CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 tight, executable reference for a simple gateway-wrapper skill: real commands with payloads, a versioned skill-ID table, and a useful mistakes table, with no tutorial filler. Its main defects are accuracy-of-detail rather than structure — a duplicated `.env` fallback entry, a repo-specific script path that does not resolve in this bundle, and no error-response guidance.

Suggestions

Fix the key-loading fallback list: items 2 and 3 both say "仓库根目录 .env" — either remove the duplicate or document the actual intended third source, and correct the same double-load in `scripts/ttfund-call.mjs` (`loadLocalEnv` calls `loadDotEnvFile` twice on the same path).

Make the script path match the bundle: the examples invoke `cat-cafe-skills/ttfund-skills/scripts/ttfund-call.mjs` but the file lives at `scripts/ttfund-call.mjs`; state the repo-root assumption once or use the bundle-relative path.

Add one line on handling gateway failures, e.g. that non-2xx responses raise `TTFund gateway HTTP <status>` with a truncated body, so the reader knows how to diagnose auth vs. payload errors.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows — a gateway URL, four executable examples, a skill-ID table, and a mistakes table, every section earning its place. It is not a 5 because the key-loading list repeats "仓库根目录 .env" as both items 2 and 3 (one wasted/erroneous line) and every example command redundantly carries the long repo-specific path prefix "cat-cafe-skills/ttfund-skills/scripts/" that could be stated once.

4 / 5

Actionability

Commands are concrete and copy-paste ready (`node ... ttfund-call.mjs FUND_SEARCH '{"query":"沪深300",...}'`) with real payloads, a `list` command, and a versioned skill-ID table covering the common cases. It is not a 5 because the documented script path `cat-cafe-skills/ttfund-skills/scripts/ttfund-call.mjs` does not resolve within this skill bundle (the file is at `scripts/ttfund-call.mjs`), and the key-loading fallback order is wrong (the same .env path listed twice, matching a script that also loads it twice, so a real third fallback is missing).

4 / 5

Workflow Clarity

As a simple single-action skill (set TTFUND_APIKEY → run `list` → invoke a skill_id with a JSON payload) the single action is unambiguous, and the Common Mistakes table acts as error-avoidance guidance for key handling and versioning. It is not a 5 because the key-setup step is muddied by the duplicated fallback entry and there is no guidance on reacting to gateway error responses (e.g., the HTTP error the script can raise).

4 / 5

Progressive Disclosure

The body is well organized into scannable sections (When to Use, Quick Reference, Skill IDs, Common Mistakes) with the single bundle script referenced one level deep and no nesting. It is not a 5 because the reference to the script uses a path that does not match the actual bundle layout (`scripts/ttfund-call.mjs`), and the 16-row skill-ID table duplicates data embedded in the script without pointing to it as the source of truth.

4 / 5

Total

16

/

20

Passed

Description

100%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 is exemplary: concrete capability enumeration, an explicit Use when clause with natural trigger terms and synonyms, explicit exclusions that delimit it from other data-source skills, and a stated output contract and credential gotcha. It is dense without padding and uses third-person phrasing throughout.

DimensionReasoningScore

Specificity

The description lists many concrete capability areas ("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") plus a concrete output contract ("结构化 JSON 事实数据,带 source/asOf") and an explicit auth requirement (TTFUND_APIKEY), giving comprehensive coverage of the wrapper's actions. Not a 4 because coverage of the domain's operations is thorough rather than having minor gaps.

5 / 5

Completeness

It explicitly answers both what ("天天基金官方 Skills 网关调用封装") and when ("Use when: 查询天天基金...基金数据") with concrete trigger phrases, and additionally supplies when-not-to-use, output shape, and a gotcha. Not a 4 because the 'when' clause is already explicit and specific rather than merely adequate.

5 / 5

Trigger Term Quality

It covers the natural phrases a Chinese-speaking user would say ("天天基金", "基金净值", "基金持仓", "基金经理", "黄金", "债市", "活期宝") together with synonyms (天天基金/天天财富/ttfund) and the key term TTFUND_APIKEY. Not a 4 because synonym coverage is already present and no obviously common natural term is missing for this domain.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (the official 天天基金 gateway) and the "Not for:" line explicitly excludes trading execution, broker/bank account operations, FRED/Tushare/yfinance/AKShare, and investment advice, minimizing overlap with adjacent data-source skills. Not a 4 because the exclusion list already resolves the main overlap risks with closely related skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
Reviewed

Table of Contents

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.