Source profileQuality 91/100

btspoony/mstar-harness/skills/mstar-skill-authoring/SKILL.md

mstar-skill-authoring

Use it for testing and engineering tasks; the detail page covers purpose, installation, and practical steps.

Source repository stars
56
Declared platforms
0
Static risk flags
0
Last source update
2026-08-28
Source checked
2026-08-28

Decision brief

What it does: where it fits

本 skill 约束如何编写、审查与验证 任意 agent skill(SKILL.md)。面向 skill 工作,不是普通应用实现。

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/btspoony/mstar-harness --skill "skills/mstar-skill-authoring"
    Safe inspection promptEditorial

    Inspect the Agent Skill "mstar-skill-authoring" from https://github.com/btspoony/mstar-harness/blob/f1b60df0b3b2e29b9a904edb4077e52cf6d7ca66/skills/mstar-skill-authoring/SKILL.md at commit f1b60df0b3b2e29b9a904edb4077e52cf6d7ca66. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      Workflow

      主链:按「Frontmatter Contract」先定触发契约(原则 3)→ 按「Body 必须回答的 5 问」写默认紧凑 body(原则 2)→ 变体细节按「Progressive Disclosure」进 references/ / templates/ / scripts/ → 行为塑形改动按「验证门控(Evidence,原则 4 + 6)」留 paired 证据 → 按「Review Template」自审并完成「完成时主动说明」三问。

      主链:按「Frontmatter Contract」先定触发契约(原则 3)→ 按「Body 必须回答的 5 问」写默认紧凑 body(原则 2)→ 变体细节按「Progressive Disclosure」进 references/ / templates/ / scripts/ → 行为塑形改动按「验证门控(Evidence,原则 4 + 6)」留 paired 证据 → 按「Review Template」自审并完成「完成时主动…
    2. 02

      Review Template

      Review the “Review Template” section in the pinned source before continuing.

      Review and apply the “Review Template” source section.
    3. 03

      Skill Review

      Trigger contract:

      Trigger contract:5 questions covered:Principles 2/5 compactness:
    4. 04

      Load Order

      在本 harness 仓库内工作时:先 Read mstar-harness-core(加载 / 冲突裁决);仓库维护另遵根目录 AGENTS.md。

      在本 harness 仓库内工作时:先 Read mstar-harness-core(加载 / 冲突裁决);仓库维护另遵根目录 AGENTS.md。在其它仓库 / 宿主上使用本 skill 时:按当地入口文档加载;本文件的原则与门控仍然适用。改现有 skill 时:读完被改 skill 及其 SSOT 引用;禁止仅为文风重写相邻 skill。

    Permission review

    Static risk signals and limitations

    No configured static risk pattern was detected

    This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score91/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars56SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    btspoony/mstar-harness
    Skill path
    skills/mstar-skill-authoring/SKILL.md
    Commit
    f1b60df0b3b2e29b9a904edb4077e52cf6d7ca66
    License
    MIT
    Collected
    2026-08-28
    Default branch
    main
    View the original SKILL.md

    Skill Authoring

    本 skill 约束如何编写、审查与验证 任意 agent skill(SKILL.md)。面向 skill 工作,不是普通应用实现。

    Load Order

    在本 harness 仓库内工作时:先 Read mstar-harness-core(加载 / 冲突裁决);仓库维护另遵根目录 AGENTS.md

    在其它仓库 / 宿主上使用本 skill 时:按当地入口文档加载;本文件的原则与门控仍然适用。

    改现有 skill 时:读完被改 skill 及其 SSOT 引用;禁止仅为文风重写相邻 skill。

    详细 writer 流程与输出模板 → references/skillsbench-authoring.md(需要完整循环时再读)。

    Workflow

    主链:按「Frontmatter Contract」先定触发契约(原则 3)→ 按「Body 必须回答的 5 问」写默认紧凑 body(原则 2)→ 变体细节按「Progressive Disclosure」进 references/ / templates/ / scripts/ → 行为塑形改动按「验证门控(Evidence,原则 4 + 6)」留 paired 证据 → 按「Review Template」自审并完成「完成时主动说明」三问。

