assign-prompt-design-evaluator SKILL.md skillA
assign-prompt-design-evaluator 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/assign-prompt-design-evaluator@v2.1.0Pins v2.1.0 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/prompt-creator/skills/assign-prompt-design-evaluator/SKILL.md- Versions recorded
- 1
- Latest version
- v2.1.0, committed Jul 12, 2026
- Size
- 6,708 bytes
- Repository stars
- 10
- License
- none declared
生成済みプロンプトを C1-C4 と 4 パスで評価したいとき、context:fork で独立評価結果 findings.json を取得したいときに使う。.
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
# assign-prompt-design-evaluator > 生成プロンプトを **C1-C4 + 4 パス** で評価し `findings.json` を返す independent evaluator。`context:fork` で起動して Sycophancy を防ぐ。 ## Purpose & Output Contract **入力**: prompt_path (評価対象 .md/.yaml) / brief (eval-log/prompt-brief.json) / output (省略時 `eval-log/docs/<NN>-<timestamp>.json`) **出力**: `eval-log/docs/<NN>-<timestamp>.json` (`../run-prompt-create/schemas/findings.schema.json` 準拠) **完了条件**: C1-C4 verdict 全付与 + findings[] に高/中/低の severity 配列。 ## C1-C4 評価軸 | Gate | 観点 | 合格条件 | |---|---|---| | **C1** | Layer 整合 | L1-L7 が seven-layer-format.md と整合、Layer 番号と役割の対応が崩れていない | | **C2** | 依存方向 | L7→L1 の単方向参照のみ。Layer N が Layer N-1 以外を参照していない | | **C3** | 再現性 | reproducible=true。再現性根拠 (output_schema / script_refs / 検証可能な完了チェックリスト) が揃い、5.2 ゴール定義が成果状態で固定手順列挙を含まない (l5-contract v2.0.0) | | **C4** | Self-Evaluation 充足 | L5.3 完了チェックリスト (停止条件) が非空で、全項目が第三者に YES/NO 判定可能 (数量レンジは l5-contract v2.0.0 で廃止) | ## 4 パスレビュー (Pass 0-4) `../run-prompt-creator-7layer/references/quality-criteria.md` §7 由来: - **Pass 0** 動的評価基準生成: `evaluation_priorities` から重み付けし以下 Pass を調整 - **Pass 1** 網羅性: 必須フィールド漏れがないか - **Pass 2** 整合性: Layer 間/メタ/responsibility_id が矛盾しないか …
Read the whole file at its exact version.
How to install
mdr add daishiman/harness-dev/assign-prompt-design-evaluator@sha256:c3a6c002021c0390The line at the top of this page pins the label v2.1.0, 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_hwa6g3c62ov3fhs4)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 12, 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 (6708 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_hwa6g3c62ov3fhs4 GET https://markdownregistry.com/api/v1/resolve?ref=daishiman/harness-dev/assign-prompt-design-evaluator GET https://markdownregistry.com/api/v1/blob/c3a6c002021c039035fb77541b4157e529095830166b5f340d997856c1d59b12
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.