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

88%

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

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 SKILL.md body is an exemplar of a lean orchestrator skill: token-efficient, well-sequenced with explicit validation checkpoints, and using clean one-level-deep progressive disclosure to real reference files. The only modest gap is that the executable common-case planning mechanics live in referenced files rather than inline.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with no concept re-explanation or padding; every line is operational ('Read X before Y', 'Do not author until...') and assumes Claude's competence, so each token earns its place.	5 / 5
Actionability	Provides highly concrete executable guidance — exact tokens ('settled-decision-invalidated'), exact status fields, and a verbatim handoff question — but the bulk of executable planning mechanics is intentionally delegated to referenced files rather than covered inline, leaving minor gaps in the body itself.	4 / 5
Workflow Clarity	Phases are clearly sequenced (Phase 0 through Phase 5) with explicit validation checkpoints ('stop before its governed action', 'invalidating evidence... stops the write') and error-recovery feedback loops (blocked status with recovery_path); this is a planning skill so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	The body is a clear orchestration overview pointing one level deep to real, verified reference files, each clearly signaled with its read-order rule; content is appropriately split with easy navigation and no 2+ level nesting reached directly from the body.	5 / 5
	Total	19 / 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 strong: it clearly states the skill's purpose and provides explicit, multi-trigger 'Use when' guidance with active disambiguation against a sibling skill. Its main weakness is moderate breadth and slightly abstract action verbs rather than fully concrete deliverables.

Suggestions

Tighten distinctiveness by naming concrete plan deliverables (e.g., 'implementation plans, breakdown docs, requirement-to-plan conversions') to narrow the niche beyond 'multi-step work'.

Add one or two common synonyms users say (e.g., 'roadmap', 'task breakdown') to lift trigger term coverage toward comprehensive.

Consider stating what ce-plan does NOT do (e.g., 'does not execute or implement') to further reduce overlap with ce-work.

Dimension	Reasoning	Score
Specificity	Lists several concrete planning actions ('create structured plans', 'break down implementation', 'plan from requirements', 'deepen an existing plan') across software and non-software domains, with only minor coverage gaps; not a 5 because the actions stay somewhat abstract about plan deliverables.	4 / 5
Completeness	Explicitly answers both what ('Create structured plans for multi-step work...') and when with a concrete 'Use when' clause listing multiple trigger phrases, matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	Includes natural user phrasings ('asked to plan', 'break down implementation', 'plan from requirements', 'deepen an existing plan') with good coverage; not a 5 because common synonyms like 'roadmap', 'task list', or 'how should I approach' are missing.	4 / 5
Distinctiveness Conflict Risk	Has a clear planning niche and actively disambiguates from a sibling skill ('prefer ce-brainstorm for exploratory framing'); not a 5 because 'multi-step work' and 'non-software tasks' keep it broad enough to risk minor overlap with general task 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: 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.