openkb

Use when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions `openkb`, an `.openkb/` directory, or a `wiki/` tree generated by openkb. The user may invoke you from any working directory; the active KB resolves via `openkb status`. Do NOT use for arbitrary Markdown directories, Obsidian vaults, or documentation sites not built by openkb.

Quality

90%

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

Quality

Content

100%Weight 40%Scale 1-3

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

An excellent content body: lean, highly actionable, with a clear sequenced workflow, explicit guardrails, and well-signaled on-demand references. No meaningful weaknesses against the rubric.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence throughout, covering only openkb-specific operational knowledge (layout, commands, trust boundary, guardrails) with no padding about concepts Claude already knows, so every section earns its place.	3 / 3
Actionability	It provides a goal-to-action table with concrete file paths and fully executable commands (`jq '.[N-1]' ...`, a Python fallback one-liner, `openkb status`/`list`/`query`), making the guidance copy-paste ready.	3 / 3
Workflow Clarity	The retrieval flow is clearly sequenced (find the KB via `openkb status` -> see what's available -> read content) with an explicit guard ('If openkb status says No knowledge base found... don't proceed') and a 'When the KB doesn't have the answer' fallback; being read-only, no destructive validation loop is required.	3 / 3
Progressive Disclosure	The body is a concise overview with well-organized sections, and it points to two real one-level-deep references (verified references/wiki-schema.md and references/commands.md) clearly signaled under a 'References (load on demand)' block with explicit load conditions.	3 / 3
	Total	12 / 12 Passed

Description

80%Weight 40%Scale 1-3

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, trigger-rich description with excellent distinctiveness and completeness, undermined only by a second-person 'you' that the rubric penalizes on specificity. Reframing the operational aside in third person and leading with skill-performed verbs would lift it to the top band.

Suggestions

Remove the second-person 'you' (e.g. rephrase 'The user may invoke you from any working directory' to 'The agent may be invoked from any working directory') to avoid the specificity penalty.

Lead with concrete skill-performed actions in third person (e.g. 'Reads and synthesizes content from an OpenKB Markdown wiki') before the trigger clause, so capabilities read as what the skill does rather than what the user asks.

Tighten the abstract phrase 'concepts compiled from their documents, cross-document synthesis' into a single concrete capability statement.

Dimension	Reasoning	Score
Specificity	The description names the domain and core capabilities ('research topics, concepts compiled from their documents, cross-document synthesis') but frames them as user intent rather than skill-performed verbs, landing at the anchor-2 level; the second-person phrase 'The user may invoke you from any working directory' triggers the rubric's mandatory -1 specificity penalty, dropping it to 1.	1 / 3
Completeness	It explicitly answers both what (research/synthesis of KB content) and when, opening with an explicit 'Use when the user asks about...' trigger plus concrete signal mentions, so it is not capped at 2.	3 / 3
Trigger Term Quality	It covers natural terms a user would actually say — 'OpenKB knowledge base', 'research topics', `openkb`, `.openkb/`, and `wiki/` — matching the anchor for good coverage of natural keywords.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche with distinct triggers and an explicit exclusion — 'Do NOT use for arbitrary Markdown directories, Obsidian vaults, or documentation sites not built by openkb' — making a wrong-skill trigger unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: VectifyAI/OpenKB
Path: skills/openkb/SKILL.md
Commit: ff54396

Reviewed: 27 days 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.