评估 CANN 算子仓的「进阶教程 / 开发指南」类文档质量——通读文档 + 对照算子代码静态查证(默认不跑),按五轴(找得到/信得过/学得会/可操作/读得懂)找出 漏讲/讲不清/过时/对不上代码/概念讲错,产出带证据与改进建议的体检报告(MD + HTML)。涉及「评进阶教程 / 开发指南文档质量 / 文档对不对得上代码 / 教程审稿 / tutorial 体检 /…

No licenceAuto-check passedDevelopment

Install Tech Docs Guard

skills CLI
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill tech-docs-guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ascend-ai-coding/awesome-ascend-skills tech-docs-guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-tools/tech-docs-guard .claude/skills/tech-docs-guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tech-docs-guard
GitHub stars
174
Token cost
~2.7k tokens
SKILL.md length
665 words
Files
15 (incl. scripts, references)
Skills in repo
69
Repo updated
First seen
Licence
None found

At a glance

评估 CANN 算子仓的「进阶教程 / 开发指南」类文档质量——通读文档 + 对照算子代码静态查证(默认不跑),按五轴(找得到/信得过/学得会/可操作/读得懂)找出 漏讲/讲不清/过时/对不上代码/概念讲错,产出带证据与改进建议的体检报告(MD + HTML)。涉及「评进阶教程 / 开发指南文档质量 / 文档对不对得上代码 / 教程审稿 / tutorial 体检 /…

  • Works in 3 steps: 不打玄学分。主观判断(讲不清 / 教不会 / 讲错)flag 之前先… → grep 不到 ≠… → 按「实际开发者影响」判,不按「机械字面对照」判。报一条(尤其升…
  • Development work in your project
  • SKILL.md covers ⚠ 本 skill 的三条灵魂(不可违背), When to invoke, Inputs(零硬编码,每次会话发现或询问) and 评估框架(五轴最小核), plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Tech Docs Guard is an agent skill from ascend-ai-coding/awesome-ascend-skills. 评估 CANN 算子仓的「进阶教程 / 开发指南」类文档质量——通读文档 + 对照算子代码静态查证(默认不跑),按五轴(找得到/信得过/学得会/可操作/读得懂)找出 漏讲/讲不清/过时/对不上代码/概念讲错,产出带证据与改进建议的体检报告(MD + HTML)。涉及「评进阶教程 / 开发指南文档质量 / 文档对不对得上代码 / 教程审稿 / tutorial 体检 / 文档信不信得过」等意图时使用。只评不改不跑,只对着文档与代码出诊断。

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including scripts and reference files (for example `references/problem-taxonomy.md`, `scripts/__init__.py` and `scripts/_state.py`).

It sits in Development. The repository describes itself as: A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/.

When your agent uses it

  • Development work in your project

Example prompts

  • “/tech-docs-guard”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 不打玄学分。主观判断(讲不清 / 教不会 / 讲错)flag 之前先 steelman——先替这段文字辩护到最强(「有没有一种读法这里其实没问题?」),辩不过去才算缺陷;报的话必须给判例(读者会卡在哪 + 原文 + 改进建议),并标「教学判断(非代码事实)」。
  2. grep 不到 ≠ 编造。对照代码只能证明「字符串出现过/没出现」,不能证明它是当前有效入口。结论三态:确认对不上(有强证据反证)/ 疑似过时(静态没找到,但可能生成/外部/分支)/ 未找到静态证据(存疑,不指控)。只有强证据才写「确认」。
  3. 按「实际开发者影响」判,不按「机械字面对照」判。报一条(尤其升 blocker)前自问:正常开发者照这文档做,真会被卡住吗?还是他会理解意图、自然适配? 文档里大量是示意/演示(教某个写法、给个例子),不是要逐字粘贴。只有文档明确要求「把这段粘贴/替换进某文件」的【规定式】内容…

What it can do on your machine

Read from SKILL.md and the folder at commit 62a4ecb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 8 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tech Docs Guard loads about 2.7k tokens when it runs, and up to ~143k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 665 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~143k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 665 words (~2,715 tokens).

