knowledge-base

How to work in a Knowledge Base project (the `knowledge-base` starter pack). Read when the project has the three-layer source-grounded layout — `external-sources/` → `research/` → `articles/` — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows, and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform `open-knowledge` skill, research and consolidate as their own sibling skills in this pack. Complements the platform `open-knowledge` skill; does not replace it.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/server/assets/skills/packs/knowledge-base/SKILL.md

Quality

Content

75%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, actionable guidance body that sequences the three-layer workflow with explicit autonomy gates and concrete frontmatter/logging conventions. It is slightly held back by a few motivational asides and by the dense single-file overview where a touch more delegation could help.

Suggestions

Trim the Karpathy 'bookkeeping/abandoned wiki' rationale to one sentence so the body stays lean and action-first.

Consider hoisting the per-procedure STOP-gate specifics (or a one-line summary of each gate) so the workflow checkpoints are inlined rather than only referenced.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence (no basic-concept padding), but a few motivational passages — the Karpathy 'tedious bookkeeping' rationale and the abandoned-wiki aside — could be trimmed without losing actionable guidance.	4 / 5
Actionability	It gives concrete, executable specifics — exact frontmatter fields (status: draft/stable/deprecated, sources:, supersedes:, superseded_by:, cluster:), a write({ document: { path, template } }) call, template names, and a log entry shape — with only minor gaps because the full procedure steps live in sibling skills.	4 / 5
Workflow Clarity	The ingest → research → consolidate loop is explicitly sequenced with a day-2 flow and real checkpoints ('Don't chain silently'; 'After ingest, ask whether to proceed to research'; STOP-gate vs session-autonomy clarification); minor validation gaps remain because the per-procedure gates are referenced rather than inlined.	4 / 5
Progressive Disclosure	Well-organized into focused sections with a procedures table that clearly signals one-level-deep references to sibling/platform skills (/open-knowledge, /research-with-sources, /consolidate-notes, references/ingest-and-sources.md); the body is a fairly dense ~80 lines, keeping it just short of a clean 5.	4 / 5
	Total	16 / 20 Passed

Description

80%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, boundary-aware description that clearly states both purpose and explicit read triggers, and cleanly distinguishes itself from sibling/platform skills. The main weakness is trigger-term naturalness, which leans on structural jargon over phrases a user would actually say.

Suggestions

Add user-natural trigger phrases (e.g. 'Use when the user asks how this knowledge-base repo is organized, or wants to ingest/research/consolidate sources') alongside the structural layout description.

Soften or gloss the 'three-layer source-grounded layout' jargon with a plain-language synonym so the trigger reads naturally to non-authors.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates concrete payload ('layer model, per-folder rules, status flows, and log discipline', 'the three procedures') plus the three folder layers, so several specific items are listed with only minor gaps in the actions themselves.	4 / 5
Completeness	It explicitly answers both what ('How to work in a Knowledge Base project ... Carries the layer model, per-folder rules, status flows, and log discipline') and when via an explicit 'Read when ...' trigger clause with concrete conditions, matching the anchor for full completeness.	5 / 5
Trigger Term Quality	It includes a couple of natural phrases ('when asked how this project is organized', 'Knowledge Base project'), but leans on jargon ('three-layer source-grounded layout', 'external-sources/ → research/ → articles/') and misses common synonyms a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (the knowledge-base pack layout) and explicitly disambiguates from adjacent skills ('Complements the platform open-knowledge skill; does not replace it'; 'The three procedures live elsewhere'), giving minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing, 1 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: inkeep/open-knowledge
Path: packages/server/assets/skills/packs/knowledge-base/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.