ttfund-skills

天天基金官方 Skills 网关调用封装。 Use when: 查询天天基金/天天财富基金数据、基金搜索、基金净值、基金持仓、基金经理、指数、黄金、债市、活期宝或官方 ttfund skills。 Not for: 交易执行、券商/银行账户操作、FRED/Tushare/yfinance/AKShare 结构化数据源、投资建议。 Output: 通过官方网关返回的结构化 JSON 事实数据，带 source/asOf 后再进入 F207 数据层。 GOTCHA: 必须有本机 `TTFUND_APIKEY`，且 key 只放环境变量或 gitignored `.env`，绝不写入 git 或回复全文。

Quality

86%

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

72%Weight 40%Scale 1-3

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

The body is actionable and well-structured with a real bundled script, but it loses conciseness to redundant version numbers and a duplicated env step, and lacks an explicit validated workflow sequence.

Suggestions

Remove the version numbers from the Skill IDs table (or move them to a clearly marked version/deprecated section) since they are time-sensitive and already defined in ttfund-call.mjs; have the script be the single source of truth.

Fix the duplicated env-reading list (items 2 and 3 both say '仓库根目录 .env') and the matching double loadDotEnvFile call in the script, so the documented key-loading order is accurate.

Add a short explicit workflow with a validation checkpoint — e.g. run 'list' to confirm a skill_id, then invoke, then check the returned source/asOf before passing data to the F207 layer.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the Skill IDs table embeds time-sensitive version numbers inline (not in a deprecated/old-patterns section) and duplicates the version map already in ttfund-call.mjs; the env-reading list also repeats '仓库根目录 .env' twice, so it could be tightened.	2 / 3
Actionability	Quick Reference gives fully executable, copy-paste-ready commands such as 'node cat-cafe-skills/ttfund-skills/scripts/ttfund-call.mjs FUND_SEARCH \'{...}\'', backed by the real bundled script, matching the executable-code anchor.	3 / 3
Workflow Clarity	Guidance is conveyed through examples and a Common Mistakes table rather than a clearly sequenced workflow with explicit validation checkpoints; the only 'sequence' listed (the env-reading order) is duplicated/buggy, so checkpoints are implicit at best.	2 / 3
Progressive Disclosure	The body is a well-organized overview with clear sections (When to Use, Quick Reference, Skill IDs, Common Mistakes) and a one-level-deep reference to the real bundled scripts/ttfund-call.mjs, with content appropriately split rather than nested.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, trigger-rich, and clearly scoped with explicit Use when / Not for guidance, all in third person. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names multiple concrete query capabilities — '基金搜索、基金净值、基金持仓、基金经理、指数、黄金、债市、活期宝' — and the action '通过官方网关返回的结构化 JSON 事实数据', matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('天天基金官方 Skills 网关调用封装...返回的结构化 JSON 事实数据') and when via an explicit 'Use when:' clause plus a 'Not for:' clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Triggers are natural terms a user would say — '天天基金净值', '天天基金搜索', '天天基金经理', '天天基金持仓', '天天黄金', '天天债市', 'ttfund' — giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	Clear niche (the official TTFund gateway) with a 'Not for:' clause explicitly distinguishing it from FRED/Tushare/yfinance/AKShare, so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: zts212653/clowder-ai
Path: cat-cafe-skills/ttfund-skills/SKILL.md
Commit: 80782c5

Reviewed: 11 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.