ce-plan

Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 body is a tight, well-structured orchestration overview: it sequences a multi-phase workflow with explicit checkpoints and feedback loops, and offloads detail to real, clearly signaled one-level-deep references. Its only weakness is a few heavy contractual sentences and some routing deferred to referenced files.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept padding, but several contractual sentences ('A run is complete when...') are long and could be tightened, matching the 'efficient; minor instances of over-explanation' anchor rather than fully lean.	4 / 5
Actionability	Gives concrete phase-by-phase dispatch rules, exact reference-read boundaries, an exact return token ('settled-decision-invalidated'), and verbatim question text to ask; below 5 because some routing detail is deferred into the referenced files rather than fully specified inline.	4 / 5
Workflow Clarity	Phases are explicitly sequenced (0 -> 1-4 -> 5) with explicit validation/checkpoint language ('STOP. Read...', 'Never classify...'), blocker reporting, and feedback loops (reload reference before acting, re-validate), matching the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview that points to one-level-deep, clearly signaled references (output-mode.md, resume.md, intake.md, etc.), all of which exist as real files; bulk detail lives in those references rather than inlined, matching the clear-overview navigation anchor.	5 / 5
	Total	18 / 20 Passed

Description

83%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 is well-formed: it states concrete capabilities, gives explicit natural-language triggers, covers both what and when, and distinguishes itself from sibling skills. It sits solidly above average, held back from the top only by slightly overlapping action verbs and broad domain framing.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('create structured plans', 'break down implementation', 'plan from requirements', 'deepen an existing plan'), matching the 'lists several specific actions' anchor; not a 5 because the actions are overlapping variations of plan-making rather than comprehensive distinct capabilities.	4 / 5
Completeness	Explicitly answers both what ('Create structured plans for multi-step work, including software and non-software tasks') and when ('Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasings ('asked to plan', 'break down implementation', 'plan from requirements', 'deepen an existing plan') giving good keyword coverage; below 5 because it lacks broader synonym variations of the natural phrases users might say.	4 / 5
Distinctiveness Conflict Risk	Explicitly carves a niche against ce-brainstorm ('WHAT') and ce-work ('HOW/execution'), making it mostly distinct; below 5 because 'planning multi-step work' is still broad enough to risk minor overlap with adjacent planning/framing skills.	4 / 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-plan/SKILL.md
Commit: 082c83e

Reviewed: 3 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.