CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gpt-image-2-5

Generate and edit images with OpenAI GPT Image 2.5 (Sunburst for quality, Flare for speed) via the PopNow API: clean typography, logos, UI mockups and photoreal edits up to 4K with exact USD quotes first. Use when the user asks for GPT Image, ChatGPT-style image generation or an OpenAI image edit.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

Highly actionable content: complete executable commands, a well-sequenced paid-operation workflow with explicit approval and retry safety, and proper separation of instructions from bundled helper code. Only minor conciseness trims (license paragraph, link list) keep it from full marks.

DimensionReasoningScore

Conciseness

The body is lean and operational — a model table, prompt tips, exact commands, and policy constraints — with almost all content being PopNow-specific knowledge Claude would not already have. Minor trims are possible (the license/trademark closing paragraph and the consolidated links line), matching the 4 anchor 'efficient; minor instances that could be trimmed' rather than the 5 anchor's every-token-earns-its-place.

4 / 5

Actionability

Every workflow step gives a copy-paste-ready command with all required flags ('--quote-id', '--approved-max-usd', '--idempotency-key', '--task-id'), plus a fully concrete executable example ('python3 scripts/popnow.py models --search "gpt image 2.5"'). Placeholders like <exact-model-path> are appropriate since step 1 mandates fetching them from the schema, matching the 5 anchor.

5 / 5

Workflow Clarity

The four-step sequence has explicit validation checkpoints and feedback loops: the quote-approval gate ('wait for an explicit yes ... a zero-price quote still needs approval'), fresh-quote-and-reapproval on expiry or price change, retry-only-with-same-idempotency-key after timeout, and explicit error handling for auth and balance failures ('pending is not failure'). This matches the 5 anchor's clear sequence with explicit validation and error-recovery guidance.

5 / 5

Progressive Disclosure

The SKILL.md is a well-organized overview with clear sections, and implementation code is appropriately externalized to the real, verified bundle files scripts/popnow.py and scripts/client.py rather than inlined. No content that belongs in a separate file is inlined and there are no nested references, matching the 5 anchor for a compact skill whose details live in scripts.

5 / 5

Total

19

/

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 description: concrete capabilities with variant and output detail, an explicit 'Use when' trigger clause, and third-person imperative voice. The only weakness is keyword coverage that omits a few natural synonyms, and slight overlap risk with sibling OpenAI image-generation skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Generate and edit images', 'clean typography, logos, UI mockups and photoreal edits up to 4K', 'exact USD quotes first' — with capability detail (both Sunburst and Flare variants and their tradeoffs). Coverage is comprehensive for the domain, matching the 5 anchor rather than 4, which expects minor gaps.

5 / 5

Completeness

It clearly answers both questions: the 'what' ('Generate and edit images ... via the PopNow API ... with exact USD quotes first') and an explicit 'Use when the user asks for GPT Image, ChatGPT-style image generation or an OpenAI image edit' with concrete trigger phrases. This matches the 5 anchor; the 4 anchor applies only when the 'when' is less explicit.

5 / 5

Trigger Term Quality

'GPT Image', 'ChatGPT-style image generation' and 'OpenAI image edit' are phrases users would naturally say, giving good keyword coverage. A few natural variations are missing (e.g., 'text-to-image', 'AI image generation', 'picture'), so it fits the 4 anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — OpenAI GPT Image 2.5 with named variants via a specific API — so it is mostly distinct. However triggers like 'ChatGPT-style image generation' and 'OpenAI image edit' carry minor overlap risk with closely related OpenAI image skills, matching the 4 anchor rather than the minimal-conflict 5.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

popnow-ai/popnow-skills

Path

skills/popnow-gpt-image-2-5/SKILL.md

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.