ce-compound

Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with excellent workflow sequencing, validation feedback loops, and a well-structured one-level-deep bundle; its main weakness is verbosity from repeated rules and motivational/philosophical padding.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational, but at ~786 lines it carries clear padding (the 'Compounding Philosophy' section, the ASCII feedback-loop diagram, 'Why compound?') and restates several rules three times across Usage, phase bodies, and Common Mistakes, so it could be tightened.	2 / 3
Actionability	Provides fully executable bash blocks with existence guards, Python-interpreter resolution, and exit-status handling, plus exact frontmatter/YAML-safety rules and manual fallback checklists scoped to match the validator — copy-paste ready.	3 / 3
Workflow Clarity	Phases are explicitly sequenced with WAIT barriers and dispatch order, and destructive/batch operations have strong validation feedback loops ('fix and re-validate until exit 0', 'Do not declare success while validation fails').	3 / 3
Progressive Disclosure	The 'Support Files' section signals every one-level-deep reference with a read-trigger, all 18 referenced paths verified as real, and content is appropriately split across references/, scripts/, and assets/ with easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is well-formed with an explicit 'Use when' trigger and two named actions, but its trigger-term coverage is narrow and it shares the CONCEPTS.md surface with a sibling skill, creating modest overlap risk.

Suggestions

Broaden natural trigger terms in the description to include user phrasings like 'after a fix lands' or 'that worked' rather than only 'capturing a learning after work'.

Sharpen the distinction from ce-compound-refresh by signaling that this skill captures fresh learnings (not repo-wide concept-map builds or refresh cycles).

Add one more concrete sub-action (e.g., cross-reference against <root>/solutions/) to lift specificity toward a comprehensive action list.

Dimension	Reasoning	Score
Specificity	Names two concrete actions tied to named artifacts ('document a recently solved problem as a durable repo learning', 'capture project vocabulary in CONCEPTS.md'), but they are higher-level rather than a comprehensive granular list like the score-3 'extract text, fill forms, merge' example.	2 / 3
Completeness	Explicitly answers both what ('Document a recently solved problem... or capture project vocabulary in CONCEPTS.md') and when via an explicit 'Use when capturing a learning after work' clause, satisfying the rubric's allowance for a present 'Use when...' trigger.	3 / 3
Trigger Term Quality	Includes relevant phrases ('recently solved problem', 'capturing a learning after work') but misses common user variations such as 'it's fixed' or 'that worked', which only appear in the body's auto_invoke rather than the description.	2 / 3
Distinctiveness Conflict Risk	The primary niche (capturing a fresh learning) is clear, but the CONCEPTS.md and solutions-doc surface is shared with the sibling ce-compound-refresh skill, leaving some overlap risk rather than a fully conflict-free niche.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (787 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-compound/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.