菜单
Root-cause-first debugging loop for code or runtime errors: understand the failure before proposing a fix. Adapted from Hermes' systematic- debugging — same iron law, smaller surface, ZLAgent-tool-aware.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Fetch and summarise recent papers from arxiv.org. Use this skill when the user wants a digest of today's or this week's cs.AI / cs.LG / cs.CL listings, a focused per-topic roundup, or a quick look at a specific submission.
Lightweight code-review checklist the agent runs before declaring a patch ready. Catches the obvious classes of issue (dead code, missing error handling, weakened tests) without a full security audit. Adapted from addyosmani's "Review" lifecycle phase.
Do not declare a task done without running verification. For code, that means running tests / smoke; for answers, that means checking the claim against a fresh source. Adapted from obra/superpowers and addyosmani's "Verify" lifecycle phase.
Umbrella skill for user document workflows — PDF, Word, Excel, PowerPoint, text extraction, summarization. Dispatches to the right MCP / tool; proposes an install via mcp-discovery when no local capability fits. Adapted from Anthropic's docx/pdf/xlsx/pptx skills.
When the user wants something the agent doesn't have a tool for yet (travel planning, GitHub issues, Linear, weather, filesystem, ...), search the live MCP ecosystem for an existing server, propose installing it, and on confirm wire it up via mcp_manage. Adapted from Hermes' mcporter skill — same flow, ZLAgent-tool-aware.
定期检查 ZLAgent 的 skill、MCP 工具、记忆摘要的变化， 生成一份变更摘要并通过 IM 发送给用户。
| name | systematic-debugging |
| description | Root-cause-first debugging loop for code or runtime errors: understand the failure before proposing a fix. Adapted from Hermes' systematic- debugging — same iron law, smaller surface, ZLAgent-tool-aware. |
| version | 0.1.0 |
| tags | ["coding","debugging"] |
| metadata | {"zlagent":{"category":"coding","triggers":["报错","这个 bug","修一下","debug","调试","root cause","traceback","exception"],"capabilities":[],"related_skills":["task-planning","skill-authoring"]}} |
Use this skill when the user reports a bug, a failing test, an unexplained runtime exception, a flaky job, or pastes a traceback.
Do NOT use this when:
No fix without a root cause. A symptom fix is failure. If you haven't completed Phase 1, you cannot propose a fix.
symptom: the user-visible failure (error message, wrong output,
hang, ...). Capture verbatim.repro: how to reproduce. Ask if missing.recent_changes: what changed since it last worked.scope: file paths / functions / cron jobs / channels involved.Phase 1 — Understand:
read_file. Avoid wide grep.Phase 2 — Localise: 5. Add minimal logging or a targeted test that would prove / disprove the hypothesis. 6. Run it (or have the user run it) and read the new evidence.
Phase 3 — Fix: 7. Propose the smallest change that addresses the root cause. Show the diff. State which assumption it corrects. 8. Verify with the same repro / test you used in Phase 2.
Phase 4 — Land: 9. State what regression test was added (or why none was needed). 10. Note any related-but-not-fixed issues; do not silently widen scope.