Evidence-driven tracing with competing hypotheses in parallel. Activate when user says: trace this, trace, why did this happen, root cause analysis, investigate why.
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
# 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 |
…
The line at the top of this page pins the label git:20260412.9d9ce51, 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.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1660 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
GitHub
zereight/gitlab-mcp · 2,059 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5oi7xmp7yr4f4xaw
GET https://markdownregistry.com/api/v1/resolve?ref=zereight/gitlab-mcp/trace
GET https://markdownregistry.com/api/v1/blob/fb21957a1ad769ffcf787c5fe7dd91df688c308a18a5edfbc95e0ba2c80ef938
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.
zereight/gitlab-mcp · .github/skills/ai-slop-cleaner/SKILL.md · Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop…
zereight/gitlab-mcp · .github/skills/cancel/SKILL.md · Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill…
zereight/gitlab-mcp · .github/skills/deep-dive/SKILL.md · 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive…
zereight/gitlab-mcp · .github/skills/deep-interview/SKILL.md · Socratic deep interview with mathematical ambiguity gating. Activate when user says: deep interview, interview me, ask…
zereight/gitlab-mcp · .github/skills/omg-autopilot/SKILL.md · Full autonomous execution from idea to working code. Activate when user says: autopilot, auto-pilot, autonomous, build…
zereight/gitlab-mcp · .github/skills/plan/SKILL.md · Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a…
zereight/gitlab-mcp · .github/skills/ralph/SKILL.md · PRD-driven persistence loop until task completion with verification. Activate when user says: ralph, don't stop, must…
zereight/gitlab-mcp · .github/skills/remember/SKILL.md · Promote reusable project knowledge to the right memory surface. Activate when user says: remember this, save this…
yeachan-heo/oh-my-claudecode · skills/trace/SKILL.md · Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/trace/SKILL.md · Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic…
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/trace/SKILL.md · Use when debugging how a value or request reaches Elixir code, finding who calls a function, or planning a signature…
ai-analyst-lab/ai-analyst · .claude/skills/trace/SKILL.md · Show the provenance trace, linking every reported number to the SQL that produced it with a confidence badge. Use after…
mirkobozzetto/arsenal · plugins/trace/skills/trace/SKILL.md · Save where the session stands before ending it, so next can resume it in a clean context. Also reads or records project…
naimkatiman/continuous-improvement · third-party/oh-my-claudecode/skills/trace/SKILL.md · Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode