Hns Oss Docs Verify logo

Hns Oss Docs Verify

OrganizationPopular
modu-ai
hns-oss-docs-verify

Mandatory verify recipe for the oss-docs harness — the runnable exit gate every specialist executes before returning: warning-free hugo build, sitemap existence, URL-blacklist grep, Mermaid LR/RL direction grep, 4-locale file-existence and section-count parity, README 4-file heading parity, and body-emoji scan. All checks are inlined here because docs-i18n-check.sh and gen_menu.py do not exist.

Overview

Publishermodu-ai
Repositorymoai-adk
Skill namehns-oss-docs-verify
Stars
1.2K
Forks
226
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by modu-ai on GitHub. Read the source before you install it.

Installation

Install the Hns Oss Docs Verify AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-oss-docs-verify
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/modu-ai/moai-adk.git /tmp/moai-adk
mkdir -p .claude/skills
cp -r /tmp/moai-adk/.claude/skills/hns-oss-docs-verify .claude/skills/hns-oss-docs-verify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hns Oss Docs Verify in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hns Oss Docs Verify on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hns Oss Docs Verify is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

oss-docs Verify Recipe (exit gate)

Runnable checks for the sprint-contract dimensions. The scripts docs-i18n-check.sh and gen_menu.py DO NOT exist — never shell out to them; every check is inlined below. All checks are read-only; this skill never commits or pushes.

1. Build clean (build-clean, must_pass, threshold 1.0)

bash
cd docs-site && hugo --minify --gc
  • Must exit 0 AND complete warning-free (any WARN/ERROR line = FAIL).
bash
test -f docs-site/public/sitemap.xml && echo "sitemap OK" || echo "sitemap MISSING"

2. URL blacklist (content-fidelity)

bash
grep -rn 'docs\.moai-ai\.dev\|adk\.moai\.com\|adk\.moai\.kr' docs-site/content README*.md
  • Expected: no matches. Only adk.mo.ai.kr is valid. Note: the pattern adk\.moai\.kr does not match adk.mo.ai.kr (different dot positions) — no false positive on the valid domain.

3. Mermaid direction (style-compliance)

bash
grep -rn 'flowchart LR\|graph LR\|flowchart RL\|graph RL' docs-site/content
  • Expected: no matches (TD-only rule; flowchart TD / graph TB pass).

4. 4-locale parity (locale-parity, must_pass, threshold 1.0)

File-existence parity — every ko page has en/ja/zh counterparts:

bash
cd docs-site/content && for f in $(cd ko && find . -name '*.md'); do
  for loc in en ja zh; do
    [ -f "$loc/$f" ] || echo "MISSING: $loc/$f"
  done
done

Section-count parity per page, ratcheted against a checked-in baseline.

Comparing tree totals is not a parity check: per-page divergences in opposite directions cancel, so a page where ko leads en nets out against a page where en leads ko and the total looks healthy. Compare each page against its own three counterparts instead.

The gate is a ratchet, not an absolute check. docs-site/.locale-parity-baseline lists the pages that already diverge; the gate fails on any divergent page NOT in that list. An absolute check would fail on every baselined page from the first run, and a gate that fails on day one gets switched off — which is worse than the weak check it replaces. Ratcheting means the debt is explicit and auditable, and it can only shrink.

bash
cd docs-site/content

# Current divergence set: pages whose ko/en/ja/zh H2-and-deeper counts disagree.
# One grep pass over the whole tree — a per-file loop over 143x4 files does not
# finish inside a 2-minute budget.
grep -rc '^#\{2,\} ' ko en ja zh --include='*.md' \
| awk -F: '
    { i=index($1,"/"); loc=substr($1,1,i-1); page=substr($1,i+1)
      n[page,loc]=$2; pages[page]=1 }
    END { for (p in pages)
            if (n[p,"en"]!=n[p,"ko"] || n[p,"ja"]!=n[p,"ko"] || n[p,"zh"]!=n[p,"ko"])
              print p }' \
| sort > /tmp/parity-now.txt

grep -v '^#' ../.locale-parity-baseline | grep -v '^[[:space:]]*$' | sort > /tmp/parity-base.txt

comm -23 /tmp/parity-now.txt /tmp/parity-base.txt   # NEW divergence  -> FAIL
comm -13 /tmp/parity-now.txt /tmp/parity-base.txt   # converged pages -> prune baseline

Failure condition (explicit): the first comm prints one or more page paths. Any output there is a FAIL — a page that was previously in parity has lost it, or a newly added page landed unbalanced. Fix the page, or (only with a deliberate decision) add it to the baseline; adding a line is admitting new debt.

