CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-ideate

Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use ce-brainstorm to refine the user's own idea.

70

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

A dense, well-engineered orchestration skill: strongly actionable, clearly sequenced with validation checkpoints, and exemplary progressive disclosure that defers detail to verified reference files. Its only real weakness is verbosity from redundant cross-phase restatements that could be consolidated.

Suggestions

Consolidate the surprise-me routing rule into one authoritative statement and cross-reference it from 0.3, 0.6, and Phase 1 instead of restating it in each.

Tighten the Phase 0.6 cost-transparency and Phase 1 issue-intelligence paragraphs into compact bullet lists to cut redundant connective prose.

Factor the repeated '<root>' resolution / no-repo-mode guidance so it is stated once and linked, reducing near-duplicate paragraphs across 0.1, 0.3, and the Artifact Root block.

DimensionReasoningScore

Conciseness

High signal density with no concept-explaining fluff, but several rules are restated across phases (e.g., surprise-me routing in 0.2/0.3/0.6/Phase 1) and long paragraphs like the Phase 0.6 cost-transparency and issue-intelligence blocks could be tightened.

2 / 3

Actionability

Provides copy-paste-ready subagent dispatch prompts with explicit placeholders, an exact executable bash scratch-dir block, and concrete file paths and precedence rules.

3 / 3

Workflow Clarity

A clearly sequenced Phase 0 → 1 → 1.5 → 2 flow with explicit validation gates, fallbacks, and error-recovery loops (e.g., the issue-scan unavailable marker, axis-coverage recovery agents).

3 / 3

Progressive Disclosure

Well-signaled one-level-deep references loaded at point of use ('Read references/divergent-ideation.md now… This load is non-optional'), with all 11 referenced bundle files verified present and detail deliberately kept out of the main body.

3 / 3

Total

11

/

12

Passed

Description

90%Weight 40%Scale 1-3

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, well-structured description with explicit what/when triggers and good natural-language keywords. The main weakness is that the named actions ('generate', 'evaluate') are somewhat abstract rather than a fully concrete, comprehensive capability list.

DimensionReasoningScore

Specificity

Names the ideation domain and two real actions ('Generate and evaluate grounded ideas'), but 'evaluate' and 'grounded ideas' are abstract rather than a comprehensive concrete action list.

2 / 3

Completeness

Explicitly states what ('Generate and evaluate grounded ideas') and a clear 'Use when the user asks for ideas, improvements, surprising options, or AI-generated directions' trigger.

3 / 3

Trigger Term Quality

Covers natural user-sayable terms — 'ideas', 'improvements', 'surprising options', 'AI-generated directions' — matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

Actively de-conflicts from the sibling skill ('use ce-brainstorm to refine the user's own idea') and scopes to 'before choosing one to develop', giving it a clear niche.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 5 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
EveryInc/compound-engineering-plugin
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.