research-wiki

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The content is highly actionable and well-sequenced with strong validation feedback loops, but it is a long monolithic document whose reference-grade detail (schemas, budget tables, integration hooks) would benefit from extraction into bundled reference files. Conciseness is good but weakened by historical-drift prose.

Suggestions

Move the paper/idea/experiment/claim page schemas and query-pack budget tables into bundled reference files under references/ and link to them, so SKILL.md stays a lean overview and progressive disclosure reaches one-level-deep structure.

Trim or relocate historical-drift asides (e.g. the 'Earlier versions of this skill described a prose-only init' paragraph) into a brief 'deprecated patterns' note to improve conciseness without losing the rationale.

Extract the four integration hooks (1–4) into a references/integration-hooks.md with short in-page summaries and links, reducing the inline wall of code blocks.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but includes lengthy historical-drift asides (e.g. the 'Earlier versions of this skill described a prose-only init' paragraph) and repeated rationale paragraphs that could be tightened, placing it at the 'mostly efficient but could be tightened' anchor rather than the lean level-3.	2 / 3
Actionability	Provides fully executable bash commands, an exact paper-page frontmatter schema, concrete query-pack budget tables, and copy-paste-ready invocations, matching the 'fully executable code/commands; copy-paste ready' anchor rather than the pseudocode/incomplete level-2.	3 / 3
Workflow Clarity	Multi-step operations are clearly sequenced with explicit validation checkpoints — the helper-resolution chain with fallback and error messages, the EXP_NODE_OK gate before adding edges, and the validator-rejection rule — matching the level-3 'clear sequence with explicit validation steps; feedback loops' anchor rather than the checkpoint-missing level-2.	3 / 3
Progressive Disclosure	The body is a large monolithic SKILL.md that keeps reference-grade detail inline (full schema, query budget tables, four hooks) rather than splitting it into bundled reference files; the referenced paths point to out-of-bundle ../shared-references/ and no references/scripts/assets bundles exist, so it sits at 'some structure but content that should be separate is inline' rather than the well-signaled one-level-deep level-3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise, concrete, and fully addresses both capability and trigger conditions with natural user-language keywords including bilingual variants. It is highly specific to its niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'accumulates papers, ideas, experiments, claims, and their relationships' — across the research lifecycle, matching the 'multiple specific concrete actions' anchor rather than the single-domain 'Names domain and some actions' level below.	3 / 3
Completeness	Explicitly answers both what ('Persistent research knowledge base that accumulates...') and when ('Use when user says...'), matching the level-3 anchor that requires both an explicit 'what' and an explicit trigger clause rather than an implied 'when' at level 2.	3 / 3
Trigger Term Quality	Natural trigger terms users would say ('research wiki', 'add paper', 'wiki query') plus bilingual variants ('知识库', '查知识库') provide good coverage; not just technical jargon, which would sit at level 2's 'missing common variations'.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow niche (persistent research knowledge base) with distinct triggers unlikely to conflict with other skills, matching the level-3 'clear niche with distinct triggers' anchor rather than the broad-overlap levels below.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: 82076e5

Reviewed: 5 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.