CtrlK
BlogDocsLog inGet started
Tessl Logo

local-knowledge-integration

Safely integrate private local knowledge systems using explicit data classification, sanitized fixtures, compatibility checks, and reversible writes. Use before indexing, syncing, retrieving from, migrating, exporting, or changing a personal vault, memory runtime, note template, or knowledge connector.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, safety-oriented body with a clear sequenced workflow, explicit validation gates, and hard stops. The only improvements are trimming the small overlap between the intro/Purpose section and the description, and adding one concrete example (e.g., a minimal sanitized fixture layout or a sample contract) to push actionability to fully executable.

Suggestions

Merge the opening line into the Purpose section (or drop it) since it largely restates the frontmatter description, trimming redundant tokens.

Add a short example of a sanitized fixture (e.g., a fictional two-file directory layout) or a one-line sample integration contract to make step 2 and step 1 concretely executable rather than descriptive.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows, but the opening line ('Use this skill before connecting tools to a private vault or changing how personal knowledge is read, indexed, synchronized, or stored') and the Purpose section partially restate the frontmatter description — minor trim candidates that keep it below the every-token-earns-its-place anchor.

4 / 5

Actionability

Steps name concrete deliverables ('produce a plan, manifest, or diff', contract fields like 'source of truth, allowed inputs, output location, privacy boundary', 'record... pass/fail results') and a worked Representative Scenario, making the guidance mostly executable. It falls short of fully copy-ready because no example fixture or example contract statement is provided.

4 / 5

Workflow Clarity

The six-step Safe Integration Workflow is clearly sequenced with explicit validation checkpoints — fixture-first testing covering 'failure behavior', a Confirm recovery step, exact-approval gating, and a Hard Stops section for error conditions. The destructive/batch validation cap does not apply because validation is explicitly present, matching the top anchor.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, has no bundle directories, and contains no dangling file references — just well-organized sections plus clearly named companion skills. Per the rubric's simple-skill guideline this earns the top score.

5 / 5

Total

18

/

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.

A strong description with an explicit what-and-when structure, concrete mechanisms, and natural trigger phrases. Its only weaknesses are minor: a few missing synonym phrasings and some overlap risk with the companion vault/memory skills it routes to.

DimensionReasoningScore

Specificity

The description names the domain plus several concrete mechanisms — 'explicit data classification, sanitized fixtures, compatibility checks, and reversible writes' — matching the anchor for several specific actions with minor gaps; it falls short of comprehensive coverage of what integration work entails, so it is not a 5.

4 / 5

Completeness

It explicitly answers what ('Safely integrate private local knowledge systems using explicit data classification, sanitized fixtures, compatibility checks, and reversible writes') and when ('Use before indexing, syncing, retrieving from, migrating, exporting, or changing a personal vault...') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

It includes natural user verbs ('indexing, syncing, retrieving from, migrating, exporting') and objects ('personal vault, memory runtime, note template, knowledge connector') that users would plausibly say. A few common phrasings like 'my notes' or 'knowledge base' are missing, keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The private-knowledge integration-safety niche is mostly distinct, but triggers like 'changing a personal vault' overlap with closely related vault-manager and memory skills, so minor overlap risk remains; it is clearly more specific than the generic-anchor examples at 3.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pvnkmnk/AgenticSelfHostSkills
Reviewed

Table of Contents

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.