CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-plan

Create SPEC document with EARS format requirements and acceptance criteria

Quality

73%

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-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 one-line delegation stub: perfectly token-efficient and structurally clean, with an unambiguous single step and a clearly signaled one-level reference. However, it delegates 100% of the skill's substance to an external "moai" skill without defining $ARGUMENTS, describing the expected output, or providing any fallback, leaving actionability incomplete.

Suggestions

Define what $ARGUMENTS should contain (e.g. the feature or task to plan) and show one example invocation, such as Skill("moai") with arguments: plan "add user login flow".

Add a sentence stating the expected deliverable (the SPEC document with EARS requirements) and a fallback if the moai skill is unavailable — e.g. draft the SPEC directly using EARS syntax ("When [trigger], the system shall [response]").

DimensionReasoningScore

Conciseness

The body is a single line — "Use Skill("moai") with arguments: plan $ARGUMENTS" — with zero padding and every token load-bearing; it fully assumes the executor's competence. Matches anchor 5; not 4 because there is nothing to trim.

5 / 5

Actionability

The one directive is concrete (exact tool name "moai" and argument string "plan $ARGUMENTS"), but key details are missing: $ARGUMENTS is never defined, there is no guidance on what the delegated call produces, no fallback if the moai skill is unavailable, and nothing about the stated deliverable (SPEC with EARS requirements) is covered here. Matches anchor 3 (concrete but incomplete); not 4 because the gaps are not minor — the entire substance of the task lives in another skill.

3 / 5

Workflow Clarity

The single step is unambiguous and precisely specified (invoke Skill "moai" with "plan $ARGUMENTS"), and no destructive or batch operations are involved, but there is no articulation of what follows delegation or how to confirm the SPEC was actually produced. Not 5 because the undefined placeholder and absent outcome check leave a minor gap; not 3 because the one required action cannot be misunderstood.

4 / 5

Progressive Disclosure

The body is one line with nothing that belongs in a separate file, and no bundle files (references/, scripts/, assets/) exist to organize; its single reference — delegation to the "moai" skill — is explicit and one level deep. Matches the simple-skill exception for reference-free, well-organized content; not 4 because there is no content misplacement or buried reference.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, moderately specific "what" — create a SPEC document with EARS-format requirements and acceptance criteria — but entirely omits any "when to use" trigger guidance, which caps completeness and weakens trigger-term quality. It carves a recognizable niche yet gives Claude no activation cues or natural-language synonyms to match against user requests.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to plan a feature, write a spec/specification, or define requirements and acceptance criteria before implementation."

Include natural synonyms users would actually say — "spec", "specification", "plan", "requirements doc" — alongside the technical terms (SPEC, EARS) so phrasing matches without jargon knowledge.

Name the concrete actions performed (e.g. "Drafts the SPEC, writes requirements in EARS syntax ('When [trigger], the system shall [response]'), and defines acceptance criteria") to raise specificity beyond a single verb.

DimensionReasoningScore

Specificity

The description says "Create SPEC document with EARS format requirements and acceptance criteria" — it names the domain (SPEC documents) and concrete artifacts (EARS-format requirements, acceptance criteria), but lists only one action with no broader coverage. Not 2 because the action and artifacts are concrete, not generic; not 4 because there are not several distinct specific actions.

3 / 5

Completeness

The "what" is clear (create a SPEC document with EARS-format requirements and acceptance criteria) but there is no "Use when..." clause or any equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent, not merely imprecise.

3 / 5

Trigger Term Quality

Terms like "SPEC document", "requirements", and "acceptance criteria" are relevant, but common variations users would naturally say ("spec", "specification", "write a plan", "PRD") are missing and "EARS format" is technical jargon. This matches anchor 3 (some relevant keywords, missing variations) — not 4 because coverage is thin for a planning task, not 2 because the terms present are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

"SPEC document", "EARS format", and "acceptance criteria" carve out a fairly distinct planning niche with only minor overlap risk against other spec-writing skills. Not 5 because a generic request to "create a spec" could still collide with other specification-writing skills; not 3 because the EARS/SPEC terminology is more specific than the anchor's "Works with document files".

4 / 5

Total

13

/

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-plan/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.