patent-map

专利地图：基于通俗解读已入库的 Obsidian 案例，点名后打开五种图。地形按 bge-small-zh 向量摊开。

Quality

61%

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 ./skills/patent-map/SKILL.md

Quality

Content

68%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 a lean, actionable quick-start with concrete commands and graceful-degradation notes, but the startup workflow lacks an explicit verification checkpoint before handing the URL to the user. References are one level deep and reasonably signaled, though embedded in step prose.

Suggestions

Add an explicit verification step after launching the server, e.g. 'Wait for a MAP_URL: line on stdout before sending the URL to the user; if it does not appear, check MAP_PORT/MAP_VAULT and retry.'

Surface the referenced files (guardrails.md, intake.md, tools/*.py) in a short navigation list so the dependency structure is scannable at a glance.

Clarify the fallback condition concretely ('if fastembed is not installed, terrain falls back to IPC clustering — no error') so the degraded path is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (terse steps, commands, machine-readable prefixes) with only minor passages that could be trimmed, matching the score-4 anchor; not 5 because a few sentences restate constraints that could be tighter.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready commands ('python skills/patent-map/tools/serve_map.py', 'pip install -r ...', 'python .../ensure_model.py') plus listed MAP_* prefixes, matching score 4; not 5 because a couple of details (expected stdout, exact fallback trigger) are left implicit.	4 / 5
Workflow Clarity	Steps are clearly sequenced (1-2-3 with concrete commands) but there is no explicit validation/verification checkpoint — the MAP_* prefixes act only as implicit verification and no validate→fix→retry loop is documented, fitting score 3 rather than 4.	3 / 5
Progressive Disclosure	Short, well-organized body with one-level-deep inline references to prompts/guardrails.md, intake.md, and tools/*.py; matches score 4. Not 5 because references are embedded in step prose rather than presented as a clear navigation section, and no bundle directories exist to confirm the referenced files.	4 / 5
	Total	15 / 20 Passed

Description

53%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 names a distinct niche and a couple of concrete actions but is jargon-heavy and lacks an explicit 'Use when...' trigger clause, leaving the 'when' only weakly implied. It is clearly distinguishable from other skills yet would benefit from plainer, more trigger-oriented phrasing.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user says 专利地图 / 案例地图 / patent-map and wants a visual map of archived Obsidian patent cases.'

Replace or gloss technical jargon ('bge-small-zh 向量摊开') with a user-facing phrase so the description reads as a natural trigger rather than an implementation note.

List the five map types or the concrete outputs to lift specificity from naming 1-2 actions to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (专利地图) and 1-2 concrete actions ('点名后打开五种图', '地形按 bge-small-zh 向量摊开') but coverage is not comprehensive, matching the score-3 anchor; below 4 because no list of several specific actions, above 2 because actions are concrete rather than generic.	3 / 5
Completeness	Clearly states what the skill does, but the 'when' is only weakly implied via '点名后' with no explicit 'Use when...' clause; per the guideline this caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('专利地图', '案例地图') but mixes in technical jargon ('bge-small-zh', '向量', 'Obsidian') and misses common synonyms/variations, fitting score 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	A clear niche (patent map over an Obsidian case vault) with distinct triggers and minimal conflict risk, fitting 'mostly distinct'; not 5 because trigger guidance leans on the user explicitly naming the skill rather than situational cues.	4 / 5
	Total	13 / 20 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: handsomestWei/patent-disclosure-skill
Path: skills/patent-map/SKILL.md
Commit: ce53860

Reviewed: 6 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.