CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flux-2

Generate and edit photoreal images with Black Forest Labs FLUX.2 (Max, Pro, Flex, Dev) and FLUX 3 Klein through the PopNow API, including LoRA variants and exact brand colors. Exact USD quotes before any charge. Use when the user asks for FLUX, Black Forest Labs, photorealism or LoRA image generation.

Quality

88%

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

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 delivers an executable, well-sequenced workflow with strong safety checkpoints around paid generation, and the bundle layout keeps helper code properly separated. The main gaps are the absence of a sample input_json and a small amount of repetition and marketing-flavored filler.

Suggestions

Add a minimal example input_json object (e.g., a text-to-image payload with prompt and hex color) so the quote step is fully copy-paste ready on first use.

State the separate-API-balance rule once (in "Setup and cost") and drop the repetition in "Data and limits" to save tokens.

Trim the marketing-style opener about what FLUX is "known for" and keep only the model-choice guidance that affects decisions.

DimensionReasoningScore

Conciseness

The body is efficient and PopNow-specific with no generic concept explanations, but the opener "FLUX from Black Forest Labs is known for photoreal light, skin and materials" and the website-credits billing note (stated in "Setup and cost" and repeated in "Data and limits") are minor over-explanations that could be trimmed.

4 / 5

Actionability

Every workflow step has a concrete, verified command (scripts/popnow.py models/quote/create/status all exist in the bundle) plus specific approval and idempotency-key semantics, but no example input_json payload is shown, leaving a minor gap for building the first request.

4 / 5

Workflow Clarity

The four-step sequence (confirm schema → quote → explicit approval → create → status) includes explicit validation checkpoints: user approval of the exact max USD cost before any charge, retry only with the same idempotency key after timeout, "pending is not failure", and terminal error handling for auth and balance failures.

5 / 5

Progressive Disclosure

The body is a clean, well-sectioned overview whose only bundle dependency is the helper script scripts/popnow.py (verified present with the documented subcommands); nothing that belongs in a separate reference file is inlined, and navigation via section headers is easy.

5 / 5

Total

18

/

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 that clearly and concretely states both capabilities and trigger conditions in third person. Keyword coverage is good but could add natural synonyms, and the broader terms like "photorealism" slightly raise overlap risk with other image-generation skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — "Generate and edit photoreal images", "LoRA variants and exact brand colors", "Exact USD quotes before any charge" — covering generation, editing, variants, color control, and cost quoting comprehensively.

5 / 5

Completeness

It explicitly answers both what ("Generate and edit photoreal images with... FLUX.2... and FLUX 3 Klein through the PopNow API") and when ("Use when the user asks for FLUX, Black Forest Labs, photorealism or LoRA image generation") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use when the user asks for FLUX, Black Forest Labs, photorealism or LoRA image generation" gives good natural keyword coverage, but misses common phrasings users would say such as "photorealistic image", "generate an image", or model-name variants like "FLUX.2 Max".

4 / 5

Distinctiveness Conflict Risk

The FLUX/Black Forest Labs/PopNow niche is clearly distinct, but the triggers "photorealism" and "LoRA image generation" are broad enough to overlap with other generic image-generation skills, creating minor conflict risk.

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-flux-2/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.