The second comm is informational: those pages have converged and should be pruned from the baseline so the ratchet tightens. Not pruning is not a failure.

A missing counterpart file also surfaces here (its count reads as empty and therefore disagrees), which overlaps with the file-existence check above — that redundancy is intentional.

README 4-file heading-count parity:

bash
grep -c '^## ' README.md README.ko.md README.ja.md README.zh.md
  • Expected: identical counts across the 4 files (and identical H2 order — spot-check with grep '^## ' <file>).

5. Body-emoji scan (style-compliance)

bash
grep -rnP '[\x{1F300}-\x{1FAFF}\x{2600}-\x{26FF}\x{2700}-\x{27BF}]' docs-site/content --include='*.md' | grep -v '{{<' | head -40
  • Review each hit: body-text emoji = FAIL (use {{</* icon */>}}); preserved typographic symbols (→ ← ↓ ✓ ✗, U+2702 in handoff blocks) and branding emoji inside orchestrator-banner example code blocks are allowed — judge code-block context before flagging.

6. Version-string sync (version-sync)

Version displays must equal the release number. Extract the expected version from the SSOT and screen for stale displays:

bash
grep -E 'version = ' docs-site/hugo.toml    # expected version, e.g. v3.1.1
grep -rn 'Release-v[0-9]' README.md README.ko.md README.ja.md README.zh.md
grep -rn '🗿 v[0-9]' docs-site/content README*.md | grep -v "$(grep -oE 'version = "v[0-9.]+"' docs-site/hugo.toml | grep -oE 'v[0-9.]+')"
  • Expected: every Release-v… badge and every 🗿 v… example equals the hugo.toml version. Any stale display (badge, statusline example, update-prompt example X ⬆️ Y, version-column example) = FAIL.
  • Historical citations ("introduced in vX.Y.Z", "since v3.0.0", "retired in v3.0.0") are not displays — do not flag them.
  • releaseDate must be bumped together with version (hugo.toml's own two-line contract).

Scoring map (sprint contract)

DimensionChecksThreshold
locale-parity§4 (file existence clean + zero NEW section-count divergence + README parity = 1.0)1.0 (must_pass)
build-clean§1 (build warning-free + sitemap = 1.0)1.0 (must_pass)
style-compliance§3 + §5 (proportion of clean checks)0.95
content-fidelity§2 + facts/figures preserved vs canonical0.9
version-sync§6 (version displays == release number)1.0 (must_pass)

A must_pass dimension below threshold blocks the harness run result (must_pass_ok: false) — fix and re-verify before handing back to the orchestrator.

Frequently asked questions

What does the Hns Oss Docs Verify AI skill do?

Mandatory verify recipe for the oss-docs harness — the runnable exit gate every specialist executes before returning: warning-free hugo build, sitemap existence, URL-blacklist grep, Mermaid LR/RL direction grep, 4-locale file-existence and section-count parity, README 4-file heading parity, and body-emoji scan. All checks are inlined here because docs-i18n-check.sh and gen_menu.py do not exist.

Why use Hns Oss Docs Verify on TypingMind?

Because you install it once and use it with any model. Hns Oss Docs Verify is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hns Oss Docs Verify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-oss-docs-verify. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hns Oss Docs Verify?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hns Oss Docs Verify?

As many as you like. As long as a model supports skills, you can use Hns Oss Docs Verify with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hns Oss Docs Verify AI skill free?

Yes. It is published on GitHub by modu-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