mcpField
T
trace

trace

github.com/zereightDevelopment2.1k58 installsUpdated today
Repository

About trace

Trace is a skill for investigating ambiguous, evidence-heavy causal questions. It guides analysts through competing explanations and probes to identify why an outcome occurred.

Key features

  1. 01Competing causal hypotheses
  2. 02Evidence for and against
  3. 03Critical unknowns and probes
  4. 04Rebuttal between leading hypotheses
  5. 05Ranked explanation output

Use cases

  1. 01Tracing runtime bugs and regressions
  2. 02Explaining performance or latency behavior
  3. 03Analyzing architecture and incidents
  4. 04Investigating config or orchestration behavior

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/zereight/gitlab-mcp --skill trace

After installing, type/tracein Claude Code to confirm it loaded.

Details

From the project README

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

  1. Restate the observed result precisely
  2. Generate 3 deliberately different hypotheses:
    • Code-path / implementation cause
    • Config / environment / orchestration cause
    • Measurement / artifact / assumption mismatch
  3. Assign @tracer to each hypothesis lane
  4. Each lane: evidence for, evidence against, critical unknown, discriminating probe
  5. Apply lenses: Systems, Premortem, Science
  6. Rebuttal round between top two hypotheses
  7. 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]

Comments

Markdown supported