aide-unified-diff-repair SKILL.md skillA
aide-unified-diff-repair from anonymousnomad/aide-sovereign-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add anonymousnomad/aide-sovereign-workbench/aide-unified-diff-repair@git:20260823.df7cbdePins git:20260823.df7cbde in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/aide-unified-diff-repair/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260823.df7cbde, committed Aug 23, 2026
- Size
- 7,359 bytes
- Repository stars
- 53
- License
- Apache-2.0
SOP for fixing the README scorecard blocker — bundled models pass function/planning smoke tests but FAIL strict unified-diff formatting. Covers the two-sided fix (harness-side tolerance+repair loop in the agent-loop parser, and model-side data/training fix via format-targeted post-training), decision rules for which side to fix, and the verification battery that proves the scorecard claim changes honestly. Use when working on diff/SEARCH-REPLACE parsing, when smoke tests fail on formatting…
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
# Unified Diff Repair — making strict formatting pass HONESTLY ## Verified problem statement README/model scorecard (as of 2026-08-24): all three bundled models PASS function-call and planning smoke tests, FAIL strict unified-diff formatting. The agent loop already tolerates CRLF + loose-indent + multi-block SEARCH/REPLACE (tests/unit/test-a1-agent.mjs covers exact/CRLF/loose-indent/two-blocks/NO_MATCH-quality) — so failures are about models emitting malformed or non-canonical blocks under strict-mode evals, not total incapacity. Two root causes possible per model: (a) format knowledge gap → data/training fix; (b) format drift under long context → harness reminder fix. ## Research base 1. Project doctrine already in place: RESEARCH_LOG.md "Unified Diff Reliability" entry (2026-08-12); docs/evidence/dap-wire-sequence.json unrelated; a1 parser tests = current tolerance surface; multi-format-retention-repair skill governs fixing one format WITHOUT regressing others; post-training-closed-loop skill governs eval→regenerate→retrain cycle; pipeline-phase-9 no-vacuous-pass laws apply to any "fixed" claim. …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/aide-unified-diff-repair@sha256:28d3f1c267572ea6The line at the top of this page pins the label git:20260823.df7cbde, 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_yrzwz7q3bp2a2vs4)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 23, 2026.
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 (7359 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
anonymousnomad/aide-sovereign-workbench · 53 stars · license Apache-2.0 · pushed 2026-10-26 · branch covert-production
API
GET https://markdownregistry.com/api/v1/artifacts/art_yrzwz7q3bp2a2vs4 GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/aide-unified-diff-repair GET https://markdownregistry.com/api/v1/blob/28d3f1c267572ea67a3f3fee11a39709561e17883856b9ba7ae06b012207fa86
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.