Name: bdistill-knowledge-extraction
Rating: 59.2 (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

68%

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/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 and well-structured with copy-paste commands throughout, but its workflow lacks explicit validation checkpoints and feedback loops, which caps workflow clarity at 3 for a batch knowledge-extraction operation.

Suggestions

Add an explicit validation checkpoint to the extraction workflow, e.g. after extraction run 'bdistill kb search' to spot-check entries or review quality_score/confidence before compounding, with a fix-and-retry loop on low-quality entries.

Frame the adversarial mode as a workflow step (validate → correct → re-validate) rather than only an optional flag, so the validation loop is visible in the sequence.

Trim the Overview marketing prose ('compounding knowledge base', the adversarial-mode descriptor) to tighten conciseness toward a leaner 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient and free of basic-concept padding, built mostly from concrete commands and examples, with only minor over-explanation in the Overview prose ('compounding knowledge base', the adversarial-mode sentence).	4 / 5
Actionability	Copy-paste-ready, fully executable commands cover install, in-session extraction, search/export, tabular ML schema, and local Ollama extraction, with a concrete JSON output example — matching 'fully executable; copy-paste ready; covers common cases'.	5 / 5
Workflow Clarity	There is a clear Install→Extract→Search/export sequence, but no explicit validation checkpoints or feedback loops; adversarial validation is only an optional flag, and because this is a batch/accumulation operation the cap-at-3 guideline applies.	3 / 5
Progressive Disclosure	The skill is self-contained with well-organized sections, no nested references, and a single one-level Related-Skills pointer; being over 50 lines it does not qualify for the simple-skill exception to 5, so 'good structure; minor organization gaps' fits.	4 / 5
	Total	16 / 20 Passed

Description

61%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 names a distinctive niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3 and limits its trigger-term and specificity strength.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when building reference datasets, Q&A corpora, or lookup tables from AI model responses, or when comparing domain knowledge across models.'

Enumerate a couple more concrete actions in the description (e.g. 'quality-scores, validates, and exports') to lift specificity from one action toward comprehensive coverage.

Include a natural synonym or two users would actually say ('knowledge base', 'reference data') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Extract structured domain knowledge from AI models') plus two delivery modes, but does not list several specific actions, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	There is a clear 'what' (extract structured domain knowledge in-session or via Ollama) but no 'Use when...' or equivalent explicit trigger guidance — only 'No API key needed.' — so completeness is capped at 3 per the missing-trigger guideline.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('domain knowledge', 'AI models', 'Ollama', 'in-session'), though common variations like 'knowledge base', 'reference data', or 'training data' are missing, fitting the 'good coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The niche of extracting knowledge from AI models via Ollama with no API key is mostly distinct with low conflict risk, but 'domain knowledge' is somewhat broad and no explicit distinguishing trigger phrases are given, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 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/skills/bdistill-knowledge-extraction/SKILL.md
Commit: 57c135b

Reviewed: 24 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.