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。

52

Quality

66%

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 body is a compact, well-sequenced workflow with genuinely useful specifics (workspace IDs, MCP tool names, grouping and sorting rules), but it is undermined by a verbatim-duplicated resources section, unresolved references, and the absence of validation steps for what is a batch operation. It reads as a reasonable draft that needs cleanup and error-handling guidance.

Suggestions

Remove the duplicated '📦 可用资源' section (identical 3-bullet list appears twice) and consolidate the reference pointers into one clearly-linked list.

Add validation checkpoints to the workflow: how to handle failed or empty stories_get/bugs_get/tasks_get calls, and how to verify dedup before output.

Ensure the referenced files (mcp-calls.md, status-mapping.md, summary-template.md) actually exist in the skill bundle and give Step 3 real content or an explicit, clearly-signaled link instead of the bare '详见 summary-template.md'.

DimensionReasoningScore

Conciseness

The body is mostly lean (workspace IDs, tool names, grouping rules are stated tersely), but the entire '📦 可用资源' section is duplicated verbatim twice, and the trailing 'IF-THEN 规则' note is redundant. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

Concrete specifics exist (workspaces 10158081 and 70093903, stories_get/bugs_get/tasks_get, 60-item cap, urgency buckets), but the actual MCP call syntax and the link-generation method are delegated to references that are not present in the bundle, and Step 3 is a bare pointer. This matches 'some concrete guidance but incomplete; missing key details' — not 4, which requires mostly executable guidance.

3 / 5

Workflow Clarity

The four steps are clearly sequenced (fetch → process → link → output) with concrete rules, but this is a batch operation (6 fetches across 2 workspaces, up to 60 items) with no validation or error-recovery checkpoints (e.g., handling failed MCP calls, empty results, or verifying dedup). Per the batch-operation cap, workflow clarity cannot exceed 3 despite the clean sequence.

3 / 5

Progressive Disclosure

The body does point to three reference files via skill:// URIs, but the resource list is duplicated, the references are not resolvable in the provided bundle (no references/ directory exists), and Step 3/4 reference 'summary-template.md' without a clear link. This fits 'some structure but could be better organized; references present but not clearly signaled' rather than 4.

3 / 5

Total

12

/

20

Passed

Description

66%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, in third person, and explicitly answers both what the skill does and when to use it, with a well-defined TAPD niche. Its main weaknesses are limited trigger synonym coverage and only partial enumeration of the skill's capabilities.

DimensionReasoningScore

Specificity

"获取 TAPD 待办单据并生成归纳总结" names the domain (TAPD) and two concrete actions (fetch to-do tickets, generate a summary), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It stays below 4 because it omits related capabilities (grouping, priority sorting, link generation) that the skill actually performs, and above 2 because the actions are concrete rather than generic.

3 / 5

Completeness

Both 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") are explicitly present with concrete trigger phrases. It falls short of 5 only because the 'when' clause is narrow and does not cover summary/aggregation phrasings that would also naturally invoke the skill.

4 / 5

Trigger Term Quality

Triggers include "获取 TAPD 单据" and "查看待办", which are natural phrases, but common variations like "汇总", "总结", "待办清单" or "TAPD bug/需求/任务" are absent. This fits 'some relevant keywords but missing common variations or synonyms' rather than 4's 'good coverage with a few missing'.

3 / 5

Distinctiveness Conflict Risk

TAPD is a specific issue-tracking platform, so the description occupies a clear niche with distinct triggers and minimal risk of firing for unrelated skills. It is clearly distinguishable from generic document- or data-processing skills.

5 / 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.

Validation — 16 / 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.