CtrlK
BlogDocsLog inGet started
Tessl Logo

clarify

Adaptive thinking partner that helps clarify, challenge, and refine ideas through persistent questioning. Auto-detects domain (product, architecture, debugging, process, general) and user mode (exploring, deciding, refining) to adapt question style. Actively pushes back on weak reasoning — flags contradictions, challenges assumptions, stress-tests claims. Produces context-appropriate artifacts when done (design doc, hypothesis list, decision matrix, or key insights). Use this skill when: (1) brainstorming or exploring an idea before implementation, (2) requirements are vague and need clarification, (3) making architectural or product decisions, (4) debugging and need to form hypotheses, (5) refining an approach that's mostly decided. Triggers on: 'brainstorm', 'clarify', 'think through', 'explore', 'help me figure out', 'what should I consider', 'let's think about', 'what could go wrong', 'help me decide'.

75

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-crafted, opinionated behavioral skill: highly actionable, clearly sequenced, and cleanly organized. Its only weakness is token efficiency — the Question Arsenal is generous and could be trimmed without losing coverage.

Suggestions

Trim the Question Arsenal: keep one representative prompt per category and drop near-duplicates (e.g. '10x version' vs 'completely different way to approach this') to reduce token load while preserving coverage.

Collapse the Good/Bad challenge and 'What Good Challenges Sound Like' lists into a single compact example set to avoid restating the same guidance twice.

Consider merging the short 'Between Questions' and 'How to Challenge' subsections into the phases that use them, since they are short behavioral notes rather than standalone stages.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no concept explanations) and is mostly efficient, but the Question Arsenal enumerates ~18 template questions across six categories where several overlap in function (e.g. '10x version' vs 'completely different way to approach this'), so it could be tightened rather than fully lean.

2 / 3

Actionability

Highly concrete and executable for an instruction-only skill: domain/mode detection tables, exact opening questions per domain, good/bad challenge phrasings, and artifact templates with explicit fields like 'Problem, user, proposed approach, key decisions, open questions, risks, next action'.

3 / 3

Workflow Clarity

A clear sequenced Core Loop and Phases 0-4 with explicit checkpoints — re-detect mode after each answer, 'challenge by round 3-4', and stop-signal handling — give a well-sequenced process with feedback points appropriate to a conversational skill.

3 / 3

Progressive Disclosure

A single cohesive behavioral skill with no need for external references, organized into clear sections (Core Loop, Phases 0-4, Anti-Patterns) and no nested references, satisfying the well-organized single-file criterion.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, well-structured description: third-person voice, concrete capabilities, explicit 'Use when' guidance, and a broad set of natural trigger terms. It cleanly satisfies all four dimensions at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'clarify, challenge, and refine ideas', 'flags contradictions, challenges assumptions, stress-tests claims', and 'Produces context-appropriate artifacts (design doc, hypothesis list, decision matrix, or key insights)' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what it does and when to use it via a numbered 'Use this skill when' list (5 scenarios) plus a 'Triggers on' phrase list, matching the 'both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

The explicit 'Triggers on' clause gives good natural coverage — 'brainstorm', 'clarify', 'think through', 'explore', 'help me figure out', 'what should I consider', 'let's think about', 'what could go wrong', 'help me decide' — terms users would plausibly say.

3 / 3

Distinctiveness Conflict Risk

It carves a clear brainstorming/thinking-partner niche with a distinctive trigger set; a few phrases like 'help me decide' are mildly generic but the set as a whole is unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mayank-arora/agent-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.