CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

brainstorming

IMMEDIATELY USE THIS SKILL before answering any task - internal design thinking that identifies the question type, selects applicable skills, and converges on the best approach before implementation

Quality

71%

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 ./examples/officeqa/.claude/skills/brainstorming/SKILL.md

The canonical home for this skill is brainstorming in sentient-agi/EvoSkill

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 content is a well-structured, lean six-phase workflow with concrete scaffolding templates and an explicit mandatory verification checkpoint plus feedback loop. It fully satisfies workflow clarity and progressive disclosure, with only minor conciseness and actionability room for improvement.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — it does not explain what a skill or formula is — with structured bullet lists and templates that mostly earn their tokens; the only mild over-explanation is the templated "Assuming [X] convention because..." block, keeping it just below the lean-5 anchor.

4 / 5

Actionability

It provides concrete executable scaffolding — explicit question dimensions to classify, skill-chain reasoning sentence templates, and a fill-in Analysis Plan block with a verification checklist — which is mostly actionable guidance with only minor gaps, and as an instruction-only skill the absence of code is not penalized.

4 / 5

Workflow Clarity

The six phases are clearly sequenced, and Phase 6 is an explicit "MANDATORY" pre-output verification checklist with a feedback loop ("If ANY check fails → re-verify inputs and reasoning"), matching the clear-sequence-with-explicit-validation-and-error-recovery anchor.

5 / 5

Progressive Disclosure

It is a single self-contained, well-sectioned file with no bundle files and no nested references, so under the simple-skill (<50 lines of guidance, single purpose) exception progressive disclosure scores 5 with well-organized sections alone.

5 / 5

Total

18

/

20

Passed

Description

43%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 states concrete capabilities but is hampered by a maximally broad trigger ("before answering any task") that creates high conflict risk and provides no natural user-uttered trigger terms. It answers "what" clearly but never answers "when" with an explicit trigger clause.

Suggestions

Replace "IMMEDIATELY USE THIS SKILL before answering any task" with an explicit, natural trigger clause such as "Use when planning a multi-step approach, choosing between skills, or structuring design thinking before implementation."

Add concrete trigger terms users would actually say (e.g. "brainstorming", "approach planning", "skill selection", "design thinking") so the skill surfaces on relevant queries.

Narrow the scope so it does not compete with every other skill; reference the specific situation (ambiguous or multi-skill tasks) rather than "any task".

DimensionReasoningScore

Specificity

Lists several concrete actions — "identifies the question type", "selects applicable skills", "converges on the best approach before implementation" — which matches the several-specific-actions-with-minor-gaps anchor, just short of the comprehensive 5-anchor coverage.

4 / 5

Completeness

It gives a clear "what" (identifies question type, selects skills, converges on approach) but has no "Use when..." or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; it is not a 4 because there is no when-clause at all.

3 / 5

Trigger Term Quality

The only trigger phrasing is the generic "before answering any task"; it lacks natural terms a user would actually say (e.g. "brainstorming", "design thinking", "plan an approach"), matching the one-or-two-generic-keywords anchor and clearly below the keyword-coverage-3 anchor.

2 / 5

Distinctiveness Conflict Risk

"before answering any task" is maximally broad, so this skill would contend with virtually every other skill for every prompt, matching the very-broad / high-overlap-risk anchor rather than the somewhat-specific 3 anchor.

2 / 5

Total

11

/

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

sentient-agi/EvoSkill

Path

examples/officeqa/.claude/skills/brainstorming/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.