bk-monitor-weekly-report
通过 GitHub MCP 获取用户 PR 并生成周报。当用户提到生成周报、写周报时使用。
79
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./bcs-services/bcs-project-manager/.cursor/skills/bk-monitor-weekly-report/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is functional with clear 'what' and 'when' clauses, making it easy for Claude to know when to select this skill. However, it could benefit from more specific actions (e.g., what the weekly report includes) and broader trigger term coverage including English variations and alternative phrasings.
Suggestions
Add more specific actions describing what the weekly report contains, e.g., 'summarizes merged PRs, code reviews, and contributions'
Expand trigger terms to include variations like 'PR总结', 'weekly summary', 'work report', '工作周报' to improve matching
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub MCP, PR, weekly report) and describes the main action (fetch PRs and generate weekly report), but doesn't list multiple specific concrete actions or detail what the weekly report contains. | 2 / 3 |
Completeness | Clearly answers both what (fetch user PRs via GitHub MCP and generate weekly report) and when (explicitly states '当用户提到生成周报、写周报时使用' - use when user mentions generating or writing weekly reports). | 3 / 3 |
Trigger Term Quality | Includes relevant Chinese keywords '生成周报' and '写周报' (generate/write weekly report), but misses common variations like 'PR总结', '工作汇报', 'weekly summary', or English equivalents that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche combining GitHub PRs with weekly report generation. The specific combination of 'GitHub MCP', 'PR', and '周报' creates distinct triggers unlikely to conflict with general document or code skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise and well-structured with appropriate progressive disclosure to external resources. However, it lacks concrete examples of API call parameters (e.g., the exact search query format) and validation/error handling steps for a multi-step workflow involving external API calls.
Suggestions
Add a concrete example of the search query format for `toolbase_github_search_issues` including date range calculation
Include error handling guidance for cases like API failures, rate limits, or no PRs found
Remove the duplicate '可用资源' section at the end
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, with no unnecessary explanations. Each step is brief and assumes Claude understands GitHub APIs and PR concepts. | 3 / 3 |
Actionability | Provides specific tool names and classification rules, but lacks concrete code examples or exact API call parameters. The search query format and date calculation are not shown. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced (1-4), but lacks validation checkpoints. No guidance on handling API errors, empty results, or what to do if PR classification is ambiguous. | 2 / 3 |
Progressive Disclosure | Good structure with clear overview and well-signaled references to external files (classification-rules.md, weekly-template.md). One-level deep references are appropriately used. | 3 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- TencentBlueKing/bk-bcs
- Commit
b08ac38
- 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.