ce-compound

Document a solved problem as a durable repo learning. Use when verified work produced non-obvious reasoning absent from its final code, tests, or existing docs; avoid routine fixes whose artifacts already explain the lesson.

Quality

73%

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-compound/SKILL.md

Quality

Content

78%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 skill body is a well-structured, procedural overview that pushes detail into clearly signaled, verified one-level-deep references and sequences Full Mode with explicit required reads and validation gates. It is concise and actionable, with only minor tightening opportunities in the mode-detection section.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural, assuming Claude's competence and avoiding re-explanation of known concepts; a few sentences (e.g., the extended mode-detection paragraph) could be tightened, but almost every token earns its place.	4 / 5
Actionability	It gives concrete, executable guidance: explicit invocation tokens, a real bash invocation example, and exact file paths to read per step; minor gaps exist where behavior is stated as rules rather than copy-paste commands.	4 / 5
Workflow Clarity	Full Mode is a clearly numbered six-step sequence with required reads per step, explicit 'done' criteria, and validation checkpoints (frontmatter/claims validation, discoverability consent); a couple of checkpoints are described as rules rather than explicit validate-then-proceed loops, keeping it just below a 5.	4 / 5
Progressive Disclosure	The body is a lean overview that defers all detail to well-signaled one-level-deep references (references/research.md, assembly.md, session-history.md, etc.), each named at the step that needs it; all referenced files exist in references/, and navigation is unambiguous.	5 / 5
	Total	17 / 20 Passed

Description

67%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 clearly answers both what the skill does and when to use it, with a well-scoped eligibility bar that distinguishes it from routine fix documentation. Trigger terms lean toward skill-internal vocabulary rather than natural user phrasing, which is the main weakness.

Suggestions

Add concrete user-facing trigger phrases (e.g., 'Use when the user asks to capture a hard-won lesson, record a non-obvious fix, or save a learning that isn't obvious from the code').

Include natural synonyms users might say, such as 'lessons learned', 'postmortem', or 'captured insight', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Document a solved problem as a durable repo learning') and the qualifying conditions ('verified work produced non-obvious reasoning absent from its final code, tests, or existing docs'), with an explicit avoidance clause; coverage is specific but focused on documentation rather than enumerating multiple actions, leaving minor gaps.	4 / 5
Completeness	It clearly states what ('Document a solved problem as a durable repo learning') and when ('Use when verified work produced non-obvious reasoning...; avoid routine fixes...'), satisfying both halves, though the 'when' could be more explicit with concrete user-facing trigger phrases.	4 / 5
Trigger Term Quality	It contains relevant terms ('solved problem', 'durable repo learning', 'verified work', 'routine fixes') but these are more skill-internal jargon than natural phrases a user would say; common user-side synonyms for capturing learnings are missing.	3 / 5
Distinctiveness Conflict Risk	The qualifying bar ('non-obvious reasoning absent from its final code, tests, or existing docs') carves a clear niche distinct from generic note-taking or refresh skills, with only minor overlap risk with closely related compound-engineering skills.	4 / 5
	Total	15 / 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: 082c83e

Reviewed: 3 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.