CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fal-platform

Platform APIs for model management, pricing, and usage tracking

Quality

49%

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 ./skills/fal-platform/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

26%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 stub: it repeats the frontmatter description three times and delegates everything else to an external repository link. Structure is minimally acceptable, but there is no actionable guidance and no workflow for the user to follow — the skill teaches nothing on its own.

Suggestions

Replace the repeated description with executable guidance: concrete API endpoints or CLI commands for the common tasks (list models, fetch pricing for a model, query usage/cost totals).

Add a simple step-by-step workflow for the most common task, e.g. '1. Resolve the model id 2. GET /pricing?model=... 3. Summarize cost per unit', with a validation step (check the response for errors) before presenting numbers.

Move detailed API documentation into bundle files under references/ (e.g. references/pricing.md, references/usage.md) linked one level deep from SKILL.md, instead of pointing users to an external GitHub repository.

DimensionReasoningScore

Conciseness

The body is short and free of concept over-explanation, but it repeats the same description sentence three times across Overview, When to Use, and Instructions — the redundancy is the entire body rather than a minor trim. This falls between 'efficient with minor trims' (4) and 'noticeably verbose padded sections' (2).

3 / 5

Actionability

There is no concrete guidance whatsoever: no API endpoints, no commands, no code, no examples — only 'This skill provides guidance and patterns for platform apis' followed by a link to an external repository. This matches anchor 1 ('only describes rather than instructs') exactly; anchor 2 requires at least high-level directional hints, which are absent.

1 / 5

Workflow Clarity

No sequence of steps exists anywhere in the body — not even a rough one — so anchor 1 ('steps missing or incoherent; no sequence') applies rather than anchor 2 ('rough sequence present'). The simple-skill exception cannot rescue it because there is no single unambiguous action stated at all.

1 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized section headers (Overview, When to Use, Instructions), no bundle files exist, and the only reference is a single clearly-signaled external link — no nested references. However, the Instructions section punts all real content to an external GitHub URL instead of one-level-deep bundle files, a minor organization gap that keeps it below 5.

4 / 5

Total

9

/

20

Passed

Description

50%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 correctly identifies a niche but reads as a topic label rather than a capability statement: it lists areas as noun phrases, has no trigger clause, and omits the product name that would distinguish it. It sits at the middle of the scale across all dimensions.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when the user mentions fal, model pricing, API costs, or usage/billing quotas.'

Convert noun phrases into concrete actions, e.g. 'List available models, fetch per-model pricing, and query usage/cost totals via the fal platform API.'

Include the product name 'fal' and natural synonyms (cost, billing, spend, quota) to improve both trigger quality and distinctiveness from generic API-pricing skills.

DimensionReasoningScore

Specificity

The description names the domain ("Platform APIs") and three functional areas ("model management, pricing, and usage tracking"), but states them as noun phrases rather than concrete actions — closer to 'Processes PDF files and extracts content' than to the multi-action anchor 4/5 examples. It lists areas, not executable capabilities.

3 / 5

Completeness

A 'what' is stated (platform APIs for model management, pricing, usage tracking), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Even the 'what' is weaker than anchor 3's example because it uses noun phrases rather than action verbs, but the when-clause is entirely absent rather than merely weak.

3 / 5

Trigger Term Quality

Some relevant keywords are present ("pricing", "usage tracking", "model management") but common variations users would naturally say are missing — notably the product name "fal", and synonyms like "cost", "billing", "quota", or "API spend". Matches the 'Works with PDF files' anchor: relevant keywords, missing variations.

3 / 5

Distinctiveness Conflict Risk

The scope is narrowed to platform-level operations, but "pricing" and "usage tracking" are generic terms that overlap with other API/billing skills (e.g., LLM API pricing or cloud cost skills), and the description never mentions "fal", which would make it clearly distinct. 'Somewhat specific but could still overlap with similar skills' fits best.

3 / 5

Total

12

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/fal-platform/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.