agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/windbg-evidence-diagnostics/SKILL.md

windbg-evidence-diagnostics

Skill29 starsChanged 7 months agoMITView on GitHub

Ground agent failure diagnosis, root cause analysis, and postmortems in raw empirical system evidence (Microsoft WinDbg MCP pattern). Enforces SHA-256 evidence fingerprints, Verifiable Evidence Boxes, and grounded abstention (EVIDENCE_INSUFFICIENT) without installing Windows debuggers or proprietary binaries.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Anti-Clone Boundary: NEVER install WinDbg, Windows Debugging Tools, or DbgEng.dll.

    line 13
  2. Distinctive:

    Evidence-First Verification: Every diagnosis must cite exact exit code, stdout/stderr chunk, and cryptographic SHA-256 fingerprint.

    line 14
  3. Very specific:

    Grounded Abstention: If required evidence cannot be gathered, return EVIDENCE_INSUFFICIENT rather than speculating.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

WinDbg MCP Evidence Diagnostics (FORMAT Steal)

Stolen from Microsoft Performance Diagnostics (Introducing WinDbg MCP: Debug with Natural Language Grounded in Evidence).

Core Posture

  • Verdict: COMPARE_NOT_CLONE.
  • Anti-Clone Boundary: NEVER install WinDbg, Windows Debugging Tools, or DbgEng.dll. Keep all evidence verification deterministic, local, and sub-50ms.
  • Evidence-First Verification: Every diagnosis must cite exact exit code, stdout/stderr chunk, and cryptographic SHA-256 fingerprint.

Key Invariants

  1. Empirical Grounding: Assertions are verified directly against raw process output.
  2. Cryptographic Integrity: Diagnostic receipts carry SHA-256 digests over output snippets.
  3. Grounded Abstention: If required evidence cannot be gathered, return EVIDENCE_INSUFFICIENT rather than speculating.

Verification Commands

node scripts/windbg-evidence-diagnostics.js
node scripts/windbg-evidence-diagnostics.js --json
node scripts/windbg-evidence-diagnostics.js --map-only
node --test tests/windbg-evidence-diagnostics.test.js

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free