problem-handling SKILL.md skillA
problem-handling from ninjasln-labs/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ninjasln-labs/agent-skills/problem-handling@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ninjasln-labs/agent-skills
- Path
problem-handling/SKILL.md- Versions recorded
- 5
- Latest version
- v1.2.0, committed Oct 2, 2026
- First version recorded
- Sep 18, 2026
- Size
- 13,621 bytes
- Repository stars
- 3
- License
- none declared
Problem handling: one evidence-driven pipeline from a reported symptom to a shipped fix — evidence-first intake, root-cause tracing (5 Whys plus RCA tools, falsifiable experiments), cognitive-bias defenses, dual-channel research, severity grading with a P0/P1 restore-first fast path, classify and scope, workaround-vs-permanent-fix decision, TDD fix, verification, and a blameless close with known-error capture plus a 3-strikes design escalation. Use when a problem, bug, error, UX complaint, or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 问题处理（Problem Handling） > 单链四阶段：**诊断 A → 分级与决策 B → 修复与验证 C → 收尾 D**。 > 铁律：**每个修复可追溯到证据**（没定位不修）；**同一症状修三次就停下问设计**。 > **诊断阶段不直接修**；进入修复先分级（P0/P1 先恢复服务）。 ## 触发时机 用户反馈问题时**立即进入本流程**（不直接动手改）： - 「体验完毕/体验终止」+ 反馈；「有问题/报错/卡住/失败/异常/不太对」 - 「先看看日志/记录」「分析一下」「怎么回事」「根因是什么」 - 任何 bug / UX 投诉 / 行为偏差——**先诊断、再分级、后修复** 显式调用形（用户点名时）： ```text @problem-handling 症状：<一句话>；日志/记录：<路径或粘贴>；影响面：<已知则填> ``` - 三个字段均可省略——省略时从 A1 现场还原开始，先问证据在哪，**不先动手改**。 - 本技能按用户反馈自动进入（无需点名）；「自主触发禁令」不适用本技能——它就是反馈的默认落点。但**无任何用户反馈时不得自行跑本流程**（无事可诊断）。 ## 核心原则 1. **证据 > 印象**——先看日志/记录/trace 还原现场，不凭印象猜 2. **根因 > 症状**——现象→根因→根因的根因（为什么×N），假设须实测证伪 3. **通用 > 特判**——不兜底/白名单穷举，找通用机制（修环境不修命令、修配置不修单例） 4. **调研 > 直觉**——多源交叉验证（≥2 独立渠道 + 官方文档 + 源码 + 实测） 5. **语境 > 抽象**——方案放当前项目/环境语境检验（多项目并行/宿主隔离/环境统一） 6. **小步 > 大改**——决策清单 → 一个一个来 7. **闭环 > 发散**——改完盘点「还剩下什么没解决」 8. **定位 > 修复**——`No fix without location`：说不清哪个组件哪步失败，就别修 9. **恢复 > 追责**——P0/P1 先恢复服务（回滚/flag/降级），根因调查可延后；复盘**无责**（追责杀死教训） 10. **不修症状**——同一症状修 3 次 → 停止，升级到设计/系统层（含环境/流程/工具的多因素） ## 阶段 A · 诊断（不直接修） **A1 现场还原（证据先行）**：先读日志/记录还原现场。证据形态按可观测性成熟度取用：结构化日志（`tail <log> | jq`）→ 关联 trace/span（按链读，不只 grep 单点）→ metrics（基线对比）→ 复现路径。**按时间顺序完整读**，找全问题（不只是眼前这一点）。 …
Read the whole file at its exact version.
How to install
mdr add ninjasln-labs/agent-skills/problem-handling@sha256:e59f8973c6ba28d5The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_i5ooeksiuikfmpie)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 18, 2026 and Oct 2, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-10-02 | fae63b1 | 13,621 B | A | view · diff |
| v1.1.0 | 2026-09-29 | 0febb7a | 13,332 B | A | view · diff |
| v1.0.2 | 2026-09-22 | 75c75c0 | 9,880 B | A | view · diff |
| v1.0.1 | 2026-09-18 | eaaa7b4 | 9,858 B | A | view · diff |
| v1.0.0 | 2026-09-18 | cbc6719 | 9,858 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13621 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ninjasln-labs/agent-skills · 3 stars · license none declared · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_i5ooeksiuikfmpie GET https://markdownregistry.com/api/v1/resolve?ref=ninjasln-labs/agent-skills/problem-handling GET https://markdownregistry.com/api/v1/blob/e59f8973c6ba28d508a3e3ddc15f014f09fa0061cae96c42f8337c7947657ec4
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.