Name: hugging-face-tool-builder
Rating: 52.8 (1 reviews)
Author: administrakt0r

hugging-face-tool-builder

Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. You can access the API directly, as well as use the hf command line tool.

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-tool-builder/SKILL.md

The canonical home for this skill is hugging-face-tool-builder in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

61%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 actionable and well-structured with concrete curl/jq commands and clearly signaled reference scripts, but it repeats the description verbatim, dumps reference material inline, and lacks an explicit sequenced workflow with validation checkpoints. Tightening the duplication and adding a validate-then-hand-off loop would lift the weakest dimensions.

Suggestions

Remove the verbatim repeat of the description as the opening paragraph; the frontmatter already carries it.

Add an explicit script-building workflow with a validation checkpoint, e.g. '1. Probe endpoint shape with low limits → 2. Draft script with --help → 3. Test non-destructively → 4. Hand off with usage examples.'

Move the full `hf --help` command listing and endpoint table into a reference file, keeping only the most-used items inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (commands and examples, no concept explanations), but the opening paragraph repeats the frontmatter description verbatim and the full `hf --help` dump plus endpoint list could be tightened, matching the 3 anchor; below 4 due to noticeable padding.	3 / 5
Actionability	Provides concrete executable commands — `curl -H "Authorization: Bearer ${HF_TOKEN}"`, `jq` query examples, and piping recipes — with only minor gaps, fitting 4; not 5 because the piping examples depend on referenced scripts rather than being fully self-contained copy-paste.	4 / 5
Workflow Clarity	Script Rules is a checklist rather than a sequenced workflow, and validation is only implicit ('Non-destructive scripts should be tested'); since the skill produces batch/piped scripts, the missing explicit validation checkpoints cap this at 3.	3 / 5
Progressive Disclosure	Well-signaled one-level-deep `references/*.sh` entries each carry a one-line description, and sections are clearly organized; held at 4 rather than 5 because the inline endpoint list and full `hf --help` output are reference material that could live in a separate file.	4 / 5
	Total	14 / 20 Passed

Description

58%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 clearly conveys what the skill does with several concrete actions and a distinct HF niche, but it lacks an explicit 'Use when...' trigger clause and has limited keyword variation. A grammar slip ('Your purpose is now is to create') slightly undermines polish without changing the score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building CLI scripts or utilities for the Hugging Face API, or when the user mentions HF, model/dataset cards, or the `hf` CLI.'

Expand natural trigger terms with synonyms users say — 'Hugging Face', 'HF Hub', 'model cards', 'dataset cards', 'hf CLI'.

Fix the duplicated/broken wording 'Your purpose is now is to create' to a clean third-person statement.

Dimension	Reasoning	Score
Specificity	Names the Hugging Face domain and several concrete actions — 'create reusable command line scripts and utilities', 'chaining, piping and intermediate processing', and 'use the `hf` command line tool' — with only minor coverage gaps, fitting the 4 anchor better than the 3 (more than 1-2 actions) or 5 (not fully comprehensive).	4 / 5
Completeness	Provides a clear 'what' but no explicit 'Use when...' trigger clause, so per the guideline completeness is capped at 3; a 4 would require an explicit (if imperfect) when-clause.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('Hugging Face API', 'hf command line tool') but lacks common variations or synonyms, matching the 3 anchor; it is above 2 (more than one generic keyword) but below 4 (missing several natural phrases).	3 / 5
Distinctiveness Conflict Risk	Targets a clear Hugging Face niche with distinct triggers, with only minor overlap risk against general scripting skills, fitting 4 rather than 5 (not maximal separation) or 3 (more distinct than 'somewhat specific').	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-tool-builder/SKILL.md
Commit: 57c135b

Reviewed: 4 days 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.