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

80%

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

The canonical home for this skill is ce-work in EveryInc/compound-engineering-plugin

Quality

Content

77%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 well-structured orchestration skill: the phase workflow is unambiguous with real validation gates and failure paths, and progressive disclosure is exemplary — every reference named in the body exists and is loaded at a defined point. The main cost is redundancy: the same prohibitions and Return-to-Caller rules are restated several times, inflating token load without adding guidance.

Suggestions

State each Return-to-Caller prohibition once in its dedicated section and reference it from Phase 0/Phase 1 instead of repeating the rules three times.

Consolidate the repeated 'never glob / never guess / do not reconstruct' enforcement phrasing into a single bundled-references rule stated once in the Execution Workflow preamble.

Add one short example of a route decision or a minimal blocked-result JSON snippet to make the outcome contracts copy-paste concrete.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining known concepts, but enforcement language repeats across sections — Return-to-Caller rules appear in Phase 0, Phase 1, and a dedicated section, and 'never glob / never guess / do not reconstruct' phrasings recur — so it could be meaningfully tightened.	3 / 5
Actionability	Guidance is concrete for an instruction-only skill: exact reference paths per phase, exact blocked-result fields (status: blocked, plan_path, run_id, changed_state, blockers, recovery_path), and the specific 'bare git commit is forbidden' rule, though there is no copy-paste example of a route decision or result payload.	4 / 5
Workflow Clarity	Phases 0 through 3-4 are clearly sequenced with explicit gating ('Before the first implementation write... read'), a hard code-review completion gate, and explicit blocked/recovery fallback paths that function as feedback loops.	5 / 5
Progressive Disclosure	The body is a lean overview that routes to well-signaled, one-level-deep references at the exact phase each governs; all referenced bundle files exist, and the remaining bundle files are reachable one level deep from those references.	5 / 5
	Total	17 / 20 Passed

Description

82%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 strong description that clearly states what the skill does and when to use it, with explicit boundary routing to a sibling debug skill and a distinct orchestrator mode. Its only weakness is that the capability statement is a single high-level action rather than a list of concrete capabilities.

Suggestions

Enumerate 2-3 concrete actions in the 'what' clause (e.g. 'implement tasks from a plan, run local verification, record evidence') to raise specificity.

Add a few more natural trigger variations users would say, such as 'execute this plan', 'specification', or 'implement this build', to broaden keyword coverage.

Consider naming the file types or inputs handled (plan documents, spec paths, recovery run ids) more explicitly as trigger terms.

Dimension	Reasoning	Score
Specificity	"Execute a plan or concrete work prompt end-to-end" names the domain with one primary action plus scoping conditions, but does not enumerate several distinct concrete actions as the score-4 anchor requires.	3 / 5
Completeness	It 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 concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "plan document", "spec path", and "build request" are present, but common variations users might say (e.g. "execute the plan", "specification", "implement this build") are missing.	4 / 5
Distinctiveness Conflict Risk	"use ce-debug for open-ended bugs" and the explicit orchestrator-vs-standalone scoping ("without the shipping tail") carve a clear niche with minimal overlap risk.	5 / 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: crdant/compound-engineering-plugin
Path: skills/ce-work/SKILL.md
Commit: f794948

Reviewed: 2 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.