CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-setup

Check Compound Engineering's tools and repo config and fix what it finds, scaffold a Compound Pack with `pack:<id>`, or draft and refresh coding standards and review docs from pull request history. Use when setting up or diagnosing Compound Engineering, or when creating or updating CODING_STANDARDS.md or REVIEW.md, including on a schedule.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

An orchestration-style SKILL.md that is exceptionally lean and actionable, with clear phase sequencing, an explicit checkout-availability decision tree, and a well-populated one-level reference bundle. The two minor gaps are the absence of an explicit re-validation step after Phase 2 fixes in the body, and some two-level chaining between reference files.

DimensionReasoningScore

Conciseness

The 95-line body is dense operational content with zero padding: it never explains concepts Claude already knows, and even its one explanatory aside ("the Bash tool's CWD is the user's project, not the skill dir, so a bare `scripts/` path will not resolve") exists to prevent a concrete failure mode. This fits the lean-and-efficient anchor rather than the 4 anchor, which requires trimmable over-explanation — none is present.

5 / 5

Actionability

The body provides a copy-paste-ready bash block with a built-in missing-script fallback and explicit version-flag substitution rules, plus exact conditional routing (named reference file, named trigger conditions) for every branch — pack scaffold, review docs, non-interactive, no-writable-checkout. Per the rubric's instruction-skill note, this concrete and specific guidance matches the fully-executable anchor rather than the minor-gaps anchor.

5 / 5

Workflow Clarity

Phases 1-3 are clearly sequenced with a diagnostic validation step (the health check) and an explicit three-way decision tree in Step 3 covering all checkout situations. It falls short of the 5 anchor because the body itself never states a post-fix re-validation loop for the main diagnose→fix path — the fix-then-rerun-check feedback loop appears only inside references/pack-scaffold.md, not in the Phases 1-3 sequence.

4 / 5

Progressive Disclosure

The body is a clear overview routing to well-signaled references (each named with its purpose and read-point), and all referenced paths exist in the bundle (11 references, 3 scripts, 3 assets). It is not the 5 anchor because instructional references chain two levels deep — e.g. SKILL.md → repo-fixes.md → config-refresh.md/project-docs.md, and non-interactive.md → pack-scaffold.md — so a few files are only discoverable through another reference.

4 / 5

Total

18

/

20

Passed

Description

92%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 explicitly states three concrete capabilities with argument syntax and pairs them with an explicit, filename-level 'Use when' clause covering scheduled runs. The only weakness is a handful of natural trigger phrases (e.g. "health check") that appear in the body but not in the trigger clause.

DimensionReasoningScore

Specificity

The description lists three distinct concrete actions — "Check Compound Engineering's tools and repo config and fix what it finds", "scaffold a Compound Pack with `pack:<id>`", and "draft and refresh coding standards and review docs from pull request history" — with concrete argument syntax, matching the comprehensive-coverage anchor. It is not the 4 anchor because no capability from the body's three modes (diagnose/fix, pack scaffold, standards docs) is left uncovered.

5 / 5

Completeness

Both questions are answered explicitly: the 'what' is the three concrete actions, and the 'when' is "Use when setting up or diagnosing Compound Engineering, or when creating or updating CODING_STANDARDS.md or REVIEW.md, including on a schedule" — concrete trigger phrases including filenames. This matches the 5 anchor exactly, not the 4 anchor where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

Good natural-term coverage: "setting up", "diagnosing", "creating or updating", exact filenames (CODING_STANDARDS.md, REVIEW.md), the `pack:<id>` argument, and "including on a schedule". It stops short of the 5 anchor because a few phrases a user would plausibly say — e.g. "health check" or "fix my CE config" — are absent as trigger terms (the checking action is stated but not mirrored in the 'Use when' clause).

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous: "Compound Engineering" is a named product and the trigger files (CODING_STANDARDS.md, REVIEW.md) and `pack:<id>` syntax are specific to it, giving minimal overlap risk with other skills. It clearly fits the clear-niche-with-distinct-triggers anchor.

5 / 5

Total

19

/

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-setup/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.