CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/hns-oss-docs-verify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly written, fully executable verification gate with clear sequencing, explicit validation checkpoints, and a feedback loop tying checks to sprint-contract thresholds. Its only weakness is that all content lives in one monolithic file with no reference split, which is justified but leaves progressive disclosure slightly short of ideal.

DimensionReasoningScore

Conciseness

The body is mostly lean executable commands with terse annotations; the ratchet rationale in §4 is somewhat verbose, though it conveys non-obvious domain design rather than concepts Claude already knows, so only minor trimming is warranted.

4 / 5

Actionability

Every section provides copy-paste-ready, executable bash — 'hugo --minify --gc', the grep patterns, the awk parity pipeline, and the comm commands — covering the common cases completely.

5 / 5

Workflow Clarity

Six numbered checks are sequenced with explicit pass/fail criteria ('no matches', 'must exit 0 AND warning-free'), an explicit 'Failure condition' block in §4, and a feedback loop ('fix and re-verify before handing back') via the scoring map.

5 / 5

Progressive Disclosure

No bundle files exist and content is intentionally inlined into well-organized numbered sections plus a scoring map; structure is good and navigation is easy, but it remains a ~150-line monolithic file rather than split reference material.

4 / 5

Total

18

/

20

Passed

Description

60%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific and distinctive, enumerating concrete verification actions, but it relies on technical jargon rather than natural user trigger phrases and omits an explicit 'Use when…' clause. Completeness is therefore capped despite a clear what/when structure.

Suggestions

Add an explicit 'Use when…' clause with natural trigger phrases (e.g., 'Use when verifying the oss-docs site before handing a sprint back to the orchestrator') to lift completeness above 3.

Soften jargon with at least one natural keyword a user might say (e.g., 'docs build', 'i18n parity check') so the description reads as a trigger, not only as harness internals.

Keep the concrete action list, but consider leading with the user-facing intent ('Verifies the oss-docs site is publication-ready') before the harness framing.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — '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' — giving comprehensive coverage of what the recipe checks.

5 / 5

Completeness

The 'what' is clear and detailed, and 'every specialist executes before returning' implies a structural when, but there is no explicit 'Use when…' trigger clause, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

The description is dominated by technical jargon ('harness', 'exit gate', 'Mermaid LR/RL direction grep', 'section-count parity') and lacks the natural phrases a user would actually say; it names the domain (hugo, docs) but misses common natural trigger terms.

2 / 5

Distinctiveness Conflict Risk

It carves a clear niche ('oss-docs harness … exit gate', hugo build, specific named checks) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
modu-ai/moai-adk
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.