- name
SKILL.md
El archivo de la skill permanece en el repositorio del publicador.
Pega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add microsoft/win-dev-skills --skill windbg-diagnostic-method -a cursor -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add microsoft/win-dev-skills --skill windbg-diagnostic-method -a claude-code -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add microsoft/win-dev-skills --skill windbg-diagnostic-method -a codex -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add microsoft/win-dev-skills --skill windbg-diagnostic-method -a grok -yEnvía el mensaje copiado en un chat de Grok Bot. El Bot obtiene este SKILL.md de GitHub y lo añade a las skills que comparten todos tus Bots.
Install this skill: https://github.com/microsoft/win-dev-skills/tree/HEAD/plugins/windbg/skills/windbg-diagnostic-methodDel publicador
Apply this method alongside the bug-family-specific skill selected for an investigation. Pattern matches route the investigation; they do not prove the root cause.
Prefer direct evidence in this order:
Never claim commands, source access, or artifacts that are unavailable in the session.
.exr -1, .ecxr, stack, and registers..bugcheck, !analyze -v, then documented context/trap
recovery for that code.candidate-pending-verification.These are the complete bug-family routes. Continue evidence-led reasoning for unsupported families; never dispatch to an absent skill.
Confidence is explanatory judgment, not measured probability.
candidate-pending-verification, set the
fix to null or a verification plan, and name the evidence/fix matrix needed.MODULE_NAME.Diagnosis confidence and fix confidence are separate. Every proposed fix must
declare fix_confidence and one fix_code_path_coverage value:
Lower confidence is always allowed when evidence quality, path coverage, or alternatives warrant it. Never raise confidence to fit the table.
Before finalizing a full diagnosis:
contrarian
agent once with the complete proposed diagnosis.CHALLENGED, test the counter-hypothesis with direct
evidence, then downgrade confidence or remain pending verification.Record contrarian_loopback as the Boolean true or false.
A full report contains these H2 sections in order:
The Trigger Verification section must distinguish observed, contradictory, and missing evidence plus fix validation. Mermaid must reflect verified evidence. The JSON summary must include:
diagnosis_statusrouting_pathroot_causeconfidencefix_confidencefix_code_path_coveragecontrarian_reviewcontrarian_loopbackAfter writing the report, run the bundled validator with PowerShell 7:
pwsh -NoProfile -File <skill-directory>\scripts\validate-diagnosis-output.ps1 `
-Path <diagnosis-markdown-path>
Use the installed windbg-diagnostic-method directory for
<skill-directory>. The script checks each section body independently,
requires at least two alternatives, accepts explicit or implicit Mermaid
participants, parses the JSON summary, and exits nonzero on failure.
Correct failed checks and rerun the script before presenting the report as structurally complete. Structural validation does not replace technical review.
Dumps, traces, ETLs, CABs, source, paths, tokens, and memory contents can be
sensitive. Obtain authorization before capture, configuration changes, or
sharing. Verifier and Page Heap can disrupt workloads and require a recoverable
test plan plus restoration steps. Public feedback follows FEEDBACK.md and
defaults to a minimal reviewed summary with no automatic attachments.
For feedback about this method or validator, follow the package FEEDBACK.md.
Do not attach private diagnosis files automatically.
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation. Not a bug-family-specific t
---name: windbg-diagnostic-methoddescription: Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration…---# plugins/windbg/skills/windbg-diagnostic-method/SKILL.mdResumen general
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation. Not a bug-family-specific triage skill.
Preguntas frecuentes
Descarga plugins/windbg/skills/windbg-diagnostic-method/SKILL.md desde el publicador, o copia la ruta y abre el repositorio. PlugMCP lista la skill y no aloja el archivo.
El publicador lo mantiene en https://github.com/microsoft/win-dev-skills.
Claude, Cursor, Codex y Grok Build pueden leer un SKILL.md que añadas desde el repositorio del publicador. Grok Bot lo instala cuando envías en un chat el enlace a la carpeta de la skill en GitHub.