CtrlK
BlogDocsLog inGet started
Tessl Logo

bk-monitor-tapd-summary

获取 TAPD 待办单据并生成归纳总结。当用户提到获取 TAPD 单据、查看待办时使用。

51

Quality

55%

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 ./bcs-services/bcs-project-manager/.cursor/skills/bk-monitor-tapd-summary/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 skill presents a clear high-level workflow with concrete API names and constraints, but lacks executable call syntax, validation checkpoints for its batch operation, and has duplicated resource-listing padding. Strengthening validation and removing the duplicate block would lift the content meaningfully.

Suggestions

Add a validation/checkpoint step (e.g. verify each stories_get/bugs_get/tasks_get returned and dedup before grouping) since this is a batch operation across 60 items.

Remove the duplicated '📦 可用资源' block and consolidate the summary-template references into a single clearly signaled link.

Provide concrete, executable MCP call examples with the status filter (e.g. the actual stories_get parameters) either inline or clearly pointed to in mcp-calls.md.

DimensionReasoningScore

Conciseness

Mostly lean step-by-step content, but the entire '📦 可用资源' block is duplicated verbatim and there is redundant cross-referencing to summary-template.md across Steps 3-4, adding padding that could be trimmed.

3 / 5

Actionability

Names concrete API operations (stories_get/bugs_get/tasks_get) and concrete workspace IDs and the 60-item cap, but gives no executable invocation form, parameters, or filter syntax, leaving it at 'concrete guidance but incomplete'.

3 / 5

Workflow Clarity

Steps are sequenced (fetch → process → links → output), but this batch operation (up to 60 items across 2 workspaces) has no validation/verification checkpoint or dedup-error handling, capping clarity at 3 per the batch-operation feedback-loop rule.

3 / 5

Progressive Disclosure

The body points to three one-level-deep reference files (mcp-calls, status-mapping, summary-template), but the '可用资源' block is duplicated and references are signaled somewhat loosely with a dangling IF-THEN note, fitting 'structure present but could be better organized'.

3 / 5

Total

12

/

20

Passed

Description

61%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 concise, third-person, and answers both what it does and when to use it, with a specific TAPD niche. Trigger-term coverage and action specificity have room to grow toward comprehensive synonyms and fuller capability enumeration.

Suggestions

Expand trigger terms with natural synonyms users might say, e.g. '查看 TAPD 待办、我的缺陷、需求进度、TAPD 任务列表'.

Enumerate more concrete capabilities in the description (e.g. '按紧急程度分组并按优先级排序输出汇总').

Consider noting the output form (汇总报告/链接列表) to sharpen the 'what' beyond '归纳总结'.

DimensionReasoningScore

Specificity

Names the domain (TAPD tickets) and two concrete actions — '获取 TAPD 待办单据' and '生成归纳总结' — but coverage is not comprehensive beyond fetch+summarize, matching the 'domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Clearly answers 'what' ('获取 TAPD 待办单据并生成归纳总结') and 'when' ('当用户提到获取 TAPD 单据、查看待办时使用'), though the trigger clause could be slightly more explicit/specific, matching the 'has both what and when' anchor.

4 / 5

Trigger Term Quality

Includes a couple of relevant natural phrases ('获取 TAPD 单据', '查看待办') but misses common variations/synonyms users might say, fitting the 'some relevant keywords but missing variations' anchor rather than the fuller 4.

3 / 5

Distinctiveness Conflict Risk

TAPD-specific niche with distinct triggers tied to a named tool, leaving only minor overlap risk with other ticketing skills, matching the 'mostly distinct' anchor rather than the fully clear 5.

4 / 5

Total

14

/

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
TencentBlueKing/bk-bcs
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.