CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

widen

Assemble cases from context, induce the widest sound rule. Use when a real case shows a class no rule yet decides, or a rule decides only the cases it came from.

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 exemplary lean instruction-only skill: a precisely sequenced procedure with built-in counterexample hunting, a smallest-narrowing repair rule, and explicit loop termination and fallback. Its only gap is the absence of a worked example showing a case set and its induced rule.

DimensionReasoningScore

Conciseness

Every line instructs and none explains concepts Claude already knows (e.g., "Do not summarize the cases. Induce the widest rule that gets every case in the set exactly right"); the body assumes competence and every token earns its place.

5 / 5

Actionability

The guidance is concrete and executable for an instruction-only skill — exact quantities ("List 10 situations"), an explicit narrowing rule, and a defined fallback — but no worked example of a case or derived rule is given, leaving the minor gap that distinguishes anchor 4 from anchor 5.

4 / 5

Workflow Clarity

Assemble → Induce → Probe → Hand back is a clear sequence with an explicit validation loop ("Found one → narrow the rule by the smallest amount that fixes it… Then list and hunt again"), a defined termination condition, and a stop-and-record fallback, fully matching the feedback-loop anchor.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (and none exist in the bundle), and is organized into four well-labeled sections — the simple-skill case where well-organized sections alone justify the top anchor.

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 answers both what and when explicitly and carves out a distinct niche, but its trigger language is abstract and jargon-leaning, which weakens natural-trigger matching and caps specificity at two named actions. Tightening the when-clause into plainer conditions and adding common synonyms would lift it.

Suggestions

Add natural trigger synonyms users would actually say (e.g., 'generalize', 'derive a rule from examples', 'widen a rule') alongside the current 'induce the widest sound rule' phrasing.

Mention one more concrete action from the body — e.g., probing the rule with counterexamples — so the description covers more of the skill's actual work.

Rewrite the when-clause conditions in plainer language (e.g., 'Use when cases arrive that an existing rule does not decide, or a rule covers only the exact cases that produced it').

DimensionReasoningScore

Specificity

The description names two concrete actions ("Assemble cases from context, induce the widest sound rule") but stops there — the probe and hand-back actions from the body are absent, matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-action anchor above.

3 / 5

Completeness

Both parts are explicit: the what ("Assemble cases from context, induce the widest sound rule") and a "Use when" clause with two trigger conditions. It falls short of anchor 5 because the when-conditions are abstract and densely worded rather than concrete trigger phrases a user would naturally produce.

4 / 5

Trigger Term Quality

Terms like "real case", "rule", and "induce" are relevant to the domain, but the phrasing is technical and misses the natural variations a user would say (e.g., "generalize", "derive a rule from examples", "widen a rule"), fitting the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche — rule induction from observed cases — with distinctive triggers ("a class no rule yet decides", "a rule decides only the cases it came from"), carrying only minor overlap risk with general reasoning or generalization 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

saadshahd/moo.md

Path

hope/skills/widen/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.