Agent Skills › zereight/gitlab-mcp › trace

trace

GitHub

基于证据驱动的竞争假设进行因果追踪，用于分析运行时错误、性能问题及架构故障等复杂现象的根因。通过系统化的假设生成与验证流程，定位最可能的解释并识别关键未知因素。

.github/skills/trace/SKILL.md zereight/gitlab-mcp

触发场景

trace this why did this happen root cause analysis

安装

npx skills add zereight/gitlab-mcp --skill trace -g -y

更多选项

非标准路径

npx skills add https://github.com/zereight/gitlab-mcp/tree/main/.github/skills/trace -g -y

不安装直接使用

npx skills use zereight/gitlab-mcp@trace

指定 Agent (Claude Code)

npx skills add zereight/gitlab-mcp --skill trace -a claude-code -g -y

安装 repo 全部 skill

npx skills add zereight/gitlab-mcp --all -g -y

预览 repo 内 skill

npx skills add zereight/gitlab-mcp --list

SKILL.md

Frontmatter

{
    "name": "trace",
    "description": "Evidence-driven tracing with competing hypotheses in parallel. Activate when user says: trace this, trace, why did this happen, root cause analysis, investigate why.\n",
    "argument-hint": "<observation to trace>"
}

Trace

Evidence-driven causal tracing using competing hypotheses. Use for ambiguous, causal, evidence-heavy questions where the goal is to explain WHY something happened.

Good Entry Cases

Runtime bugs and regressions
Performance / latency behavior
Architecture / premortem / postmortem analysis
Config / routing / orchestration behavior
"Given this output, trace back the likely causes"

Core Contract

Always preserve: Observation → Hypotheses → Evidence For → Evidence Against → Best Explanation → Critical Unknown → Discriminating Probe

Workflow

Restate the observed result precisely
Generate 3 deliberately different hypotheses:
- Code-path / implementation cause
- Config / environment / orchestration cause
- Measurement / artifact / assumption mismatch
Assign @tracer to each hypothesis lane
Each lane: evidence for, evidence against, critical unknown, discriminating probe
Apply lenses: Systems, Premortem, Science
Rebuttal round between top two hypotheses
Rank, detect convergence, synthesize

Output

### Observed Result
[What happened]

### Ranked Hypotheses
| Rank | Hypothesis | Confidence | Evidence Strength |
|------|------------|------------|-------------------|

### Most Likely Explanation
[Current best explanation]

### Critical Unknown
[Single missing fact]

### Recommended Discriminating Probe
[Single next probe]