bdistill-knowledge-extraction

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bdistill-knowledge-extraction/SKILL.md

Quality

Content

61%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a well-structured overview of the bdistill tool with concrete CLI examples and clear installation steps. Its main weaknesses are the lack of validation/verification checkpoints in the workflow (what happens when things go wrong?) and some unnecessary explanatory text that could be trimmed. The actionability is strong with copy-paste ready commands, though some command contexts (slash commands vs CLI) could be clearer.

Suggestions

Add validation checkpoints: after installation verify with `bdistill --version`, after extraction show how to check quality scores and handle low-quality entries, and after export verify the output file.

Trim the 'When to Use This Skill' section and security notes — Claude doesn't need to be told when to use a tool in this much detail; a single line would suffice.

Clarify the invocation context for /distill and /schema commands — are these MCP tool calls, CLI commands, or chat slash commands? This ambiguity reduces actionability.

Dimension	Reasoning	Score
Conciseness	The overview section explains what bdistill does in a way that's somewhat redundant with the description. The 'When to Use This Skill' section is moderately useful but includes some padding (e.g., explaining what ML models are 'regression, classification — NOT competing LLMs'). The security notes section states obvious things like 'no data is sent to external services' for local execution. Overall mostly efficient but could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste ready commands for installation, extraction, search, and export. The CLI examples are specific and executable. Minor gaps: the /distill commands appear to be slash commands but it's unclear exactly how they're invoked (MCP tool calls vs CLI vs chat commands), and the /schema command lacks full context on how to use the output.	4 / 5
Workflow Clarity	The three-step workflow (Install → Extract → Search/Export) is clearly sequenced and easy to follow. However, there are no validation checkpoints — no guidance on what to do if installation fails, if extraction produces low-quality results, or how to verify the knowledge base is correctly populated. For a tool that involves batch knowledge extraction, some validation steps would be expected.	3 / 5
Progressive Disclosure	The content is well-structured with clear sections covering different use cases (in-session, local, tabular ML). The skill references a related skill (@bdistill-behavioral-xray). However, there are no bundle files and no references to deeper documentation for advanced usage, configuration options, or troubleshooting. For a skill of this length (~80 lines), the structure is appropriate but could benefit from pointing to more detailed references.	4 / 5
	Total	14 / 20 Passed

Description

53%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 identifies a reasonably specific niche—extracting structured knowledge from AI models using Ollama—but lacks a 'Use when...' clause that would help Claude know when to select it. The trigger terms are somewhat technical and may not match how users naturally phrase their requests. The 'No API key needed' detail is helpful for differentiation but doesn't compensate for the missing usage triggers.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user wants to extract or distill expert knowledge from language models, or mentions Ollama, local LLMs, or knowledge distillation.'

Include more natural synonyms and user-facing terms such as 'LLM', 'local model', 'knowledge distillation', 'expert knowledge', 'model querying' to improve trigger term coverage.

Specify the concrete outputs or actions more clearly, e.g., 'Generates structured JSON/YAML knowledge bases by querying AI models with targeted prompts.'

Dimension	Reasoning	Score
Specificity	Names the domain (extracting domain knowledge from AI models) and mentions a concrete mechanism (Ollama for local open-source models), but the core action 'extract structured domain knowledge' is somewhat vague—it doesn't specify what form the output takes or what concrete steps are involved.	3 / 5
Completeness	The 'what' is present (extract structured domain knowledge from AI models via Ollama), but there is no explicit 'when' clause. The description lacks a 'Use when...' trigger phrase, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes some relevant keywords like 'Ollama', 'domain knowledge', 'open-source models', and 'structured', but misses many natural user phrases like 'knowledge extraction', 'LLM', 'local model', 'distill knowledge', or 'expert knowledge'. Users might not naturally say 'extract structured domain knowledge'.	3 / 5
Distinctiveness Conflict Risk	The combination of 'structured domain knowledge extraction' and 'Ollama' is fairly distinctive and unlikely to overlap with most other skills. However, it could potentially conflict with general AI/LLM interaction skills or knowledge management skills, creating minor overlap risk.	4 / 5
	Total	13 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/bdistill-knowledge-extraction/SKILL.md
Commit: fbdfd63

Reviewed: about 18 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.