CtrlK
BlogDocsLog inGet started
Tessl Logo

flux-best-practices

Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/flux-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a tight, well-organized overview with concrete prompt guidance and a clear one-level-deep reference structure, but it loses points for missing referenced bundle files and minor verbosity.

Suggestions

Ensure the referenced bundle files (rules/*.md, AGENTS.md) exist alongside SKILL.md so the progressive-disclosure links resolve.

Tighten the "Extended reference" blockquote and trim the "When to Use" list to avoid restating the frontmatter description.

Consider adding a short validation/preview step (e.g., "Verify the prompt covers Subject, Lighting, and Camera fields before generating") to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

Mostly lean — prompt formula, model table, critical rules, and an example with no padding of basic concepts; minor trimming possible in the "Extended reference" blockquote and the "When to Use" list which partly restate the description.

4 / 5

Actionability

Provides a concrete prompt structure formula, a use-case→model decision table, six critical rules, and a full example prompt — actionable guidance with minor gaps since the deepest specifics live in referenced rules files.

4 / 5

Workflow Clarity

The flow (identify use case → pick model via table → apply formula → follow rules) is clear and unambiguous for a single-purpose prompting skill, though it is not a multi-step workflow with explicit validation checkpoints.

4 / 5

Progressive Disclosure

Well-structured overview with a clearly signaled one-level-deep "Rules Reference" index and pointers to AGENTS.md and the bfl-api skill; docked one point because the referenced rules/*.md and AGENTS.md files are not actually present in the bundle.

4 / 5

Total

16

/

20

Passed

Description

75%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 specific and well-scoped to FLUX models with concrete capabilities and strong trigger terms, but it lacks an explicit "Use when..." trigger clause, which caps completeness at 3.

Suggestions

Add an explicit "Use when..." clause naming natural trigger phrases (e.g., "Use when generating images with BFL FLUX models, or when the user mentions FLUX, FLUX.2, FLUX.1, text-to-image, or image editing").

Spell out common synonyms/acronyms like "text-to-image" and "image-to-image" alongside T2I/I2I to broaden natural trigger coverage.

Consider mentioning file or output contexts (e.g., "image generation prompts") to round out keyword variations.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing" — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Has a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance; per the guidelines this caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural keywords ("FLUX image generation", "prompting", "T2I", "I2I", "hex colors", "typography", "FLUX.2/FLUX.1"), but missing common variations/synonyms like "AI images" or "text-to-image" spelled out.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to BFL FLUX models with specific family names (FLUX.2, FLUX.1), giving a distinct niche with minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 12 missing

Warning

Total

15

/

16

Passed

Repository
calesthio/OpenMontage
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.