analysis-workflow

Estrelas3

Forks1

Atualizado23 de julho de 2026 às 22:15

Analyze, validate, debug, troubleshoot, critique, red-team, adversarial, or what-could-go-wrong questions. Not for PR/diff review; use code-review.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

ilude

ilude/dotfiles

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

Explorador de arquivos

4 arquivos

SKILL.md

readonly

name	analysis-workflow
description	Analyze, validate, debug, troubleshoot, critique, red-team, adversarial, or what-could-go-wrong questions. Not for PR/diff review; use code-review.

Analysis Workflow

Boundary

Need	Use
Debugging, validation, root-cause analysis, red-team critique	`analysis-workflow`
Reviewing a diff/branch/PR/commit for findings	`code-review`
Logs, metrics, traces, alerts, SLOs	`logging-observability`
Failed live mutation	Follow the active repository incident policy

Core Principle

Structured evidence beats analysis theater. Form hypotheses, test them, and separate observed facts from guesses.

Practical Steps

State the question or failure mode.
Gather direct evidence before proposing fixes.
List plausible hypotheses and what would falsify each.
Run the cheapest decisive check first.
Distinguish confirmed facts, likely causes, and unknowns.
Recommend the smallest next action backed by evidence.

Debugging Checklist

What changed recently?
Can the issue be reproduced?
What exact input/state triggers it?
Which layer first diverges from expected behavior?
What evidence would disprove the leading theory?

Anti-Patterns

Producing long critique without checking evidence.
Treating correlation as cause.
Jumping to broad refactors before isolating the fault.
Reporting risks without probability, impact, or mitigation.
Retrying without evidence that distinguishes a new hypothesis.

Mais deste repositório

mesmo repositório

pi-extension

ilude/dotfiles

Pi extensions and tool policy: extensions/*.ts, hooks, registerTool, promptGuidelines, registerCommand, footer/status UI, tool_result, session hooks, or subprocesses. Not for slash-command placement; use pi-command.

2026-08-023

docs

ilude/dotfiles

README, CHANGELOG, docs/, RFCs, ADRs, guides, or Markdown structure. Not for prose cleanup or archival work.

2026-07-273

no-ai-slop

ilude/dotfiles

Prose cleanup for filler, hype, vague claims, repetition, detection tells, or uncited specifics. Not for Markdown architecture or archival work.

2026-07-273

planning

ilude/dotfiles

Requirements, user stories, acceptance/verification criteria, or testable outcomes. Not for PRD drafting (/prd) or Pi /goal prompts.

2026-07-273

prd

ilude/dotfiles

Use for /prd-it or to draft, refine, or review a Product Requirements Document. Not for acceptance criteria, planning, or Pi /goal prompts.

2026-07-273

pi-log-analytics

ilude/dotfiles

Pi session, trace, metrics, routing, workflow-friction, workflow-telemetry, usage, or local JSONL analysis with DuckDB. Use for aggregating or correlating Pi runtime logs. Not for adding telemetry, generic SQL/database design, or non-Pi logs.

2026-07-273

name	analysis-workflow
description	Analyze, validate, debug, troubleshoot, critique, red-team, adversarial, or what-could-go-wrong questions. Not for PR/diff review; use code-review.

Analysis Workflow

Boundary

Need	Use
Debugging, validation, root-cause analysis, red-team critique	`analysis-workflow`
Reviewing a diff/branch/PR/commit for findings	`code-review`
Logs, metrics, traces, alerts, SLOs	`logging-observability`
Failed live mutation	Follow the active repository incident policy

Core Principle

Structured evidence beats analysis theater. Form hypotheses, test them, and separate observed facts from guesses.

Practical Steps

State the question or failure mode.
Gather direct evidence before proposing fixes.
List plausible hypotheses and what would falsify each.
Run the cheapest decisive check first.
Distinguish confirmed facts, likely causes, and unknowns.
Recommend the smallest next action backed by evidence.

Debugging Checklist

What changed recently?
Can the issue be reproduced?
What exact input/state triggers it?
Which layer first diverges from expected behavior?
What evidence would disprove the leading theory?

Anti-Patterns

Producing long critique without checking evidence.
Treating correlation as cause.
Jumping to broad refactors before isolating the fault.
Reporting risks without probability, impact, or mitigation.
Retrying without evidence that distinguishes a new hypothesis.