cm-imagegen

Generate or edit raster images through CodexManager's OpenAI-compatible Images API when Codex should use the current Codex provider base_url and auth.json API key instead of the official built-in image_gen tool. Use when the user asks for CodexManager image generation, API-key/provider-mode image generation, or image generation through CodexManager account pools, routing, logs, and billing.

Quality

86%

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

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 body is highly actionable and well-structured, with a clear validated workflow and clean one-level-deep progressive disclosure to real reference files. The main weakness is redundant output-reporting guidance repeated across the Workflow and Commands sections.

Suggestions

Consolidate the output-reporting rules: the 'After a successful call' bullets duplicate workflow steps 11 and 14 — keep one canonical location and cross-reference it instead of restating.

Remove the repeated 'attach/report the generated PNG file from generated-images/' instruction (it appears in the intro, workflow, and Commands sections) to a single statement.

Tighten overlap between 'Prompt augmentation', 'Prompting best practices', and references/prompting.md by summarizing the in-body sections and deferring detail to the reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and operational, but output-reporting guidance is duplicated: the 'After a successful call' block restates workflow steps 11 and 14, and 'attach the generated PNG file from generated-images/' appears three or more times, so it could be tightened.	3 / 5
Actionability	Provides copy-paste ready commands ('python …cm_image_gen.py generate --prompt', 'edit --image … --prompt …'), a concrete options list, a labeled prompt schema, and worked generate/edit examples covering the common cases.	5 / 5
Workflow Clarity	A 14-step workflow is clearly sequenced with an explicit validation checkpoint (step 9: inspect and validate subject/style/composition/text/invariants), a feedback loop (step 10: iterate one change, re-check), and batch handling (step 13), so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized sections plus a one-level-deep reference map pointing to real files (references/prompting.md, sample-prompts.md, cli.md, image-api.md, codex-network.md, scripts/cm_image_gen.py), making navigation easy with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it names concrete actions, an explicit execution mechanism, and clear 'Use when' triggers tied to a well-defined niche, while contrasting itself with the competing official tool. The only weakness is slightly less exhaustive trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists concrete actions 'Generate or edit raster images' plus the specific execution mechanism (CodexManager OpenAI-compatible Images API, provider base_url, auth.json), with only minor coverage gaps relative to the full edit/generate surface.	4 / 5
Completeness	Explicitly answers both what ('Generate or edit raster images through CodexManager's OpenAI-compatible Images API…') and when ('Use when the user asks for CodexManager image generation…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases like 'CodexManager image generation', 'API-key/provider-mode image generation', and 'account pools, routing, logs, and billing', giving good keyword coverage though a few synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CodexManager provider-mode image generation) and actively distinguishes itself from the official built-in image_gen tool, minimizing conflict risk.	5 / 5
	Total	18 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: qxcnm/Codex-Manager
Path: cm-skills/cm-imagegen/SKILL.md
Commit: a4805dd

Reviewed: 3 hours 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.