CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dissolve

Find a design that keeps both sides of a trade-off. Use when a trade-off is taken as forced — getting one thing is said to mean giving up another.

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.

An exceptionally lean, well-sequenced reasoning procedure with explicit validation, a bounded feedback loop, a strict output contract, and clean routing to sibling skills. The only notable gap is the absence of a brief worked example that would make the parting patterns fully concrete.

DimensionReasoningScore

Conciseness

Every line instructs and nothing explains concepts Claude already knows — the limit check, the four named parting patterns, the bounded retry, and the output contract all carry weight. This matches the 'lean and efficient; every token earns its place' anchor; there is no padding to trim, ruling out 4.

5 / 5

Actionability

The procedure is concrete and executable for a reasoning skill: four specific parting patterns ('a moment when only one applies, a part of the system only one touches...'), an explicit retry rule ('try a different parting once'), and a strict output contract ('Hand back three parts and nothing else'). It stops short of 5 because there is no worked example covering a common case to anchor the pattern.

4 / 5

Workflow Clarity

The six steps are clearly sequenced with explicit validation checkpoints — the step 2 limit check gates early exit, and step 5 is a test with a feedback loop and bounded retry ('discard it and try a different parting once. If the second fails the same test, the trade-off is real'). Not a destructive or batch operation, so the validation cap does not apply; this matches the top anchor including error-recovery behavior.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and self-contained with no need for external references, and it is well organized into procedure, output contract, and routing notes. The simple-skill guideline applies: this earns a 5 on organization alone; the cross-references to 'consult' and 'reframe' skills are routing, not buried bundle references.

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.

A concise, third-person description with an explicit 'Use when' clause and a clear single purpose. Its weaknesses are limited action coverage and a trigger condition phrased abstractly, which leaves common synonyms and concrete user phrasings uncovered.

Suggestions

List a couple more concrete actions or outcomes (e.g., 'dissolve a false dilemma into a design where both sides hold; name what the design newly costs') to raise specificity.

Add natural trigger phrases users would actually say, such as 'dilemma', 'either/or', 'can't have both', or 'we have to pick one', to improve trigger term coverage.

Sharpen the 'when' clause with concrete user-utterance examples (e.g., 'Use when someone says you can't have X without losing Y') to reach explicit trigger-phrase completeness.

DimensionReasoningScore

Specificity

The description names the domain (trade-offs) and one concrete action — "Find a design that keeps both sides of a trade-off" — matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not 4 because it does not list several specific actions or capabilities.

3 / 5

Completeness

It has a clear 'what' ("Find a design that keeps both sides of a trade-off") and an explicit 'Use when' clause ("Use when a trade-off is taken as forced"), so it clears the completeness cap. It falls short of 5 because the 'when' is phrased as an abstract condition rather than concrete trigger phrases a user would naturally say.

4 / 5

Trigger Term Quality

"trade-off", "forced", and "getting one thing is said to mean giving up another" are relevant natural terms, but common variations users would say — "dilemma", "either/or", "can't have both", "compromise" — are missing, matching the 'some relevant keywords but missing common variations' anchor. Not 4, since the paraphrases all restate one keyword rather than covering distinct trigger phrases.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct — dissolving trade-offs presented as forced — with a qualifying condition that narrows triggering, but "trade-off" alone is broad enough to overlap with general decision-weighing or option-comparison skills. Not 5 because the description does not state what it is not (e.g., trade-offs the user deliberately chose); not 3 because the "taken as forced" qualifier does real disambiguation work.

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/dissolve/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.