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

92%

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 1-3

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

A dense, highly actionable, well-sequenced orchestrator with strong progressive disclosure and validation checkpoints. Its one weakness is conciseness: several governing rules (pipeline-mode output, the completion/handoff contract, the post-generation menu) are restated across multiple phases and could be consolidated.

Suggestions

Consolidate the repeated pipeline-forces-OUTPUT_FORMAT=md rule: state it once in Phase 0.0 and have later phases reference it instead of re-deriving it in 0.1, 5.2, and 5.3.8.

Merge the Mandatory Completion Contract, the Phase 5.4 menu rules, and the final pre-response checklist into a single canonical handoff/contract section, with later phases pointing back rather than restating.

Tighten the Phase 5.4 menu block: the option list, platform caps, routing, and cross-skill invocation rule overlap across several paragraphs and could be expressed once with the per-platform variants as a compact table.

Dimension	Reasoning	Score
Conciseness	The body is accurate but padded: the pipeline-forces-md rule, the Phase 5.4 handoff contract, and the completion/menu rules are restated in the Mandatory Completion Contract, Phase 0.0/0.1/5.2, Phase 5.4, and the final pre-response checklist, which is tighter-able repetition rather than novel content.	2 / 3
Actionability	Provides exact executable guidance throughout — `git rev-parse --show-toplevel`, concrete config keys (`plan_output:`, `docs_root`), literal handoff wording, and precise menu options with routing — well above the pseudocode/incomplete anchor.	3 / 3
Workflow Clarity	Sequenced phases 0.0–5.4 with explicit validation gates ("REQUIRED: Write the plan file to disk before presenting any options", "STOP. Load references/plan-handoff.md now", the load-bearing HTD presence audit, and the final pre-response checklist) give clear feedback loops and checklists.	3 / 3
Progressive Disclosure	The body is an orchestrating overview that points one level deep to real, clearly-signaled reference files (plan-sections, plan-handoff, deepening-workflow, synthesis-summary, and the agents/*.md prompts, all verified to exist), keeping detailed mechanics out of SKILL.md.	3 / 3
	Total	11 / 12 Passed

Description

100%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.

The description is concise, concrete, and complete: it names several specific actions, gives explicit "Use when..." triggers, and distinguishes itself from the related brainstorm skill. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create structured plans", "break down implementation", "plan from requirements", "deepen an existing plan" — matching the top anchor for enumerating specific capabilities rather than naming only a domain.	3 / 3
Completeness	Explicitly states what it does ("Create structured plans for multi-step work, including software and non-software tasks") and when to use it via a literal "Use when..." clause, satisfying both halves.	3 / 3
Trigger Term Quality	Surfaces natural user phrasings ("plan", "break down implementation", "plan from requirements", "deepen an existing plan") that a user would actually say, giving good coverage beyond jargon.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche (structured implementation plans) and actively distinguishes itself from a sibling with "prefer ce-brainstorm for exploratory framing", lowering conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (833 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-plan/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.