open-knowledge-discovery

Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an OpenKnowledge project, wants to share an OpenKnowledge project with collaborators, asks whether OpenKnowledge supports a particular capability, or asks how `ok init` / `ok cowork` / OK Desktop set up a project. Do NOT load to perform OpenKnowledge reads/writes — the runtime guidance for editing markdown inside an initialized OK project ships as a separate project-local skill installed into each detected agent's skills dir (for example `.claude/skills/open-knowledge/`) whenever `ok init` runs.

Quality

89%

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

Quality

Content

78%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 concrete commands and clear conditional workflows, and well-structured for a single-file skill. Its main weakness is conciseness: the runtime-contract separation and the do-not-init-to-view points are stated multiple times and could be consolidated.

Suggestions

Consolidate the runtime-contract disclaimer: state once that in-project read/write guidance ships as the separate project-local skill, then have later sections reference it instead of re-explaining.

Merge the repeated 'Never run ok init just to view or open a file' guidance into a single prominent callout in the Opening-a-file section rather than restating it.

Add a brief post-`ok init` verification cue (e.g. 'ok init prints which agents it wired; re-run to refresh') so the mutating setup step has an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with commands and short imperatives, but the runtime-contract disclaimer ('does not carry the in-project read/write contract / ships separately') is restated in the intro, install section, and a dedicated Working-inside-a-project section, and the 'never run ok init just to view a file' point is repeated — more than minor tightening needed.	3 / 5
Actionability	Fully executable guidance throughout — copy-paste commands (npx @inkeep/open-knowledge init, ok init, ok cowork, ok open /abs/path), the preview_url MCP tool with its file parameter, --project <dir> variants, and a concrete decision branch by viewing surface covering the common cases.	5 / 5
Workflow Clarity	Clear sequences (numbered share steps 1-3, conditional open-a-file branch by surface) with feedback guidance ('exits non-zero and says why, so you never need a second command'); minor validation gaps since the mutating ok init setup step has no explicit post-run verify checkpoint.	4 / 5
Progressive Disclosure	Single-file skill with well-organized section headers and one-level-deep pointers to docs/source links; no bundle files exist and none are needed, so well-organized sections satisfy the no-external-references exception.	5 / 5
	Total	17 / 20 Passed

Description

100%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 is exemplary: it enumerates concrete actions, provides natural trigger phrasings users would actually say, explicitly covers both what and when, and carves out a distinct niche with a clear exclusion. It is long but every clause earns its place as a trigger or boundary.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across the skill's full surface — 'install it on a repository', 'open or preview a single markdown file', 'share an OpenKnowledge project', and setup mechanics for ok init / ok cowork / OK Desktop — giving comprehensive coverage rather than just several actions.	5 / 5
Completeness	Explicitly answers both 'what' (discovery/install/opening guidance) and 'when' with concrete trigger phrases ('Read when the user asks...'), plus an explicit Do-NOT-load exclusion, matching the both-what-and-when-with-concrete-triggers anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including user phrasings ('what OpenKnowledge is', 'share... with collaborators', 'whether OpenKnowledge supports'), command names (ok init, ok cowork), and product synonyms (OpenKnowledge/OK), matching the comprehensive-coverage-with-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Clear OpenKnowledge niche with distinct triggers tied to the product name and commands, and an explicit exclusion ('Do NOT load to perform reads/writes') that minimizes conflict with the separate project-local skill.	5 / 5
	Total	20 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: inkeep/open-knowledge
Path: packages/server/assets/skills/discovery/SKILL.md
Commit: 60997a2

Reviewed: 1 day 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.