Name: bdistill-knowledge-extraction
Rating: 56.8 (1 reviews)
Author: administrakt0r

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

64%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/bdistill-knowledge-extraction/SKILL.md

The canonical home for this skill is bdistill-knowledge-extraction in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

76%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 copy-paste-ready commands and clean single-level organization, but its batch extraction workflow lacks any validation or verification checkpoint, capping workflow clarity. Tightening the marketing-flavored overview prose would further improve conciseness.

Suggestions

Add an explicit validation/verification step to the workflow (e.g., how to confirm a /distill entry was stored and quality-scored before exporting) to satisfy the batch-operation feedback-loop requirement and lift workflow clarity above 3.

Trim the Overview's marketing prose ('turns your AI subscription sessions into a compounding knowledge base') and deduplicate it against the When-to-Use section to push conciseness toward 5.

Make the related-skill pointer a real navigable reference or note its availability so progressive-disclosure navigation is fully clear.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, but the Overview contains mildly marketing-flavored prose ('turns your AI subscription sessions into a compounding knowledge base') and slight redundancy with the When-to-Use section, fitting anchor 4's 'minor instances of over-explanation that could be trimmed' rather than the fully lean anchor 5.	4 / 5
Actionability	Copy-paste-ready commands and invocations run throughout (pip install, claude mcp add, /distill presets and flags, bdistill kb subcommands, /schema syntax, ollama pull), covering the common cases fully and matching anchor 5.	5 / 5
Workflow Clarity	Steps 1-3 (Install -> Extract -> Search/export) are clearly sequenced, but this is a batch/extraction operation with no validation or feedback checkpoint (e.g., confirming a /distill entry was stored or verifying export integrity), which per the rubric caps workflow clarity at 3 even though the sequence itself would otherwise be 4.	3 / 5
Progressive Disclosure	Content is well-organized into clear single-level sections with no nested references and only one related-skill pointer; with no bundle files present this is good structure with minor gaps (the related-skill pointer is a bare name, not a navigable link), fitting anchor 4 rather than the idealized reference structure of anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

53%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 states what the skill does and is reasonably specific, but it omits any 'when to use' trigger guidance and relies on technical terms over natural user phrases. Adding an explicit Use-when clause with common trigger phrases would raise completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases (e.g., building lookup tables, Q&A datasets, research corpora, cross-model knowledge comparison) so users and Claude know when to invoke it.

Broaden specificity by listing more concrete actions beyond extraction (structure, quality-score, search, export) to move from ~2 actions toward comprehensive coverage.

Add natural synonyms users actually say ('build a dataset', 'reference data', 'training data for ML') alongside the technical jargon to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names the domain and ~2 concrete delivery modes ('Extract structured domain knowledge', 'in-session', 'via Ollama') but does not enumerate the broader action set (structure, quality-score, search, export), fitting anchor 3 rather than the 'several specific actions' of 4.	3 / 5
Completeness	It gives a clear 'what' (extract structured domain knowledge in-session or via Ollama) but has no 'Use when...' or equivalent trigger guidance; per the rubric a missing when-clause caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like 'domain knowledge', 'AI models', 'Ollama', and 'API key' are relevant but lean technical; the natural phrases a user would say ('build a dataset', 'Q&A dataset', 'reference data') are largely absent, matching anchor 3 over 2 (some relevant keywords present) and below 4 (no good natural-term coverage).	3 / 5
Distinctiveness Conflict Risk	The AI-model knowledge-distillation niche with Ollama/no-API-key framing is mostly distinct with only minor overlap risk against generic data-extraction skills, fitting anchor 4; it is more specific than anchor 3 but lacks the fully concrete distinct triggers of anchor 5.	4 / 5
	Total	13 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/bdistill-knowledge-extraction/SKILL.md
Commit: 57c135b

Reviewed: 23 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.