code-review-context

Model visible context

Quality

36%

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

72%

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 concise, well-organized set of hard constraints on context management that assumes competence and stays within budget. Its main weakness is actionability and workflow rigor: it states rules and identifies the relevant trait/location but never shows how to implement or validate them.

Suggestions

Add a minimal executable example of a `ContextualUserFragment` struct in `core/context` so item 6 is copy-paste ready instead of a directive.

Turn item 5's "additional manual review" into an explicit validation step, e.g. a check command or checklist that flags fragments crossing 1k tokens, to give the risky context-injection operation a feedback loop.

Clarify whether the numbered items are ordered workflow steps or independent invariants; if a process, add explicit sequence and validation checkpoints, otherwise relabel them as invariants.

Dimension	Reasoning	Score
Conciseness	The body is a lean six-rule list with a one-line framing sentence and no padding or explanation of concepts Claude already knows, matching the score-3 anchor "Lean and efficient; assumes Claude's competence; every token earns its place". It is not a 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	It gives some concrete specifics (10K and >1k token caps, the `core/context` location, the `ContextualUserFragment` trait) but no executable struct definition or trait-implementation example, matching the score-2 anchor for incomplete guidance with missing key details. It is above 1 because real concrete numbers and identifiers are present, but below 3 because nothing is copy-paste ready.	2 / 3
Workflow Clarity	The numbered rules read as a sequenced list but are constraints rather than a process, and the only checkpoint is item 5's "additional manual review", matching the score-2 anchor "Steps listed but validation gaps; checkpoints missing or implicit". It is not 3 because context injection is a risky/batch operation with no validate-fix-retry feedback loop.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized as a clean intro-plus-numbered list, which the rubric's simple-skills note allows to score 3. It is not a 2 because no content is mis-inline and no deep reference nesting exists.	3 / 3
	Total	10 / 12 Passed

Description

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 terse, abstract noun fragment that fails to convey what the skill does or when to use it, scoring the minimum across every dimension. It reads as a working placeholder rather than a discoverable trigger.

Suggestions

Rewrite as a third-person action sentence naming concrete capabilities, e.g. "Reviews and constrains Codex's model-visible context to keep it bounded, incremental, and cache-friendly."

Add an explicit "Use when..." trigger clause listing natural terms users would say, such as "when modifying context injection, adding model context fragments, or auditing context size".

Replace the generic phrase "Model visible context" with domain-specific keywords (context fragments, ContextualUserFragment, token caps, cache misses) to reduce conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description "Model visible context" names no concrete actions at all, matching the score-1 anchor "Vague or no actions; abstract language". It cannot reach 2 because it does not name a domain or any actions.	1 / 3
Completeness	Both the "what" and the "when" are missing or extremely weak, matching the score-1 anchor and the guideline capping completeness at 2 when no "Use when..." trigger exists. A 2 would require an explicit what statement, which is absent.	1 / 3
Trigger Term Quality	No natural keywords a user would say appear; "Model visible context" is technical jargon with no common phrasings, matching the score-1 anchor. It is not a 2 because there are no relevant natural-language variations present.	1 / 3
Distinctiveness Conflict Risk	"Model visible context" is so generic it would overlap with many skills, matching the score-1 anchor "Very generic; would conflict with many skills". It is not a 2 because nothing scopes it to a distinct niche.	1 / 3
	Total	4 / 12 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: openinterpreter/openinterpreter
Path: .codex/skills/code-review-context/SKILL.md
Commit: a4da0fc

Reviewed: 2 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.