CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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-engineered orchestration skill body: a clearly phased workflow with explicit stop-conditions and completion gates, and a lean overview that delegates all mechanical detail to real, well-signaled one-level-deep reference files. The only trimmable fat is repetition of the read-before-phase and stop-if-unread meta-rules, and the body itself intentionally contains little copy-paste-ready material.

DimensionReasoningScore

Conciseness

The body is dense and directive with no explanations of concepts Claude already knows, but the reference-reading meta-rule is stated generally in the opening paragraph and then repeated per reference ('If it cannot be read, stop' recurs for input-triage, return-to-caller, and the general case). This is 'efficient; minor instances of over-explanation that could be trimmed' rather than the 5 anchor's every-token-earns-its-place, and well above the 3 anchor's unnecessary explanation.

4 / 5

Actionability

Concrete, executable rules appear throughout — 'A bare `git commit` can absorb the user's pre-existing index, so it is forbidden', exact result fields (`status: blocked`, `plan_path`, `changed_state`, `standalone_shipping_skipped: true`) — but most executable mechanics are delegated to the bundled references, leaving minor gaps in the body itself. For an instruction-only orchestrator this matches 'mostly executable guidance; concrete code or commands with minor gaps' rather than the fully copy-paste-ready 5 anchor.

4 / 5

Workflow Clarity

Phases 0 through 3-4 are explicitly sequenced with validation gates at each transition (stop-before-action on unreadable references, the code-review receipt-or-skip-phrase completion gate, evidence-completeness check before return) and explicit error-recovery paths (blocked result with `recovery_path`, preserving partial state). This matches the top anchor's clear sequence with explicit validation steps and feedback loops; it is clearly above the 4 anchor, which tolerates missing checkpoints.

5 / 5

Progressive Disclosure

The body is a lean overview that routes to eight one-level-deep references, each verified to exist in references/ and each introduced with what it decides ('It decides the source, control tokens, recovery...'). This matches the top anchor — clear overview, well-signaled one-level-deep references, appropriate content split — with no nesting or buried references.

5 / 5

Total

18

/

20

Passed

Description

87%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: concrete, third-person, with explicit 'Use when' triggers covering plan documents, spec paths, and build requests, plus deliberate disambiguation from ce-debug and shipping workflows. The only minor gap is that the action list centers on implement-and-verify rather than a breadth of distinct capabilities.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Execute a plan or concrete work prompt end-to-end', 'implementation and local verification only' — across named input forms ('plan document', 'a spec path', 'a clear build request'). It falls short of the 5 anchor's comprehensive multi-action coverage because the actions revolve around one verb (implement/execute) plus verification rather than a broad distinct-action list, but sits clearly above the 1-2-action coverage of the 3 anchor.

4 / 5

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 concrete trigger phrases, plus an additional when-clause for orchestrators and a negative trigger ('use ce-debug for open-ended bugs'). Third-person voice throughout; clearly matches the top anchor rather than the 4 anchor's 'when could be more explicit'.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present: 'implementing from a plan document', 'a spec path', 'a clear build request'. A few natural variations (e.g. 'execute this plan', 'build this feature') are absent, matching 'good keyword coverage; a few natural terms missing' rather than the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Actively disambiguates from adjacent skills: 'use ce-debug for open-ended bugs' and 'without the shipping tail' / 'implementation and local verification only' separate it from both debugging and shipping skills. This is a clear niche with distinct triggers and minimal conflict risk, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.