CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clarify

Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.

Quality

82%

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.

The body is an exemplar of token efficiency: a crisp four-step workflow with an explicit stop rule and clean boundaries to sibling skills, all in seven lines. The only minor gap is the absence of a short example exchange, which keeps actionability at 4.

DimensionReasoningScore

Conciseness

The body is lean and telegraphic — "One exchange: readings out, pick back." — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching anchor 5.

5 / 5

Actionability

Directives are concrete and executable — "each ending in what it would build or do differently", "name the source", "Take the pick as the confirmed ask and restate it" — but no example exchange shows the output form. For an instruction-only skill this matches anchor 4 (minor gaps) rather than 5 (no example covering the common case).

4 / 5

Workflow Clarity

The sequence is unambiguous — name readings, drop ones a source rules out, ask the user to pick, restate the pick — with an explicit stop-condition: "If the user cannot pick, the words are not the problem — stop." As a single-task skill under 50 lines with a clear checkpoint, it matches anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external files (no references/, scripts/, or assets/ exist), and is organized into clear short paragraphs with explicit routing to the interrogate and elicit skills. Per the simple-skill guideline, well-organized sections alone earn anchor 5.

5 / 5

Total

19

/

20

Passed

Description

62%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 clearly states both what the skill does and when to use it, in a distinct niche, but is held back by thin keyword coverage. Missing natural trigger terms like "ambiguous" or "two interpretations" keeps trigger quality and completeness at mid-range.

Suggestions

Add natural trigger terms users would actually say, e.g. "Use when the user's request is ambiguous, has two interpretations, or would build different things depending on the reading."

Enumerate the concrete actions so coverage reads as comprehensive: name the competing readings, eliminate ones a source rules out, get the user's pick, and restate the confirmed ask.

Add one or two concrete trigger phrases (e.g. "ambiguous requirements", "two ways to read this") to sharpen distinctiveness against generic clarification skills.

DimensionReasoningScore

Specificity

"Turn words with two readings into one confirmed ask" names the domain and a single concrete action, but does not list several specific actions. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4 (no multi-action list) or 2 (the named action is concrete, not generic).

3 / 5

Completeness

Both parts are explicit: the what ("Turn words with two readings into one confirmed ask") and the when ("Use when the user's words admit two readings that would build different things"). The when is present and explicit but lacks concrete trigger phrases, matching anchor 4 rather than 5, and exceeds anchor 3 because the when is not merely implied.

4 / 5

Trigger Term Quality

"two readings" is a relevant phrase, but the natural terms a user would actually say — "ambiguous", "unclear", "two interpretations" — are absent. This matches anchor 3 (some relevant keywords, missing common variations or synonyms), not 4, since the most common synonyms are missing rather than just a few.

3 / 5

Distinctiveness Conflict Risk

"two readings that would build different things" carves a fairly distinct niche — deciding between buildable readings via a user pick — with only minor overlap risk against generic clarification skills. It matches anchor 4; not 5 because no trigger keywords fully separate it from a generic ask-clarifying-questions skill.

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

saadshahd/moo.md

Path

hope/skills/clarify/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.