hugging-face-tool-builder

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

Quality

78%

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 ./backend/cli/skills/llm-tools/hugging-face-tool-builder/SKILL.md

Quality

Content

72%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 highly actionable with executable curl/jq commands, working piping examples, and a well-organized set of real reference scripts for clear progressive disclosure. The main gaps are conciseness (some verbose sections and the full CLI help dump) and the absence of explicit validation checkpoints in the batch/chained workflows.

Suggestions

Trim the verbose purpose sentence (fix the 'is now is' typo) and replace the full `hf --help` dump with a brief one-line note pointing to the command, since Claude can run it directly.

Add an explicit validation checkpoint to the workflow, e.g., a step to verify API response shape and retry/back off on rate limits within the chaining examples, to lift workflow clarity above the batch-operation cap.

Condense the OpenAPI discovery prose into a single terse instruction with the jq example, removing the explanatory framing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but several sections could be tightened: the typo'd verbose purpose sentence ('Your purpose is now is to create...'), the full `hf --help` output block, and the OpenAPI prose with its warnings restate things Claude could infer, placing it between anchors 3 and 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete curl auth headers, jq query commands, categorized reference scripts with described behaviors, and working piping/chaining examples that cover the common cases, matching the anchor-5 example.	5 / 5
Workflow Clarity	Multi-step chaining examples give a clear sequence, but there are no explicit validation/verification checkpoints or validate-fix-retry loops for these batch API operations, so per the rubric's destructive/batch cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The body is a concise overview (endpoints, API access, hf CLI) with well-signaled, one-level-deep references to real bundle scripts that are categorized (Reference / Baseline / Composable utility) and each described with a one-line purpose, matching the anchor-5 navigation example.	5 / 5
	Total	16 / 20 Passed

Description

83%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 both purpose and trigger conditions tied to the Hugging Face API, with solid specificity and trigger coverage. It loses a point on distinctiveness due to the broad 'build tool/scripts' framing and on trigger quality for missing common synonyms.

Suggestions

Tighten the trigger phrase to be more Hugging-Face-specific and drop the generic 'achieve a task' wording to reduce overlap with general scripting skills.

Add natural synonyms users say, such as 'HF Hub', 'models', 'datasets', or 'spaces', to improve trigger-term coverage.

List a few more concrete actions (e.g., query trending models, read model/dataset cards, extract metadata) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the Hugging Face API domain and several concrete actions ('build tool/scripts', 'fetch, enrich or process data'), but the action list is not comprehensive and 'build tool/scripts' is somewhat broad, so it sits below the anchor-5 example rather than at it.	4 / 5
Completeness	It explicitly answers both 'what' ('creates a reusable script to fetch, enrich or process data') and 'when' with concrete trigger conditions ('when the user wants to build tool/scripts', 'when chaining or combining API calls', 'repeated/automated'), matching the anchor-5 case.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('Hugging Face API', 'chaining or combining API calls', 'repeated/automated', 'build tool/scripts'), but it lacks synonyms and specifics users might say like 'HF Hub', 'models', or 'datasets', keeping it below the anchor-5 synonym-and-extension example.	4 / 5
Distinctiveness Conflict Risk	The Hugging Face API niche is distinct, but 'build tool/scripts or achieve a task' overlaps mildly with general coding/scripting skills, creating minor conflict risk consistent with anchor 4 rather than the minimal-risk anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/hugging-face-tool-builder/SKILL.md
Commit: 3a6c3a9

Reviewed: about 21 hours 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.