ce-work

Execute a plan or concrete work prompt end-to-end. Use when implementing from a plan document, a spec path, or a clear build request; use ce-debug for open-ended bugs. Standalone use owns the shipping tail; outer orchestrators pass `mode:return-to-caller [implementation_engine:<compact-json>] [implementation_run:<safe-id>] <plan path>` for implementation, recovery, and local verification only.

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 strong orchestration skill: actionable, well-sequenced, with validated checkpoints and clean one-level-deep references to real bundle files. Its main weakness is length and rule repetition across phases, which costs token efficiency without adding clarity.

Suggestions

Consolidate the route-resolution gate description: it is restated in Phase 0, Phase 1 Step 4, and inline — state it once and cross-reference to reduce repetition.

Tighten or move the dense Return-to-Caller envelope field list (a ~20-field spec) into a bundled reference so the SKILL.md body reads as an overview.

Trim the long enumeration of verification_evidence sub-fields inline; the contract is already detailed and could live in references/implementation-result-schema.json.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of generic concept explanations, but it is very long and several passages restate the same rule multiple ways (e.g. route-resolution gate is described in Phase 0, Phase 1 Step 4, and again inline), so it is 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	Provides concrete executable bash snippets (branch detection, git checkout/worktree, commit workflow) and specific decision tables for complexity, strategy, and commit timing — copy-paste ready and unambiguous.	3 / 3
Workflow Clarity	Multi-step phases (0→1→2→3-4) are explicitly sequenced with named stops, mandatory gates ('read references/... before ...'), validation checkpoints, and feedback loops for parallel batches (inspect actual tree, re-validate against advancing canonical tree), matching the top anchor.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep references to real bundled files (execution-engines.md, implementation-loop.md, shipping-workflow.md, cross-model-execution.md, etc., all verified present), with clear 'read X before Y' navigation and no nested-reference chains.	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 specific, trigger-rich, and explicitly answers both what and when, with a built-in disambiguator against ce-debug. Voice is third person and it avoids verbosity despite the dense orchestrator contract; the trailing mode-token syntax is the only mildly dense part but it is factual rather than padded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Execute a plan or concrete work prompt end-to-end', 'implementing from a plan document, a spec path, or a clear build request', plus explicit recovery/verification routing via mode tokens — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Execute a plan or concrete work prompt end-to-end') and when ('Use when implementing from a plan document, a spec path, or a clear build request'), with an explicit 'Use when' clause — the top anchor for completeness.	3 / 3
Trigger Term Quality	Natural trigger terms a user would say — 'implementing from a plan document', 'a spec path', 'a clear build request' — with a clear contrastive pointer ('use ce-debug for open-ended bugs') that disambiguates routing, giving good coverage of natural invocation terms.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (plan/spec/build execution) and explicitly redirects open-ended bugs to 'ce-debug', which materially lowers conflict risk with sibling skills — matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-work/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.