CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-harness

Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate)

Quality

72%

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 ./.agents/skills/moai-harness/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 maximally lean, unambiguous delegator that cleanly hands off to the moai skill with no wasted tokens or nested references. Its weaknesses are that it forwards without any detail on the subcommands it advertises (status/apply/rollback/disable) and provides no validation checkpoint for the state-changing operations in its scope.

Suggestions

Add a one-line table or list of the harness subcommands (e.g. status, apply, rollback, disable) with the arguments each accepts so the forwarding instruction is actionable without opening the moai skill.

Include one or two concrete invocation examples showing typical $ARGUMENTS values.

Mention the approval/verification gate (e.g. confirm with the user before apply or rollback) so state-changing operations have an explicit checkpoint.

DimensionReasoningScore

Conciseness

The body is a single line — 'Use Skill("moai") with arguments: harness $ARGUMENTS' — with zero padding, no explanation of concepts Claude already knows, and every token earning its place. This matches the 'lean and efficient' anchor exactly.

5 / 5

Actionability

The instruction is concrete — an exact skill name ('moai') and exact argument prefix ('harness') — but it is incomplete: there are no usage examples, no list of valid subcommands or arguments, and the full substance is delegated to a skill whose behavior is not described anywhere in this bundle. This fits 'some concrete guidance but incomplete; missing key details' better than 'mostly executable with minor gaps'.

3 / 5

Workflow Clarity

As a simple single-action skill the forwarding step is unambiguous, which alone could score 5 under the simple-skill exception. However, the skill's stated scope includes state-changing operations — 'apply', 'rollback', and 'disable' of the harness learning subsystem — and the body contains no validation or verification step for them, which caps workflow clarity at 3 per the destructive-operations guideline.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist), so nothing needs splitting. The single delegation to Skill("moai") is a clearly signaled, one-level-deep pointer with nothing buried or nested — matching the well-organized simple-skill case that merits a 5.

5 / 5

Total

16

/

20

Passed

Description

58%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 conveys a concrete, two-pronged capability with named subcommands, but it omits any 'when to use' trigger guidance and relies on internal jargon ('Context-First Discovery', 'harness learning subsystem') that users would not naturally say. It is serviceable but would benefit from an explicit trigger clause in plainer language.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to check, apply, roll back, or disable harness learning, or wants to create a new harness from a description.'

Replace or gloss internal jargon such as 'Context-First Discovery + name derivation + approval gate' with natural trigger phrases users would actually type.

Include common synonyms or user-facing terms for 'harness learning subsystem' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'status/apply/rollback/disable' subcommands plus 'Context-First Discovery + name derivation + approval gate' — so it goes beyond naming the domain. It is not a 5 because the actions are wrapped in undefined internal jargon ('harness learning subsystem', 'Context-First Discovery') and coverage of what 'manage' entails beyond the four verbs is not comprehensive.

4 / 5

Completeness

The 'what' is stated clearly ('Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis'), but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' is concrete and detailed, not vague.

3 / 5

Trigger Term Quality

Terms like 'status', 'apply', 'rollback', and 'disable' are natural verbs a user might say, but there are no natural trigger phrases (no 'Use when...' or equivalent) and jargon like 'Context-First Discovery' and 'name derivation' is not language a user would spontaneously use. Some relevant keywords exist, but common variations and synonyms are missing — matching the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor.

3 / 5

Distinctiveness Conflict Risk

The niche scope ('harness learning subsystem' of a specific moai system, with named subcommands) makes it mostly distinct with only minor overlap risk against other harness- or config-management skills. It is not a 5 because 'harness' is a common generic software term and no distinct trigger phrases are given to disambiguate from other harness-related skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

modu-ai/moai-adk

Path

.agents/skills/moai-harness/SKILL.md

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.