ce-compound

Document a recently solved problem as a durable repo learning. Use when capturing a learning after work.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

92%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.

The body is a well-architected orchestration overview: lean, highly actionable, with an explicit numbered workflow, parallelization guidance, validation/feedback signals, and clean one-level-deep progressive disclosure where every reference resolves to a real bundle file. The only soft spot is the dense Mode Detection paragraph, which could be tightened without losing information.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what a 'learning' or 'frontmatter' is — but the dense Mode Detection paragraph runs long and could be tightened, fitting 'efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place anchor.	4 / 5
Actionability	It gives fully executable guidance — exact tokens (mode:non-interactive, depth:lightweight), the exact failure-report string 'Documentation skipped', the git rev-parse --show-toplevel resolution, and the precise Step ordering — covering the common invocation cases copy-paste ready, which is the top anchor; absence of inline code is fine for an instruction-orchestration skill.	5 / 5
Workflow Clarity	The numbered Full Mode sequence is explicit with a required-read per step, a concrete parallelization instruction ('start it after launching the parallel block so the two overlap'), and parseable terminal validation signals (Documentation complete / Documentation skipped) plus a frontmatter validate→fix→re-run loop referenced in assembly, matching the clear-sequence-with-explicit-validation-and-feedback-loops anchor.	5 / 5
Progressive Disclosure	The SKILL.md is a clear overview that points each step to a well-signaled one-level-deep references/<x>.md, and every referenced file (and the second-level schema.yaml, assets/template, and validator scripts) resolves in the bundle, matching the clear-overview-with-one-level-deep-references anchor.	5 / 5
	Total	19 / 20 Passed

Description

62%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.

The description cleanly states what the skill does and when to use it in third person, but the 'when' trigger is generic and lacks natural synonyms or file-type cues a user would actually say. It is a solid, low-conflict description that stops short of the concrete trigger-phrase coverage of the top anchor.

Suggestions

Sharpen the 'Use when' clause with concrete trigger phrases a user would naturally say, e.g. 'Use when the user says a bug is fixed, a problem is solved, or after successfully resolving and verifying an issue.'

Add a second concrete capability (e.g. grounding claims against the current tree, recording vocabulary) so the 'what' reads as more than a single action.

Optionally include a natural synonym or two ('durable learning', 'solution write-up') to broaden trigger-term coverage without adding jargon.

Dimension	Reasoning	Score
Specificity	Names one concrete action — 'Document a recently solved problem as a durable repo learning' — but offers no second action or broader coverage, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It explicitly answers both what ('Document a recently solved problem as a durable repo learning') and when ('Use when capturing a learning after work'), but the 'when' is generic rather than tied to concrete trigger phrases, fitting the 'both present, when could be more specific' anchor.	4 / 5
Trigger Term Quality	'Use when capturing a learning after work' and 'solved problem' give some relevant keywords, but there are no synonyms, file types, or common natural variations users would actually say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'durable repo learning' rooted in 'a recently solved problem' carves a mostly-distinct niche with only minor overlap risk against generic documentation skills, matching the 'mostly distinct; minor overlap risk' anchor; voice is correctly third-person.	4 / 5
	Total	14 / 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-compound/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.