“模拟一个挑剔但讲证据的审稿人:通读进阶教程,对照代码查证它「看得懂 / 跑得通 / 信得过」,把「漏讲 / 讲不清 / 过时 / 对不上代码 / 讲错」逐条带证据写成体检报告。”

— opening of SKILL.md by ascend-ai-coding
name
tech-docs-guard
keywords
文档质量, 文档体检, 算子文档, 文档对照代码, 教程审稿, tutorial 体检, doc review, CANN 文档

Read the full SKILL.md on GitHub

Files

SKILL.md and 14 other files (scripts, references) in skills/agent-tools/tech-docs-guard of ascend-ai-coding/awesome-ascend-skills.

  • SKILL.md
  • references/examples/example-report.html
  • references/examples/report-card.png
  • references/examples/report-overview.png
  • references/problem-taxonomy.md
  • scripts/__init__.py
  • scripts/_state.py
  • scripts/codecheck.py
  • scripts/find_tutorials.py
  • scripts/linkcheck.py
  • scripts/render_report.py
  • scripts/requirements.txt
  • scripts/support_table_check.py
  • templates/report-engine.html
  • tests/test_tech_docs_guard.py

Open the folder on GitHubat commit 62a4ecb

Compare with similar skills

Tech Docs Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tech Docs Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tech Docs Guard this skillascend-ai-coding/awesome-ascend-skills174—~2.7kAutomated safety check: PassNone
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k24 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 24 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 22 repos~577 tokens
    DevelopmentAuto-check passed

More from ascend-ai-coding/awesome-ascend-skills

All 69 skills in this repo
  • Ascend Dmi

    ascend-ai-coding/awesome-ascend-skills

    当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景: - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽(h2d/d2h/d2d/p2p) - 跑算力/功耗基准测试(TFLOPS、TOPS) - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试(aicore、内存) - 复位/恢复卡住或异常的 NPU 卡 典型用户问题(即使不提…

    174 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Ascendc

    ascend-ai-coding/awesome-ascend-skills

    End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.

    174 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Atc Model Converter

    ascend-ai-coding/awesome-ascend-skills

    Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.

    174 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • External Cannbot Ops Pypto Op Develop

    ascend-ai-coding/awesome-ascend-skills

    当需要编写 PyPTO 算子实现时使用此 skill。基于需求规格、设计方案和参考实现,生成完整可运行的 PyPTO 算子实现与配套测试、文档。Triggers: 实现算子、写 kernel、编写实现、写 impl、算子编码、开始编码、code the op、写 test、生成测试、写实现代码、op develop、kernel 实现。

    174 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • External Gitcode Ascend Megatron Change Analyzer

    ascend-ai-coding/awesome-ascend-skills

    Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.

    174 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • External Gitcode Ascend Megatron Commit Tracker

    ascend-ai-coding/awesome-ascend-skills

    Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.

    174 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Tech Docs Guard

What does Tech Docs Guard do?

评估 CANN 算子仓的「进阶教程 / 开发指南」类文档质量——通读文档 + 对照算子代码静态查证(默认不跑),按五轴(找得到/信得过/学得会/可操作/读得懂)找出 漏讲/讲不清/过时/对不上代码/概念讲错,产出带证据与改进建议的体检报告(MD + HTML)。涉及「评进阶教程 / 开发指南文档质量 / 文档对不对得上代码 / 教程审稿 / tutorial 体检 /…. Tech Docs Guard is an agent skill from ascend-ai-coding/awesome-ascend-skills.

When should I use Tech Docs Guard?

Tech Docs Guard fits situations like: development work in your project.

How do I install Tech Docs Guard in Claude Code?

Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill tech-docs-guard -a claude-code`. Or copy the skill folder (skills/agent-tools/tech-docs-guard in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/tech-docs-guard in your project. Claude Code loads it when a task matches its description.

How do I install Tech Docs Guard in Codex?

Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill tech-docs-guard -a codex`. Or copy the skill folder (skills/agent-tools/tech-docs-guard in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/tech-docs-guard in your project. Codex loads it when a task matches its description.

Can I use Tech Docs Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill tech-docs-guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-docs-guard, .gemini/skills/tech-docs-guard, .github/skills/tech-docs-guard and .opencode/skills/tech-docs-guard in your project.

What does Tech Docs Guard need to run?

Going by SKILL.md and its folder, Tech Docs Guard needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Tech Docs Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tech Docs Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tech Docs Guard use?

No licence was found for Tech Docs Guard or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Tech Docs Guard use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 140k tokens, read only when the agent opens those files.

What are the alternatives to Tech Docs Guard?

Skills that share tags, products or a category with Tech Docs Guard: Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tech Docs Guard?

ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on October 7, 2026.

Source: ascend-ai-coding/awesome-ascend-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.