CtrlK
BlogDocsLog inGet started
Tessl Logo

ir-record

当执行 IR(投资人关系)任务时维护 SQLite 追踪数据库,记录投资人档案、接触历史和项目申报,避免重复,跟踪进展。

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/ir-record/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is a well-structured, token-efficient operations manual: executable script commands with argument enums, status machines, and clear per-work-block usage rules. Main gaps are the absence of an explicit validate/retry feedback loop for DB writes and minor schema verbosity.

Suggestions

Add an explicit validation checkpoint for database mutations (e.g. 'after record-investor.sh, re-run check-investor.sh to confirm the row exists') to strengthen the feedback loop for batch/destructive operations.

Consider moving the full field-by-field schema tables into a separate references/ file and keeping only key fields inline, improving progressive disclosure and token budget.

Clarify the init-db.sh idempotency guarantee inline (one line) so Claude knows re-running is safe without opening the script.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence: schema tables, status-machine diagrams, and executable command blocks with no padding or explanation of concepts Claude already knows; only minor verbosity in field-by-field status enumerations.

4 / 5

Actionability

Every script invocation is given as a copy-paste-ready command with full argument lists, value enums, and required-field callouts; the referenced scripts all exist in the bundle, making guidance fully executable.

5 / 5

Workflow Clarity

The '使用规则' section sequences multi-step flows (check → record → update → query) with dedup checks as implicit checkpoints and HEARTBEAT triggers, but there is no explicit validate/retry feedback loop for the database operations.

4 / 5

Progressive Disclosure

Content is well organized into overview, schema, commands, and usage-rule sections with one-level-deep references to bundled scripts; structure is clear, though detailed schema could arguably live in a separate reference file.

4 / 5

Total

17

/

20

Passed

Description

67%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 third-person, names a clear niche (IR/investor-relations tracking), and includes an explicit 'when' trigger clause with several concrete actions. Its main weakness is trigger-term breadth — it relies on domain jargon (IR, 投资人关系) rather than the natural phrases users would say.

Suggestions

Broaden trigger terms to include natural user phrasings and synonyms (e.g. '投资人名单', '融资进展', '跟进投资人', 'track investors', 'pipeline') rather than only 'IR' and '投资人关系'.

Make the 'when' clause more concrete by naming triggering situations (e.g. '当搜索到新投资人、需要记录接触、或查询待跟进进度时').

Consider mentioning the SQLite file artifact or file extension as an additional natural trigger cue.

DimensionReasoningScore

Specificity

Lists several concrete actions ('维护 SQLite 追踪数据库', '记录投资人档案、接触历史和项目申报', '避免重复', '跟踪进展') rather than vague language, though coverage is actions-oriented rather than fully enumerated.

4 / 5

Completeness

Has both a clear 'what' (维护数据库, 记录档案/接触/申报) and an explicit 'when' trigger ('当执行 IR...任务时'), but the when clause could be more specific about concrete triggering situations.

4 / 5

Trigger Term Quality

Contains relevant domain terms ('IR', '投资人关系', 'SQLite', '投资人档案') but lacks common synonyms and natural user phrasing variations a user might actually say; missing broader trigger phrasing.

3 / 5

Distinctiveness Conflict Risk

The IR/投资人关系 + SQLite tracking niche is fairly distinct with minimal overlap risk against other skills; only minor overlap with generic database skills.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TeamWiseFlow/xiaobei
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.