh context is fully specified — it targets the current branch's open PR. Surveys ALL the PR's CI health (every workflow and check — failing checks diagnosed from logs and fixed, a behind branch updated, at most one flake re-run), checks whether the AI Diff Reviewer run covered the current head — and when it never ran because the trigger label is missing, arms it — adding the label is the loop's first move, not an error. Walks…
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
# AI Diff Reviewer — Address Review (sub-skill) The one-invocation loop for the most repeated instruction after a CI round: *"revisa los comentarios del reviewer en el PR, resuélvelos y luego haz toggle del ready label."* The reviewer's comments are only half of a PR's health, so the loop is **green-CI aware**: every OTHER workflow the PR runs — the codecheck that runs tests, linters and typecheck; build jobs; the branch-protection rule that requires the branch to be up to date with its base — is surveyed too, and a red one is diagnosed from its logs and fixed in the same consented pass, before the reviewer is re-armed. This sub-skill is that whole sentence, executable — and **repo-adaptive**: it discovers how THIS repository triggers its reviewer (label gate or push trigger) and re-arms it the right way instead of guessing. Relationship to the family: - [`apply-review`](../apply-review/SKILL.md) **reads** a CI review and walks findings with a no-commit / no-push boundary (each apply is a working-tree edit needing a per-finding yes). - This sub-skill **closes the loop**: same finding-loading rules (v3 …
Read the whole file at its exact version.
How to install
mdr add dailybothq/deepworkplan-skill/ai-diff-reviewer-address-review@sha256:7443b396b01c552fThe line at the top of this page pins the label v3.3.15, 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_ejipkpmyte6zvvj2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Sep 25, 2026 and Oct 14, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v3.3.15 latest | 2026-10-14 | e516dd0 | 26,124 B | A | view · diff |
| v3.3.14 | 2026-10-13 | 3782159 | 26,124 B | A | view · diff |
| v3.3.13 | 2026-10-13 | 11900fa | 26,124 B | A | view · diff |
| v3.3.12 | 2026-10-12 | 3148863 | 26,124 B | A | view · diff |
| v3.3.11 | 2026-10-12 | 501db55 | 26,124 B | A | view · diff |
| v3.3.3 | 2026-10-11 | 48f1cb4 | 26,123 B | A | view · diff |
| v3.3.2 | 2026-10-11 | 83bbaed | 26,123 B | A | view · diff |
| v3.3.1 | 2026-10-11 | 6a32489 | 26,123 B | A | view · diff |
| v3.3.0 | 2026-10-09 | 4404c27 | 26,123 B | A | view · diff |
| v3.2.3 | 2026-10-06 | 16eb123 | 26,123 B | A | view · diff |
| v3.2.2 | 2026-09-28 | 8e0d994 | 26,123 B | A | view · diff |
| v3.1.1 | 2026-09-25 | 6bd2522 | 10,768 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 (26124 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
dailybothq/deepworkplan-skill · 23 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ejipkpmyte6zvvj2 GET https://markdownregistry.com/api/v1/resolve?ref=dailybothq/deepworkplan-skill/ai-diff-reviewer-address-review GET https://markdownregistry.com/api/v1/blob/7443b396b01c552f9ba7d3f1a4fc14e96cb79ab85b24a9c27757fcae748d1eb7
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.