llm-wiki

Compile heterogeneous knowledge sources—including documents, notes, web content, transcripts, research materials, and code repositories—into a Karpathy-style, evidence-grounded LLM Wiki with a maintained index; default entity and concept pages; and selective method, comparison, analysis, or instruction-requested summary pages. Use with ov compile to create or incrementally refresh knowledge that is easy for people and agents to retrieve, navigate, and reuse.

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 ./examples/compile/ov-compile-skills/llm-wiki/SKILL.md

Quality

Content

71%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 content is well-organized, concrete, and procedurally clear with strong templates and a final quality gate, but it is a long monolithic file with no progressive disclosure and only limited mid-process validation feedback loops.

Suggestions

Split the stable reference material (page-type taxonomy + routing tests, provenance/link-format rules, frontmatter spec) into one-level-deep reference files (e.g. references/page-types.md, references/provenance.md) and point to them from SKILL.md so the main file reads as an overview.

Add an explicit validate→fix→retry feedback loop inside the drafting flow (e.g. after writing each page, re-check the type-routing test and provenance rules before moving on) rather than relying solely on the end-of-run Quality gate.

Include one fully worked example page (e.g. a sample entity or concept page with frontmatter, opening summary, provenance, and relationships) so the page-writing guidance is unambiguously copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is dense and prescriptive and assumes Claude's competence without padding basic concepts, but the page-type gating rules are restated across Knowledge model, Plan against existing knowledge, Write pages, and Quality gate, leaving minor repetition that could be trimmed.	4 / 5
Actionability	It provides concrete copy-paste artifacts (frontmatter YAML block, page-path table, "[Readable source title](viking://...)" link format, single "## Sources" heading rule), but no full worked example page, leaving a minor gap versus the fully-executable anchor.	4 / 5
Workflow Clarity	The process is clearly sequenced via H3 stages (Establish scope → Survey → Extract → Plan → Index → Write → Provenance → Integrate) with an explicit Quality-gate checklist, but mid-process validate→fix→retry feedback loops are only weakly implied rather than explicit.	4 / 5
Progressive Disclosure	The file is well-sectioned with clear H2/H3 hierarchy and tables, but it is a monolithic ~270-line SKILL.md with no one-level-deep references, and spec material (page-type taxonomy, provenance formatting, frontmatter spec) that could be split into reference files is inlined.	3 / 5
	Total	15 / 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.

The description is specific, comprehensive, and clearly distinguishable, with an explicit trigger clause tied to the ov compile command. Its main weakness is that the "when" guidance is anchored to the tool command rather than to natural user-stated situations and is missing common synonyms.

Dimension	Reasoning	Score
Specificity	"Compile heterogeneous knowledge sources...into a...LLM Wiki with a maintained index; default entity and concept pages; and selective method, comparison, analysis, or instruction-requested summary pages" lists multiple concrete actions with comprehensive page-type coverage, matching the comprehensive-coverage anchor.	5 / 5
Completeness	A clear "what" is paired with an explicit "Use with ov compile to create or incrementally refresh knowledge that is easy for people and agents to retrieve, navigate, and reuse", but the "when" leans on the tool command rather than user-stated situations, so it sits just below the concrete-trigger-phrase anchor.	4 / 5
Trigger Term Quality	It names concrete source kinds (documents, notes, web content, transcripts, research materials, code repositories) and the natural trigger "ov compile", but common synonyms such as "knowledge base" or "build a wiki" are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	"Karpathy-style, evidence-grounded LLM Wiki", "ov compile", and the maintained-index/page-type niche give it a clearly distinct trigger surface with minimal overlap against other skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: volcengine/OpenViking
Path: examples/compile/ov-compile-skills/llm-wiki/SKILL.md
Commit: b2f1f9d

Reviewed: 3 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.