run-skill-iter-improve SKILL.md skillA
run-skill-iter-improve from daishiman/harness-dev is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daishiman/harness-dev/run-skill-iter-improve@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daishiman/harness-dev
- Path
plugins/harness-creator/skills/run-skill-iter-improve/SKILL.md- Versions recorded
- 6
- Latest version
- v0.1.0, committed Aug 24, 2026
- First version recorded
- Jul 12, 2026
- Size
- 33,587 bytes
- Repository stars
- 10
- License
- none declared
既存skillの品質を実走eval駆動で反復改善したいとき、run-skill-live-trialの受け入れFAILやgoal-proxy乖離を改善に引き継ぐときに、PASS詐欺・context汚染・評価縮退を構造的に防ぐeval帰属改善ループとして起動する。.
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
## Pre-choice usable artifact execution Purpose & Output Contractの最小の実成果物をmain contextで作成する。effect別のparse/open・secret・irreversible・corrupt guardだけを実行し、現物path・digest・開き方を提示してからaccept-as-is/light/standard/detailedを記録する。accept-as-isはその場でhandoff完了とし、後続sectionを実行しない。 ## Post-choice selected improvement execution 以下の既存workflow・goal-seek・評価・修正sectionはlight/standard/detailedが記録されて`semantic_evaluator_started`へ遷移した場合だけ実行する。release/exhaustiveは別の明示eventを必要とする。 # run-skill-iter-improve > **配布注記**: cross-skill refs (`../run-goal-elicit/`, `../run-build-skill/`, `../run-elegant-review/`) は repo-bundled 前提 (単独配布非対応)。本 skill と `run-skill-live-trial` は実行 acceptance 系として**ローカル開発環境限定**であり、量産先 plugin へは配備しない (正本: `../run-build-skill/references/feedback-loop-deployment.md` の配備境界)。CI でも実行しない。 ## Purpose & Output Contract target skill の品質を「current proof の機械再利用判定 → 未解決分だけ fresh-context 並列実走 eval → 弱点 diagnose + PASS 詐欺審問 → skill 層を少数件 Edit → commit → GOAL VERIFICATION」で反復改善する **eval 帰属のメタ改善ループ** (skill が skill を改善する)。 …
Read the whole file at its exact version.
How to install
mdr add daishiman/harness-dev/run-skill-iter-improve@sha256:27d36765f59f1167The line at the top of this page pins the label v0.1.0, 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_lap7uvbjp6bavcvz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 12, 2026 and Aug 24, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-08-24 | b4545d9 | 33,587 B | A | view · diff |
| v0.1.0 | 2026-08-24 | 6e903ca | 32,951 B | A | view · diff |
| v0.1.0 | 2026-08-21 | cf93ab3 | 23,250 B | A | view · diff |
| v0.1.0 | 2026-08-20 | e94df0f | 22,549 B | A | view · diff |
| v0.1.0 | 2026-08-20 | 41f52c2 | 21,525 B | A | view · diff |
| v0.1.0 | 2026-07-12 | 4cd8faf | 20,824 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 (33587 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
daishiman/harness-dev · 10 stars · license none declared · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lap7uvbjp6bavcvz GET https://markdownregistry.com/api/v1/resolve?ref=daishiman/harness-dev/run-skill-iter-improve GET https://markdownregistry.com/api/v1/blob/27d36765f59f11677498a4978a3c39e0627152314014eb7f301ed22587da930e
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.