ce-ideate

Generate and evaluate grounded ideas. Use when the user wants ideas, improvements, or surprising directions before choosing one to develop. Not for refining an idea they already have (ce-brainstorm) or judging one already on the table (ce-pov).

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

A well-architected orchestration skill: terse, pointer-driven, with a clear phased workflow and exemplary progressive disclosure. The main improvement lever is tightening the longest compound sentences and surfacing a couple of validation checkpoints inline rather than solely by reference.

Suggestions

Break Boundary #4 (dispatch-on-unidentified-subject) into a short bulleted list so the tool-discovery rules are scannable instead of a single dense sentence.

Inline one or two of the key scope-gate checks (e.g. the 'ask when subject is not identifiable' rule) so the workflow's validation is visible without opening references/scope-gates.md.

Consider trimming the standalone 'The current year is 2026' line or folding it into the artifact-dating guidance, since it reads as a non-sequitur in an ideation overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and pointer-based, delegating detail to references and assuming Claude's competence; a few compound run-on sentences (notably Boundary #4) could be tightened, keeping it just below fully lean.	4 / 5
Actionability	Concrete guidance throughout — exact paths (<root>/ideation/), commands (git rev-parse --show-toplevel), config files, and an 8-hex run-id format — with the detailed dispatch prompts appropriately deferred to references, leaving minor gaps in standalone executability.	4 / 5
Workflow Clarity	A clearly sequenced Phase 0 → 1 → 1.5 → 2 flow with explicit required-read checkpoints, scope gates, and warn-and-proceed grounding validation; validation is present for the batch fleet dispatch, so the batch cap does not apply, though several checkpoints live in referenced files.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to 13 verified one-level-deep reference files plus an agents/ directory, each clearly signaled (e.g. "Read references/grounding.md before dispatching"), with content appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

82%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.

A strong description: it states concrete actions, gives explicit natural-language triggers, and sharply distinguishes itself from sibling skills via negative boundaries. The only soft spot is specificity, where the action list is brief rather than comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (ideas) and two concrete actions — "Generate and evaluate grounded ideas" — but coverage is not comprehensive (no ranking/critique detail), matching the 2-actions anchor.	3 / 5
Completeness	Explicitly answers both what ("Generate and evaluate grounded ideas") and when ("Use when the user wants ideas, improvements, or surprising directions before choosing one to develop") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"ideas, improvements, or surprising directions" are natural phrases users would say, with good coverage; a few synonyms (e.g. suggestions, brainstorm) are missing, so it sits above the midpoint but short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche reinforced by explicit negative boundaries ("Not for refining an idea they already have (ce-brainstorm) or judging one already on the table (ce-pov)"), giving minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-ideate/SKILL.md
Commit: 26bf5b1

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.