code-review-context

Model visible context

Quality

30%

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 ./.codex/skills/code-review-context/SKILL.md

Quality

Content

61%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 concise and states concrete, bounded rules with specific thresholds and code locations, but it functions as a constraint checklist rather than executable guidance and lacks a validation/feedback loop for the risky context mutations it governs.

Suggestions

Add a minimal example struct in core/context implementing ContextualUserFragment so the rule is copy-paste actionable rather than abstract.

Insert an explicit validation step (e.g. 'Before merging a context change, confirm item size <=10K tokens and that new >1k items are flagged P0 for review') to create a validate-then-proceed loop.

Group the rules under short section headers (e.g. '## Size bounds', '## Review process') to add structure without length.

Dimension	Reasoning	Score
Conciseness	The body is lean with direct, numbered rules and assumes Claude's competence; the only mild over-explanation is the opening framing sentence 'Codex maintains a context (history of messages) that is sent to the model in inference requests,' which restates a concept Claude already knows.	4 / 5
Actionability	Concrete thresholds (10K tokens, >1k as P0) and a specific path/trait ('structs in core/context', 'ContextualUserFragment trait') provide actionable guidance, but there is no example struct or trait implementation showing how to apply the rules, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The numbered items are constraints rather than a true execution sequence, and while item 5 adds a manual-review checkpoint for P0 items, there is no validate-fix-retry loop for the batch/destructive context changes the rules govern, capping clarity at 3.	3 / 5
Progressive Disclosure	The content is short, single-purpose, and well-organized as a numbered list with no need for external references; it falls just short of 5 because there are no section headers or structural signposting beyond the raw list.	4 / 5
	Total	14 / 20 Passed

Description

0%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 is a two-word fragment that fails to convey what the skill does, when to use it, or how it differs from other skills. It reads as an internal label rather than a discoverability description.

Suggestions

Rewrite as a full third-person sentence stating concrete actions, e.g. 'Reviews proposed model-context changes for Codex, enforcing bounded size, incremental history, and struct-based fragment rules.'

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'adding context items', 'injecting fragments into model context', or 'reviewing context budget'.

Include concrete trigger terms users would actually say (e.g. 'context fragments', 'token budget', 'cache misses') to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	The description 'Model visible context' names no concrete actions and uses only abstract language, matching the 'entirely vague; no concrete actions' anchor.	1 / 5
Completeness	Both 'what' and 'when' are extremely vague and there is no 'Use when...' trigger clause, matching the 'missing both what and when, or both extremely vague' anchor.	1 / 5
Trigger Term Quality	'Model visible context' is technical jargon that no user would naturally say when needing this skill, matching the 'no natural keywords; only technical jargon' anchor.	1 / 5
Distinctiveness Conflict Risk	'Model visible context' is entirely generic and could plausibly apply to virtually any skill involving model context, matching the 'entirely generic; would conflict with virtually any skill' anchor.	1 / 5
	Total	4 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/codex
Path: .codex/skills/code-review-context/SKILL.md
Commit: 78245b4

Reviewed: 5 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.