    6 条作者原则(Decision Rules,必须遵守)

    来源:SkillsBench 大规模实验。违反任一都会降低 agent 性能。

    #原则强制动作
    1专家流程优先先提取真实操作步骤、决策标准、约束、API 坑与失败恢复;模型只做编辑器。禁止把一键生成稿当最终版。
    2紧凑程序性body 只答 5 问(见下);详例 / 长文档进 references/,按需加载。过长 body 几乎无提升甚至负提升。
    3路由最小化任务真正需要时才加载;目标 1–3 个 skill。description 必须具体到可精准匹配,避免无关激活。
    4按 model+harness 实测文件可移植 ≠ 行为可移植。在实际使用的模型与宿主(omp / Cursor / Codex / Claude Code 等)分别验证触发、执行、token、回归。
    5只补模型缺口编码内部约定、受监管流程、脆弱 API、专业判断、反复失败模式。不写模型已会的通用知识。
    6每次改动=受控实验必须有 paired 证据(with vs without,或 before/after + 可观察标准)。held-out / 压力场景未提升则拒绝合入。禁止“感觉更好”。

    Body 必须回答的 5 问

    合格 SKILL.md 清晰回答:

    1. 何时加载?(触发 / 排除)
    2. 按什么顺序与关键决策点执行?
    3. 哪些约束 / 不变量绝不可违反?
    4. 正确结果长什么样?(成功标准 / 证据)
    5. 主路径不够时打开哪些额外资源?

    答不进这 5 问的内容 → 删或移到 references/

    运行时别名(runtime alias map)

    已发布的 mstar-* 专题 skill 允许运行时模式lintFiveQuestion(body, "runtime"))用锁定别名表回答同一问题(引擎常量 RUNTIME_HEADING_ALIASES):

    问题运行时别名(标题子串,大小写不敏感)
    Workflowprocessplaybook
    Decision Ruleshard rulescore rulesrulegatenot to dored flags反模式红线规则门禁
    Evidenceoutput format证据
    Referencesdependencies关系
    • 别名表是锁定表:改表必须同步引擎回归测试与 corpus。
    • 新写 / greenfield skill(authoring / strict)仍要求 canonical 标题;运行时别名只豁免已发布专题 skill 的机械 lint,不豁免语义——别名标题必须真实回答对应问题,正文不得因别名而缩水。

    Skill Purpose Test

    仅当全部成立才新建 / 扩写 skill:

    1. 行为应跨多项目、角色或任务复用。
    2. 需要判断或排序,且不宜用代码强制。
    3. 现有 skill 树尚未拥有同一规则(避免副本)。
    4. 触发条件可写清,agent 知道何时读取。

    不要为这些建 skill:一次性项目约定(放项目 AGENTS.md / 等价处)、可 lint/脚本化的机械规则、无复用手法的事故叙述、已有 skill 规则的副本。

    Frontmatter Contract

    ---
    name: example-skill
    description: Use when...
    ---
    
    • name:稳定、小写、连字符。
    • description触发契约,不是流程摘要。写清症状、上下文、角色、产物与排除条件。
    • 第三人称;足够具体以避免无关加载(原则 3)。
    • 禁止在 description 里总结整条 workflow(否则 agent 可能只跟摘要、跳过 body)。

    Bad:Explains how to write plans with steps, tests, commits, and review gates.
    Better:Use when a non-trivial task has a spec or requirements and needs a written implementation plan before code changes.

    Engine check (when available): run mstar skill lint <skill-dir> (or import { lintFrontmatter, lintFiveQuestion } from "@mstar-harness/engine" in a host hook) to lint the frontmatter contract and the five-question body contract above. On fail -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.

    默认 Body 结构

    # Skill Title
    
    ## Load Order
    ## Scope
    ## Workflow
    ## Decision Rules
    ## Evidence
    ## References
    

    Keep SKILL.md focused on the main execution path. Move long examples, templates, schemas, and detailed variants into references/, templates/, or scripts/.

