ce-optimize

Run metric-driven optimization loops. Use when improving a measurable outcome through experiments.

Quality

73%

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-optimize/SKILL.md

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.

The content is an exemplary progressive-disclosure overview: tightly sequenced phases, explicit validation checkpoints and feedback loops, and concrete scripts/paths, all backed by real reference files. Only minor conciseness trims and a few inline detail gaps keep it from full marks across every dimension.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview that defers detail to references and avoids explaining concepts Claude already knows, with only minor dense passages that could be trimmed; fits 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Concrete executable guidance is present (named scripts like `scripts/decide.mjs`, config paths, exact commands such as `git rev-parse --show-toplevel`), with the full per-step detail appropriately delegated to verified reference files.	4 / 5
Workflow Clarity	Four phases are sequenced with explicit validation checkpoints (CP-0 through CP-5), a write-order discipline ("measure -> write -> verify -> then show"), gates with feedback loops, and resume logic; this batch/destructive-adjacent skill includes the required validation, so no cap applies.	5 / 5
Progressive Disclosure	The overview is concise and points one level deep to clearly signaled reference files (usage-guide, persistence, spec, measurement, loop, wrap-up) and scripts that all exist on disk, with content appropriately split for easy navigation.	5 / 5
	Total	18 / 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 both capability and trigger in third person, with reasonable distinctiveness. Its main weakness is somewhat abstract trigger language and limited enumeration of concrete actions.

Suggestions

Add concrete trigger phrases users would naturally say (e.g. "Use when tuning a metric, running optimization experiments, or iterating on a measurable benchmark").

Enumerate one or two more specific actions (e.g. "build the measurement harness, generate hypotheses, run experiment batches") to lift specificity from 3 toward 4-5.

Include natural synonyms/file references (e.g. ".yaml spec", "benchmark", "tuning") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Run metric-driven optimization loops" names the domain and one concrete action, but does not enumerate several specific actions; matches the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Both the "what" ("Run metric-driven optimization loops") and the "when" ("Use when improving a measurable outcome through experiments") are present, though the trigger phrasing is somewhat abstract rather than concrete.	4 / 5
Trigger Term Quality	Trigger words like "optimization", "measurable outcome", and "experiments" are relevant but lack common natural variations or synonyms a user would say; fits 'some relevant keywords but missing variations'.	3 / 5
Distinctiveness Conflict Risk	"metric-driven optimization loops" carves out a mostly distinct niche with only minor overlap risk against closely related skills; not maximally distinct but clearly differentiated.	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-optimize/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.