CtrlK
BlogDocsLog inGet started
Tessl Logo

creative-ideation

Generate ideas via named methods from creative practice.

59

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 ./optional-skills/creative/creative-ideation/SKILL.md
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 exemplar routing-focused SKILL.md: a crisp operating-rules core, a concrete 4-step procedure with override and ambiguity handling, a validation-style anti-default check, and a clean file map over a real, one-level-deep reference bundle. The only weakness is mild repetition of the anti-slop directive across sections, which costs a little token efficiency without hurting clarity.

DimensionReasoningScore

Conciseness

The body is dense and well-structured — cue tables, routing rules, and an output template with essentially no padding or explanation of concepts Claude already knows. A few directives repeat the anti-slop theme across Operating rules, Step 2, and the Anti-default check (e.g. "Routing failures produce slop" / "If you generate without routing, you've defeated the skill"), which is minor over-explanation that could be trimmed — one notch below fully lean.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact signal-extraction tables, override rules with concrete thresholds ("Refuse the first **5** ideas, not 3"), a per-route file path for every table entry, verbatim example clarifying questions, and a copy-paste output template. Specific examples cover the common cases; nothing stays at the abstract level.

5 / 5

Workflow Clarity

The 4-step routing procedure is clearly sequenced (extract signals → apply overrides → route by phase/domain → handle ambiguity), followed by an explicit Anti-default check that acts as a validation checkpoint with stop conditions and a recovery loop ("routing failed, redo") — matching the anchor's "explicit validation steps; feedback loops for error recovery; checklists". This is generative, not destructive/batch work, so no cap applies.

5 / 5

Progressive Disclosure

Verified against the actual bundle: all 22 referenced method files, plus anti-slop.md, heuristics.md, full-prompt-library.md, method-catalog.md, and exercises.md exist, none of the reference files chain-reference further (exactly one level deep), and the File Map section gives one-line descriptions of each with "load only the one you're using" guidance. The body is a pure router/overview — content is appropriately split and easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

50%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 a clear, moderately specific "what" but omits any explicit "when to use" trigger guidance and lacks the natural brainstorming vocabulary (brainstorm, stuck, inspire me, help me pick) that would let it fire on the right prompts. It is serviceable but well below the quality of the rubric's good examples, which all pair a concrete "what" with a "Use when..." clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for ideas, wants to brainstorm, says they're stuck or wants inspiration, or asks help choosing between ideas."

Include the natural trigger vocabulary users actually say — brainstorm, ideation, inspire me, I'm stuck, help me pick — rather than only the generic "Generate ideas".

Mention the routing behavior (reads the situation and picks one matching method) so the description distinguishes this skill from generic brainstorming helpers.

DimensionReasoningScore

Specificity

"Generate ideas via named methods from creative practice" names the ideation domain and one concrete action with its mechanism (named methods), but stops short of listing several specific actions. It is more concrete than score 2's "names the domain but actions are minimal or generic" yet does not reach the multi-action coverage of scores 4-5.

3 / 5

Completeness

The "what" is clearly stated (generate ideas via named methods from creative practice), but there is no "Use when..." clause or equivalent trigger guidance — the "when" is only weakly implied by "ideas" and "creative". Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant natural terms like "Generate ideas" and "creative" are present, but common user phrasings — "brainstorm", "brainstorming", "I'm stuck", "inspire me", "help me pick", "what should I make" — are absent. This matches "some relevant keywords but missing common variations or synonyms"; it is not comprehensive enough for 4-5.

3 / 5

Distinctiveness Conflict Risk

The creative-ideation niche gives it some distinctness, but the bare phrase "Generate ideas" overlaps with any general brainstorming, writing, or research ideation skill. It is "somewhat specific but could still overlap with similar skills" rather than a clearly distinct trigger set (4-5) or a totally generic description (1-2).

3 / 5

Total

12

/

20

Passed

Validation

75%

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

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 28 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.