All skills
simota avatar

/scout

@e307415
by shingo imotasimota/agent-skills85 stars
15

Investigating bugs via root cause analysis, reproduction steps, and impact assessment. Investigation-only — finds why bugs occur and where to fix them, no code. Use when a bug needs RCA before a fix.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/scout

This session only. Nothing lands on disk.

referencefishbone-6m.md

≈325 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Fishbone Delta

Purpose: Scout fishbone breadth, evidence, and anti-blame contract. Ishikawa notation is model-known.

Software/Ops Categories

Use the 6M labels only as prompts, adapting names when the domain fits better:

  • Machine: infrastructure, runtime, hardware, platform
  • Method: code, procedure, workflow, controls
  • Material: inputs, data, dependencies
  • Measurement: telemetry, alerts, thresholds
  • Environment: external service, load, regulation, operating condition
  • People/organization: staffing, knowledge flow, incentives, handoffs

People is never a terminal blame bucket; trace the system condition that made individual action decisive.

Workflow Contract

  1. State one factual effect without embedding a suspected cause.
  2. Generate candidate causes across applicable categories before convergence.
  3. Weight candidates using an agreed probability/impact scale.
  4. Mark each top candidate confirmed, ruled out, or uncertain with evidence.
  5. Identify primary and contributing causes and explain their interaction.

Required Output

Provide the effect, categorized cause map, weighted top causes, evidence/verdict table, primary-plus-contributor narrative, corrective action, detection improvement, owners, and handoffs to Builder/Triage/Lore as appropriate.

Source: SKILL.md on GitHub

1 warning13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    Scout is a comprehensive bug investigation and root-cause analysis skill that follows security best practices, including mandatory PII masking, data protection policies, and clear role boundaries. While it processes untrusted user input, it includes robust mitigations such as delegating security concerns to specialized agents and explicitly forbidding code modification or secret exposure.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    3/11 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at e307415. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/scout