chanlun

基于缠论（缠中说禅）的形态识别引擎，使用czsc库自动检测K线分型、笔、中枢，并生成一买/一卖/二买/二卖/三买/三卖等买卖点信号。支持多周期分析和形态分类（3/5/7/9/11笔形态）。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/chanlun/SKILL.md

Quality

Content

82%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-organized, highly actionable body with executable code and a clear processing pipeline, supported by real one-level-deep reference files. Minor conciseness and organization refinements (moving the bulk signal-function table to a reference) would push it to the top level.

Suggestions

Move the full 43-function / 15-row signal-function table into a references file (e.g. references/信号函数.md) and keep only the top 3-4 in SKILL.md to improve progressive disclosure.

Tighten '实现方式' and the data-format table, which restate library behavior Claude can infer from docs.

Add an explicit verification step after analysis (e.g. check that c.bi_list is non-empty / expected笔 count) to strengthen workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with sectioned tables and a focused quick-start, but '实现方式' and some descriptive prose (e.g. the data-format table) restate things Claude could infer, leaving minor instances that could be trimmed.	4 / 5
Actionability	Copy-paste ready executable code (RawBar construction, CZSC instantiation, accessing bi_list/bars_ubi), a pip install command, and a concrete table of named signal functions cover the common cases fully.	5 / 5
Workflow Clarity	The core pipeline '原始K线 → 去包含处理 → 分型识别 → 笔检测 → 中枢构建 → 买卖点判定' gives a clear sequence and the quick-start is concrete, but there are no explicit validation/checkpoint steps; this is an analysis skill (non-destructive) so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	Well-structured overview with one-level-deep references (核心概念/分型.md, 买卖点/一买一卖.md, etc.), all of which resolve to real bundle files; the inline signal-function table is borderline bulk that could live in a reference, keeping it just short of a 5.	4 / 5
	Total	17 / 20 Passed

Description

75%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 highly specific and distinctive description that names concrete capabilities and the underlying library, but it omits any explicit 'when to use' trigger guidance, which caps its completeness score. Adding a 'Use when...' clause would raise the overall quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing price structure with 缠论/缠中说禅, or when the user mentions 买卖点, 中枢, 分型, 笔, or czsc.'

Include natural synonyms/extensions users might say (e.g. 'chanlun', '.czsc', '缠中说禅') to broaden trigger-term coverage.

Keep third-person voice ('Detects...', 'Generates...') consistent throughout; the current phrasing is already compliant.

Dimension	Reasoning	Score
Specificity	Names the czsc library and lists multiple concrete actions — '自动检测K线分型、笔、中枢' and '生成一买/一卖...三买/三卖等买卖点信号' — plus multi-period analysis and form classification, giving comprehensive coverage.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' or equivalent explicit trigger clause; the rubric caps completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	Good coverage of domain terms a user would naturally say ('缠论', '买卖点', '中枢', '分型', 'K线'), but it lacks common synonyms/file extensions and stops short of the comprehensive variation coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (缠论/czsc form recognition) with distinctive triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 missing, 6 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/chanlun/SKILL.md
Commit: d71ed8d

Reviewed: 4 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.