Name: trace
Author: zereight

Imported from zereight/gitlab-mcp (.github/skills/trace/SKILL.md). Install upstream with npx skills add zereight/gitlab-mcp --skill trace. Copyright stays with the author.

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]

Install trace and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zereight-gitlab-mcp-trace", "kind": "skill", "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.", "publisher": "zereight", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Evidence-driven tracing with competing hypotheses in parallel. Activate when user says: trace this, trace, why did this happen, root cause analysis, investigate why." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/zereight/gitlab-mcp", "path": ".github/skills/trace/SKILL.md", "ref": "HEAD", "url": "https://github.com/zereight/gitlab-mcp/blob/HEAD/.github/skills/trace/SKILL.md", "key": "zereight/gitlab-mcp/.github/skills/trace/SKILL.md" } }, "instructions": "# Trace\n\nEvidence-driven causal tracing using competing hypotheses. Use for ambiguous, causal, evidence-heavy questions where the goal is to explain WHY something happened.\n\n## Good Entry Cases\n- Runtime bugs and regressions\n- Performance / latency behavior\n- Architecture / premortem / postmortem analysis\n- Config / routing / orchestration behavior\n- \"Given this output, trace back the likely causes\"\n\n## Core Contract\nAlways preserve: Observation → Hypotheses → Evidence For → Evidence Against → Best Explanation → Critical Unknown → Discriminating Probe\n\n## Workflow\n1. Restate the observed resul", "cost": { "context_tokens": 349 } }

trace

About

Trace

Good Entry Cases

Core Contract

Workflow

Output

Use it

Install trace and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews