CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

complain

Surfaces what the agent would change and kept to itself — a decision it would make differently, effort it saw wasted, a better route to the goal, a fact the user lacks, friction in the tools, permissions, setup or docs the work ran on. Use when you hold one of these and have not said it.

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean instruction-only skill: it defines its object precisely, specifies an exact output format and placement, and wastes no tokens. The only minor gaps are the placeholder-only card example and the unexplained 'band' term.

DimensionReasoningScore

Conciseness

The ~15-line body has no padding: every line instructs (definition of a suggestion, one-line format, card placement), and it trusts the reader's competence ('Keep the reasoning until the user asks'). It never explains concepts Claude already knows, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The card block is a copy-paste-ready template and the format rule is exact ('the problem, then `→` what you would do'), but the JSON holds only a `…` placeholder with no filled-in example, and 'the band keeps those' is unexplained jargon leaving minor gaps.

4 / 5

Workflow Clarity

This is a simple single-action skill and the action is unambiguous: hold the suggestion, end the reply with it as a card ('never in its text'), and carry on with the task. No destructive or batch operations are involved, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ exist), and the short paragraph structure is fully adequate for content of this size, matching the simple-skill exception.

5 / 5

Total

19

/

20

Passed

Description

81%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.

A specific, complete, third-person description that clearly states both what the skill surfaces and when to use it. Its main weakness is trigger-term coverage: it lacks the natural synonyms (feedback, complaint, suggestions) that would help it be selected by name or phrasing.

Suggestions

Add natural trigger synonyms users would actually say — e.g., 'feedback', 'complaint', 'what would you change', 'retrospective' — so the skill is discoverable beyond its precise but unusual phrasing.

Echo the skill's own name or output artifact (e.g., 'suggestions card') in the description so searches for 'card' or 'suggestion' match the trigger.

Briefly differentiate the trigger from ordinary review/feedback output (e.g., 'unspoken, not already-delivered feedback') to reduce overlap with code-review or feedback skills.

DimensionReasoningScore

Specificity

It enumerates concrete, comprehensive categories of what gets surfaced ('a decision it would make differently, effort it saw wasted, a better route to the goal, a fact the user lacks, friction in the tools, permissions, setup or docs') in third person, with no vague padding or over-claims. Not 4: there are no coverage gaps to point to.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is the enumerated list of surfaced items, and the 'when' is concrete ('Use when you hold one of these and have not said it'). Not 4: the when-clause is already explicit and specific, not something that 'could be more explicit'.

5 / 5

Trigger Term Quality

Relevant keywords exist ('change', 'friction', 'tools, permissions, setup or docs') but the natural phrases a user or agent would echo are missing — 'feedback', 'complaint', 'suggestions', 'what would you do differently'. Fits 'some relevant keywords but missing common variations'; not 4 because coverage is partial rather than good-with-a-few-missing.

3 / 5

Distinctiveness Conflict Risk

A clear niche (agent-held unspoken suggestions, emitted as a card at reply end) with a distinct trigger, but it can overlap with general feedback/review skills that also collect improvement suggestions. Mostly distinct with minor overlap risk.

4 / 5

Total

17

/

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

saadshahd/moo.md

Path

hunch/skills/complain/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.