CtrlK
BlogDocsLog inGet started
Tessl Logo

update-codex

Use when updating this codex-app Linux port from the latest upstream Codex Mac DMG, preserving local Linux patches, installing the refreshed desktop app, and publishing the tag-driven Linux release artifacts.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

83%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.

A well-structured, highly actionable workflow with explicit validation checkpoints and copy-paste commands. The main weakness is progressive disclosure: the pet/avatar patch detail is inlined in SKILL.md rather than externalized into a reference file, since no bundle files are provided.

Suggestions

Extract the detailed Linux pet/avatar overlay patch requirements (titlebar, hit-testing, activity-bubble sizing) into a references/ file and link to it from the Contract, keeping only a one-line summary in SKILL.md.

Move the exact preserved-patch bullets out of the Contract and into a dedicated patch-preservation reference so the main file stays a concise overview.

Consider adding a references/ directory with a patch-markers or linux-patches.md file that the verification step can point to, improving navigability of the large patch list.

DimensionReasoningScore

Conciseness

The body is mostly lean — a contract list, numbered workflow with exact commands and paths, and terse notes — assuming Claude's competence without explaining basic concepts; the only mild drag is the dense multi-clause pet/avatar patch prose in the Contract that could be tightened or externalized.

4 / 5

Actionability

Provides copy-paste-ready commands throughout — `desktop/scripts/refresh-recovered-from-dmg.mjs --app-asar <path>`, `node --check`, `npm run test:linux`, `readlink -f`, the tag/push sequence, and exact asset filenames — covering the common cases with executable specifics.

5 / 5

Workflow Clarity

A clearly sequenced six-step workflow with explicit validation checkpoints (step 3 is dedicated patch-preservation tests, step 5 verifies the installed app's version, patch markers, and live `--ozone-platform=x11` process) and feedback guidance in the Notes for error recovery, satisfying the destructive/batch validation requirement.

5 / 5

Progressive Disclosure

No bundle directories (references/scripts/assets) exist, and the body inlines substantial detail — notably the long pet/avatar patch requirements in the Contract — that would naturally belong in a separate reference file; structure is present but a meaningful chunk of content is inlined rather than split out.

3 / 5

Total

17

/

20

Passed

Description

88%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.

A strong, specific description that clearly states what the skill does and when to use it, with concrete actions and a clear trigger clause. Trigger term breadth could be slightly wider with everyday synonyms, but it is otherwise excellent.

DimensionReasoningScore

Specificity

Lists multiple concrete actions verbatim — "updating this codex-app Linux port from the latest upstream Codex Mac DMG", "preserving local Linux patches", "installing the refreshed desktop app", and "publishing the tag-driven Linux release artifacts" — giving comprehensive, specific capability coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both halves: the "what" is the enumerated action chain (update, preserve patches, install, publish) and the "when" is the opening "Use when updating this codex-app Linux port from the latest upstream Codex Mac DMG" trigger clause.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say ("updating", "codex-app Linux port", "publishing", "release artifacts") but lacks common synonyms or variation; the terms are domain-specific rather than the broad everyday keywords the anchor expects, so it sits just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche is highly specific — a single named app's Linux port maintenance with a unique DMG-to-Linux rebuild pipeline — making it extremely unlikely to collide with other skills or trigger for the wrong one.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
am-will/codex-skills
Reviewed

Table of Contents

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.