skill-review SKILL.md skillA

skill-review from pillumina/ascend-sleuth is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pillumina/ascend-sleuth/skill-review@git:20261030.0194eb5

Pins git:20261030.0194eb5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pillumina/ascend-sleuth
Path
skills/skill-review/SKILL.md
Versions recorded
5
Latest version
git:20261030.0194eb5, committed Oct 30, 2026
First version recorded
Sep 10, 2026
Size
10,483 bytes
Repository stars
5
License
MIT

对一个 skill(默认 diagnose)做**质量与体验**审视:静态审计 / 扰动实验 / 盲辨与走查 / 坏路径体验 / 注意力预算 五个视角,产出评审报告(落 proposals/reviews/)与可选改进建议。 **不做 CI 硬门**——体验是判断性规范,硬门化等于假硬化。用户显式要求"审视某个 skill 的 质量/体验""诊断用起来是不是很机械/哪里别扭"时使用。.

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

# Skill Review(质量与体验审视)

> **定位**:`eval/` 管**正确性**(golden / S2:答对了没有)与**交互回归**(ixn:该问的问了没有);
> 本 skill 管**质量与体验**——机械感、摩擦、坏路径、注意力预算。三者互补,不替代。
> 产出是**建议**,不是闸门。参数自包含,不依赖 `docs/` 也能执行。

## 何时用

> **不由内容流程自动触发**:issue-ingest / to-postmortem / to-reference / knowledge-groom 的收尾走的是
> `/skill:evolve-check`(轻量,无信号即止);`evolve-check` 的 T8 只**累积**体验信号、不跑本协议。
> 本协议只有三条触发路径:**用户显式要求** / **`self-evolve` 深度轮按目标转接** / **大改某个 skill 之后**(建议,非强制)。
> 且它是 `disable-model-invocation: true`——agent 不会自发拉起。

- 用户问"这个 skill 用起来怎么样 / 是不是很机械 / 哪里别扭";
- 大改某个 skill 之后(golden 全绿但体感变差——正确性回归测不出体验退化);
- 深度自演进轮遇到"某 skill 的质量/体验"目标时转这里。

## 不做什么(边界,先读)

- **不进 CI**:体验是判断性规范,机器判不了(可机械检查 + 确定性后果 + 反复复发三条都不满足)。
  把它做成硬门 = 假硬化,比没有检查更坏——它制造虚假的安全感。强度如实标注为"判断"。
- **不替代 golden / S2 / ixn**:那三个管正确性与交互**回归**;本 skill 的结论不推翻它们,也不被它们替代。
- **不作为验收证据**:pilot 级样本(每格 1–3 次)只作方向性判据,报告必须写清样本量。
- **不自动改 skill**:发现该改的,用 `python3 scripts/evolve_intake.py record …` 落记录(按部署声明落卡或台账),走既有流程(建议与决定分离)。
- **不给自己开后门**:本协议自身的改动与其他 skill 同等(走 methodology PR + 双签,不因"它是评审者"而降级),
  且每轮审视的**首个动作**是先用**档 0 审自己**——本文件的篇幅/强制词/预算档是否还成立。

## 预算分档(先选档,再动手——**别默认跑全套**)

| 档 | 花什么 | 跑哪些 | 什么时候值得 |
|---|---|---|---|
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pillumina/ascend-sleuth/skill-review@sha256:77eafc062bab6a40

The line at the top of this page pins the label git:20261030.0194eb5, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_enj6bzu3atcxplp3.svg)](https://markdownregistry.com/a/art_enj6bzu3atcxplp3)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 10, 2026 and Oct 30, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20261030.0194eb5 latest2026-10-30 0194eb5 10,483 BA view · diff
git:20260913.0e975d52026-09-13 0e975d5 10,369 BA view · diff
git:20260910.5a23bfd2026-09-10 5a23bfd 10,317 BA view · diff
git:20260910.c41340d2026-09-10 c41340d 10,042 BA view · diff
git:20260910.d634f392026-09-10 d634f39 8,204 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10483 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

GitHub

pillumina/ascend-sleuth · 5 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_enj6bzu3atcxplp3
GET https://markdownregistry.com/api/v1/resolve?ref=pillumina/ascend-sleuth/skill-review
GET https://markdownregistry.com/api/v1/blob/77eafc062bab6a40067505febd3157f38f36acf292c4b4d257cca09dfbe532a8

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.