    Skill-relative script and asset paths

    When a skill ships executables or assets under scripts/ / templates/ / references/, name them as skill → relative path

    • Good: skill my-skillscripts/do-thing
    • Good: <my-skill>/scripts/do-thing(已加载 skill 根的占位写法)
    • Bad:把 skills/my-skill/scripts/do-thing 写成消费仓库 cwd 下的字面路径

    Agents 按 skill 名 发现 skill;文档若给出完整仓内相对路径,agent 常在应用仓库 cwd 下按字面搜索而找不到。先解析已加载 skill 根目录,再拼 scripts/… / references/…

    在本 harness:解析方式见 mstar-host § Resolve loaded skill root(omp skill://、各宿主插件挂载等)。其它环境按当地 skill 安装约定解析。

    Engine check (when available): import resolveAssetPath from @mstar-harness/engine in a host hook to resolve a skill-relative asset per the convention above (no CLI form yet). On fail -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.

    Progressive Disclosure

    1. Frontmatter:仅触发
    2. SKILL.md:主执行路径
    3. references/ / templates/ / scripts/:变体细节,按需加载

    多宿主 / 多域细节按文件拆分,并在 body 写明「何时打开哪份」。

    验证门控(Evidence,原则 4 + 6)

    行为塑形改动必须留下证据,任选可观测形式:

    • 2–3 个压力 prompt(无 skill 易失败;有 skill 应通过)
    • before/after 期望 + 触发短语 + 一次具体校验(检索、链接、dry-run)
    • 记录失败原因、token / 延迟回归;未提升则回滚文案

    压力场景骨架:

    {
      "skill_name": "example-skill",
      "evals": [
        {
          "id": 1,
          "prompt": "会诱使 agent 违反目标规则的真实任务",
          "expected_output": "合规行为长什么样",
          "files": []
        }
      ]
    }
    

    完成时主动说明

    写完 / 大改 skill 后必须交代:

    1. 删了 / 压了什么,以及如何满足原则 2 与 5
    2. 如何验证原则 6(paired 证据或压力场景)
    3. 触发契约是否仍足够窄(原则 3)

    Review Template

    ## Skill Review
    - Trigger contract:
    - 5 questions covered:
    - Principles 2/5 compactness:
    - SSOT alignment:
    - Progressive disclosure:
    - Evidence for behavior change (P6):
    - Stale references checked:
    - Verdict: Approve | Request Changes | Needs Discussion | Unconfirmed
    - Unconfirmed: paired evidence (P6) cannot be established or verified
    

    References

    何时打开
    需要完整 skill-writer 流程、原则细则、输出模板references/skillsbench-authoring.md
    需要把「真实产物」固化为可重跑断言(P6 重武器选项)references/regression-fixation.md

    Frequently asked questions

    What to verify before installation and use

    What does the mstar-skill-authoring source document cover?

    本 skill 约束如何编写、审查与验证 任意 agent skill(SKILL.md)。面向 skill 工作,不是普通应用实现。

    How do I install mstar-skill-authoring?

    The source record exposes this install command: npx skills add https://github.com/btspoony/mstar-harness --skill "skills/mstar-skill-authoring". Inspect the command and pinned source before running it.

    Alternatives

    Compare before choosing

    Computed 10029,236

    garrytan/gbrain

    bulk-ingestion

    End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see MANIFEST-PATTERN.md) so any crash, session boundary, or subagent fan-out resumes from ground truth instead of memory.

    Computed 10025,136

    alirezarezvani/claude-skills

    app-store-optimization

    App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist

    Computed 1005,277

    dotnet/skills

    migrate-vstest-to-mtp

    Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", set OutputType=Exe only for test projects in Directory.Build.props, or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. USE FOR: MTP behavioral differences vs VSTest (exit code 8, zero tests discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE); centralizing

    Computed 991,260

    vipshop/cache-dit

    cache-dit-model-integration

    High-level guide for integrating a new DiT model into cache-dit: Cache (BlockAdapter/ForwardPattern), Context Parallelism, Tensor Parallelism, Text Encoder Parallelism (TE-P), VAE Parallelism (VAE-P), generate CLI, installation, testing workflow, and detailed references. Use when adding support for a new diffusion transformer model in cache-dit.