CtrlK
BlogDocsLog inGet started
Tessl Logo

problem-solving

Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification

51

Quality

56%

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 ./.claude/skills/problem-solving/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is a clean dispatch index with clear routing and good structural intent, but it only describes techniques abstractly and—critically—every referenced sub-skill file is missing from the bundle, so the progressive-disclosure promise is unfulfilled. Tightening the redundant routing and providing the referenced files would lift the weaker dimensions.

Suggestions

Add the referenced sub-skill files (when-stuck/, collision-zone-thinking/, inversion-exercise/, meta-pattern-recognition/, scale-game/, simplification-cascades/) so the one-level-deep references resolve and progressive disclosure works.

Collapse the redundant routing (the When-to-Use table and Quick Reference code block convey the same dispatch) into a single table to improve conciseness.

Replace the abstract technique one-liners with a concrete first step or example for each sub-skill so the index offers some executable guidance even before the reader opens the referenced file.

DimensionReasoningScore

Conciseness

The index is mostly lean, but the stuck-type routing is presented three times (per-skill one-liners, the 'When to Use' table, and the 'Quick Reference' code block), and the 'Core Philosophy' quote is mild editorial padding that could be tightened.

2 / 3

Actionability

The dispatch table gives concrete routing guidance (stuck-type to sub-skill with file locations), but each technique is only described abstractly ('Flip every assumption and see what still works') rather than instructed, and the referenced sub-skill files do not exist in the bundle.

2 / 3

Workflow Clarity

As a single-purpose dispatch skill the action is unambiguous: 'Start here when stuck' points to when-stuck, and the table plus quick reference give a clear stuck-type to technique mapping, which satisfies the simple-skill allowance for workflow clarity.

3 / 3

Progressive Disclosure

The body is well-structured as an overview with one-level-deep, clearly signaled **Location:** references, but none of the referenced files (when-stuck/SKILL.md, collision-zone-thinking/SKILL.md, etc.) exist in the bundle, so navigation is broken and disclosure never progresses to the detail.

2 / 3

Total

9

/

12

Passed

Description

50%

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 is specific enough to convey the skill's niche and lists concrete techniques, but it omits an explicit 'Use when...' trigger clause and leans on invented jargon that users would not naturally say. It is solid but lands at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when stuck on a problem, need to break out of conventional thinking, or want an elegant solution instead of managing complexity') to raise completeness and trigger quality.

Replace or pair jargon like 'collision-zone thinking' with natural user phrases ('stuck', 'brainstorming', 'can't see a way forward') so the description triggers on what users actually say.

Lead with the concrete outcomes/actions rather than the abstract phrase 'Creative problem-solving techniques' to sharpen specificity and distinctiveness.

DimensionReasoningScore

Specificity

It names the domain ('breaking through stuck points') and enumerates four concrete techniques ('collision-zone thinking, inversion, pattern recognition, and simplification'), but the techniques are abstract labels rather than observable actions like the 3-anchor's 'extract text, fill forms, merge documents'.

2 / 3

Completeness

It clearly states WHAT the skill does, but there is no explicit 'Use when...' trigger clause; 'for breaking through stuck points' only implies the when, so per the rubric completeness is capped at 2.

2 / 3

Trigger Term Quality

'problem-solving' and 'stuck points' are natural user terms, but 'collision-zone thinking' and 'inversion' are skill-specific jargon users would not naturally say, and common variations like 'stuck on a problem' or 'brainstorming' are missing.

2 / 3

Distinctiveness Conflict Risk

The umbrella 'Creative problem-solving techniques' is broad and could overlap with general reasoning, brainstorming, or planning skills, though the named techniques give it some niche distinctiveness.

2 / 3

Total

8

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
mrgoonie/claudekit-skills
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.