More from pillumina/ascend-sleuth

AGENTS.md AGENTS.md file
pillumina/ascend-sleuth · AGENTS.md
git:20261102.0c3a557 · audit A · 5 stars
CLAUDE.md CLAUDE.md file
pillumina/ascend-sleuth · CLAUDE.md
git:20261102.0c3a557 · audit A · 5 stars
DESIGN.md@dsh-plugins/dsh-sleuth-copilot DESIGN.md file
pillumina/ascend-sleuth · dsh-plugins/dsh-sleuth-copilot/DESIGN.md
git:20261105.43c4f37 · audit A · 5 stars
ask SKILL.md skill
pillumina/ascend-sleuth · skills/ask/SKILL.md · 昇腾知识库快问快答:用户问一个能一句话问完的问题(错误码或环境变量取值、某类问题怎么定位、 本次现象先查什么、某个术语是什么、库里有没有收录)时,用单个索引文件定位,读不超过 2 个词条, 按固定 5 行格式答「一句话 + 表或候选 +…
git:20261030.a103b40 · audit A · 5 stars
diagnose SKILL.md skill
pillumina/ascend-sleuth · skills/diagnose/SKILL.md · 昇腾训练/推理问题的核心诊断循环:收集症状、按 triage-tree 路由、两阶段加载 并验证 Tier 2 case、命中给 fix(高危 root cause 改提示 halt)或转深度排查。 Tier-2…
git:20261104.0a4ba96 · audit A · 5 stars
doc-standards SKILL.md skill
pillumina/ascend-sleuth · skills/doc-standards/SKILL.md · 写或改任何给人读的文档之前,先定类型、再套骨架、最后过反例清单。覆盖 docs/ 六层、 README、定位报告、case/reference 词条、EV 卡、postmortem、PR body、skill 正文。给出九类…
git:20261009.3640a77 · audit A · 5 stars
doctor SKILL.md skill
pillumina/ascend-sleuth · skills/doctor/SKILL.md · 本机环境体检:一条命令问清这台机器上哪些流程能跑、哪些会降级(缺 Python 包、git、node、gh, traces/ 能否解析,知识库索引在不在),并给出每项缺失的修法。任务开始前环境可疑、换机器、 内网新部署、或流程中途以一句…
git:20261027.748c4a1 · audit A · 5 stars
evolve-check SKILL.md skill
pillumina/ascend-sleuth · skills/evolve-check/SKILL.md · 任何内容流程收尾的伴随演进评估(数据驱动的 self-evolving,非独立目标轮)。 用户下内容目标(补 case / reference 沉淀 / 诊断 / 拉取 / replay)后,执行中产生…
git:20261030.875bdba · audit A · 5 stars
issue-ingest SKILL.md skill
pillumina/ascend-sleuth · skills/issue-ingest/SKILL.md · 从外部 issue 源(GitHub 等)批量导入案例知识。编排上游 issue 拉取、硬过滤、价值评估、沉淀与状态标记:拉取精简元数据(fetch_issues.py,不含…
git:20261030.0194eb5 · audit B · 5 stars
knowledge-groom SKILL.md skill
pillumina/ascend-sleuth · skills/knowledge-groom/SKILL.md · 昇腾知识库的周期性维护引擎。先同步远端知识到确定 commit,用有界子 agent 比对本地草稿与现有 case 的语义(root cause / 机制 / 修复 / 证据),由确定性脚本校验并保守聚合,更新本地草稿评估状态; 再批处理…
git:20261105.abfd57d · audit A · 5 stars
preload-panel SKILL.md skill
pillumina/ascend-sleuth · skills/preload-panel/SKILL.md · 在 DSH 会话中加载 ascend-sleuth 面板,并处理「装了但 tab 不出现」。先按本机给模型的工具与桌面版 自带的东西选装载路:有 cordis_define / cordis_run 在会话内热加载;有…
git:20261103.12b1f39 · audit A · 5 stars
reference-ingest SKILL.md skill
pillumina/ascend-sleuth · skills/reference-ingest/SKILL.md · 从 GitCode 等可按 API 枚举的**文档仓**批量摄取官方文档,沉淀为 reference 先验词条(面向训练/推理的中断、精度、性能定位)。编排「仓库文档面普查 → 增量扫描(path×blob sha…
git:20261009.3640a77 · audit A · 5 stars

Every file in pillumina/ascend-sleuth

Other files named skill-review

skill-review SKILL.md skill
techygarg/lattice · dev-skills/skill-review/SKILL.md · Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario…
git:20261009.a96f344 · audit A · 211 stars
skill-review Cursor rule
uipath/skills · .cursor/rules/skill-review.mdc · Strict skill audit/review framework — use when user asks to review, audit, grade, or compare skills, or when reviewing…
git:20260427.33384fd · audit A · 177 stars
skill-review SKILL.md skill
gke-labs/kube-agents · .agents/skills/skill-review/SKILL.md · Reviews agent skill definitions for token efficiency, clarity, and standardized formatting.
git:20260924.e118413 · audit A · 124 stars
skill-review SKILL.md skill
runxhq/runx · skills/skill-review/SKILL.md · Inspect, safely test, and assess one Runx skill package for capability, trust, and operator readiness. Use when…
git:20261023.420f372 · audit A · 104 stars
skill-review SKILL.md skill
hiroro-work/claude-plugins · .claude/skills/skill-review/SKILL.md · Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements…
git:20260930.c4b8cab · audit A · 47 stars
skill-review SKILL.md skill
coupler-io/skills · .agents/skills/skill-review/SKILL.md · Use this skill when reviewing a Coupler.io skill before merge, auditing an existing one, or checking a pack of skills…
v1.2.0 · audit A · 40 stars
skill-review SKILL.md skill
stacklok/toolhive-catalog · .claude/skills/skill-review/SKILL.md · Review skill submissions and updates for compliance, security, and quality. Use when evaluating skill.json files…
git:20260603.8ac39de · audit A · 25 stars
skill-review SKILL.md skill
ivy00johns/skill-madness · skills/meta/skill-review/SKILL.md · Audit and review skills for quality, consistency, and triggering accuracy — including skills that under-trigger or…
v1.3.0 · audit A · 11 stars

Browse by kind, by grade A, or by owner.