trade-journal

Analyze a user's trade journal (CSV/Excel broker export). Parses 同花顺/东方财富/富途/generic formats, produces a trading profile and 4 behavior diagnostics (disposition effect, overtrading, chasing, anchoring). Use the `analyze_trade_journal` tool.

Quality

80%

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

Quality

Content

78%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 highly actionable, well-sequenced skill body with concrete tool calls, return shapes, report templates, and error handling. The main gaps are progressive disclosure (lengthy reference-style blocks inlined, no separate reference files) and minor conciseness wins from externalizing the JSON/template material.

Suggestions

Move the full JSON return-shape examples and report templates into reference files (e.g. references/return_shape.md, references/report_templates.md) and link to them from SKILL.md to improve progressive disclosure.

Condense the inline JSON examples to the essential fields, keeping the bulk in a reference file so the overview stays lean.

Add a brief 'Use when' trigger reminder at the top of the body to mirror the description's intended trigger guidance.

Dimension	Reasoning	Score
Conciseness	Dense and operational with no concept-explanation padding (no 'what is a CSV/disposition effect' filler), but the two full JSON return-shape blocks and two full report templates add length that could be trimmed or externalized.	4 / 5
Actionability	Copy-paste-ready tool calls with exact params, precise filter_expr syntax, fill-in report templates, explicit detection-threshold table, and named error strings with prescribed responses cover the common cases fully.	5 / 5
Workflow Clarity	Clear sequence (call tool → present report → follow-up dialogue → error handling) with conditional decision checkpoints (win_rate/profit_loss_ratio thresholds) and explicit error branches; read-only analysis so the destructive-validation cap does not apply.	4 / 5
Progressive Disclosure	Section headers give reasonable structure, but ~209 lines with full JSON return shapes and complete report templates inlined, and no external reference files at all, means content that could be split out is kept inline.	3 / 5
	Total	16 / 20 Passed

Description

82%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 specific, well-triggered, and distinctive description that clearly states what the skill does and names concrete broker formats and diagnostics. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause such as 'Use when the user uploads a broker export (交割单) or asks to analyze their trade history/trading performance.'

Mention the Chinese term 交割单 as a natural trigger synonym since the skill targets Chinese broker exports.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Parses 同花顺/东方财富/富途/generic formats', 'produces a trading profile and 4 behavior diagnostics (disposition effect, overtrading, chasing, anchoring)' — covering inputs, outputs, and named diagnostics comprehensively.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' trigger clause — 'Use the `analyze_trade_journal` tool' is a how instruction, not a when trigger, so completeness is capped at 3 per the missing-trigger guidance.	3 / 5
Trigger Term Quality	Includes natural terms users say ('trade journal', 'CSV/Excel broker export') plus the specific broker names (同花顺/东方财富/富途) that retail traders reference, giving comprehensive keyword and format coverage.	5 / 5
Distinctiveness Conflict Risk	A clear niche (broker trade-journal analysis with named Chinese broker formats) with highly distinct triggers and minimal overlap risk with 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/trade-journal/SKILL.md
Commit: 1907e47

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.