incident

Estrellas4

Forks0

Actualizado8 de julio de 2026 a las 16:46

Create an incident, regression, bug investigation, or debugging artifact with timeline, metrics, and hypothesis table. Use for outages, postmortems, root-cause analysis, production issues, flaky failures, or debugging narratives.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

samilozturk

samilozturk/artilens

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

SKILL.md

readonly

name	incident
description	Create an incident, regression, bug investigation, or debugging artifact with timeline, metrics, and hypothesis table. Use for outages, postmortems, root-cause analysis, production issues, flaky failures, or debugging narratives.
allowed-tools	["Bash","Read","Agent"]

Incident Recipe

Gather the incident data: timeline events, hypotheses (with status), and metric summaries from the conversation context or the user directly. There is no CLI command for this skill.
Start a background subagent with the Agent tool: subagent_type: general-purpose, model: sonnet, run_in_background: true. Prompt template: "Read ${CLAUDE_PLUGIN_ROOT}/references/artifact-authoring.md. Load the artifact-design skill, then author and publish an artifact with the Artifact tool. Data: <timeline, hypotheses, metrics gathered above, inline>. Page plan: timeline; hypothesis table with a status column; metric summaries; copy-as-prompt. All visual design decisions are yours."
Continue your own task. When the subagent finishes, relay the artifact URL to the user.
For long-running investigations, re-gather updated data and republish to the same URL as new evidence arrives.

Más de este repositorio

mismo repositorio

agents

samilozturk/artilens

Visualize subagent, Agent tool, and delegated task activity from the current Claude Code session. Use when work was delegated or the user asks what agents/subagents did, what ran in the background, or how tasks were coordinated.

2026-07-084

artifacts

samilozturk/artilens

List, find, inspect, diff, resume, or update this project's locally registered artifacts. Use when the user references a previous artifact, asks what artifacts exist, wants artifact history, or wants to continue from an artifact.

2026-07-084

board

samilozturk/artilens

Create a draggable planning, kanban, roadmap, or backlog board artifact with copy-as-prompt feedback. Use for task ordering, project boards, sprint planning, prioritization, or moving cards between columns.

2026-07-084

commands

samilozturk/artilens

Catalog available slash commands, ArtiLens skills, plugins, and contextual recommendations. Use when the user asks what commands/tools/skills are available, what ArtiLens can do, or what to run next.

2026-07-084

compare

samilozturk/artilens

Create an option comparison artifact with tradeoffs and a recommendation. Use when the user wants to compare approaches, architectures, libraries, plans, implementation choices, pros/cons, or decision options.

2026-07-084

context-files

samilozturk/artilens

Inventory project context files — CLAUDE.md, AGENTS.md, rules, SKILL.md files, plans, and docs — with read-frequency from the current transcript. Use when the user asks what context is loaded, which files shaped the session, or before auditing stale or unused context files.

2026-07-084

name	incident
description	Create an incident, regression, bug investigation, or debugging artifact with timeline, metrics, and hypothesis table. Use for outages, postmortems, root-cause analysis, production issues, flaky failures, or debugging narratives.
allowed-tools	["Bash","Read","Agent"]

Incident Recipe

Gather the incident data: timeline events, hypotheses (with status), and metric summaries from the conversation context or the user directly. There is no CLI command for this skill.
Start a background subagent with the Agent tool: subagent_type: general-purpose, model: sonnet, run_in_background: true. Prompt template: "Read ${CLAUDE_PLUGIN_ROOT}/references/artifact-authoring.md. Load the artifact-design skill, then author and publish an artifact with the Artifact tool. Data: <timeline, hypotheses, metrics gathered above, inline>. Page plan: timeline; hypothesis table with a status column; metric summaries; copy-as-prompt. All visual design decisions are yours."
Continue your own task. When the subagent finishes, relay the artifact URL to the user.
For long-running investigations, re-gather updated data and republish to the same URL as new evidence arrives.