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. Use when an outer orchestrator needs implementation and local verification only, without the shipping tail.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-work/SKILL.md

Quality

Content

63%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 disciplined, well-structured orchestration skill that sequences phases with explicit gates and delegates detail to a real, one-level-deep reference bundle. Its weakness is actionability — the kernel reads as routing prose with little inline executable content — and some repeated fail-closed language inflates token use.

Suggestions

Consolidate the fail-closed reference-loading protocol into one stated rule instead of restating it in each phase to recover tokens without losing the gate.

Add a short inline example of the structured return envelope or a minimal worker dispatch packet so the executable surface is visible without opening a reference.

Inline one concrete command per phase (e.g. the exact commit path-limit flag or validation invocation) so the kernel is actionable on its own for the common path.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's intelligence, but the fail-closed reference-loading protocol is restated across nearly every phase and several guard clauses repeat, which could be tightened without losing meaning.	3 / 5
Actionability	Gives concrete per-phase reads ('read references/workspace-setup.md', path-limited commits) but the executable surface is mostly pointers to other files rather than copy-paste commands or code; key steps live behind the references.	3 / 5
Workflow Clarity	A clear Phase 0→3-4 sequence with explicit checkpoints (engine-before-write gate, WIP/write gate, code-review completion gate) and error-recovery semantics, with only minor validation gaps inside the referenced owners.	4 / 5
Progressive Disclosure	The body is a tight overview with well-signaled one-level-deep references, every named reference file exists in references/, and detail is appropriately split out rather than inlined.	5 / 5
	Total	15 / 20 Passed

Description

78%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 well-constructed description that explicitly states both what it does and when to use it, and actively disambiguates from sibling skills. It is slightly stronger on triggers and completeness than on action specificity, which stays at the routing level.

Dimension	Reasoning	Score
Specificity	Names the domain ('Execute a plan or concrete work prompt end-to-end') and a couple of concrete actions (implement, locally verify) but the action set is not comprehensive — most detail is deferred to routing phrases.	3 / 5
Completeness	Clearly answers what ('Execute a plan or concrete work prompt end-to-end') and provides two explicit 'Use when...' clauses with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural trigger terms ('plan document', 'spec path', 'clear build request', 'outer orchestrator') though it leans on internal jargon and omits some plain synonyms.	4 / 5
Distinctiveness Conflict Risk	Distinguishes itself from ce-debug ('use ce-debug for open-ended bugs') and the shipping tail, carving a clear niche with minor residual overlap with adjacent ce-* skills.	4 / 5
	Total	16 / 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-work/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.