root-cause-analysis
/root-cause-analysis
Writes a canonical RCA artifact for an incident or failure. Use when the workflow is root-cause-analysis and the team needs one durable record of problem, evidence, root cause and solution.
- Author
- eliyce ↗
- Repository
- paqad-ai ↗
- Licence
- MIT
- Last repository change
- 12.11.2026
Assessment and security
- Files in this package
- 7
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 12.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/lint-output.sh
What it does and when to use it
Writes a canonical RCA artifact for an incident or failure. Use when the workflow is root-cause-analysis and the team needs one durable record of problem, evidence, root cause and solution.
Original author description
Writes a canonical RCA artifact for an incident or failure. Use when the workflow is root-cause-analysis and the team needs one durable record of problem, evidence, root cause and solution.
How it works
- What It Does
- Use This When
- Inputs
- Procedure
- Output Contract
- Escalate / Stop Conditions
- Resources
SKILL.md preview
--- name: root-cause-analysis description: 'Writes a canonical RCA artifact for an incident or failure. Use when the workflow is root-cause-analysis and the team needs one durable record of problem, evidence, root cause and solution.' metadata: model_tier: reasoning cacheable: 'false' output_format: markdown paqad-meta: skill.meta.yaml --- ## What It Does Produces a canonical root cause analysis document with a fixed section set so investigations stay comparable across stacks and incidents. ## Use This When When the workflow is explicitly root-cause-analysis and the team needs a durable artifact that captures the problem, evidence, root cause, and solution in one place. ## Inputs - Read the incoming problem statement first. - Read the current stack snapshot, logs, traces, tests, or incident notes when available. - Use stack-specific tools and rules only as investigation inputs, not as a reason to vary the RCA structure. ## Procedure 1. Restate the problem clearly and identify the affected stack context. 2. Capture symptoms, impact, and timeline evidence before writing a conclusion. 3. Separate confirmed root causes from contributing factors and open questions. 4. Record the remediation in the `Solution` section even when it is proposed rather than already deployed. 5. End with verification steps and follow-up actions needed to prevent recurrence. ## Output Contract - Match `assets/output.template.md` exactly: 8 canonical sections in the order from `assets/section-order.txt`. - `## Solution` is always present, even when the remediation is proposed not deployed. - Output must pass `scripts/lint-output.sh` (exit 0): it enforces the section order strictly. ## Escalate / Stop Conditions - Ask when there is not enough evidence to distinguish root cause from speculation. - Warn when the available evidence conflicts across logs, tests, or runtime observations. - Do not present a guess as a confirmed root cause. ## Resources - `references/rca-sections.md` - `scripts/lint-output.sh` - `assets/output.template.md` - `assets/section-order.txt` - `agents/openai.yaml`
Files in this package (7)
- SKILL.md 2 KB
- skill.meta.yaml 1 KB
- agents/openai.yaml 1 KB
- assets/output.template.md 1 KB
- assets/section-order.txt 1 KB
- references/rca-sections.md 1 KB
- scripts/lint-output.sh 1 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · eliyce/paqad-ai | 90 | MIT |
| arozumenko/sdlc-skills | 100 | MIT |
| qa-aman/claude-skills | 100 | MIT |
| robert-adunka/triz-skills | 100 | MIT |
| arjunprabhulal/devops-skills | 100 | MIT |
| static-var/keystone | 100 | MIT |
| rohitg00/skillkit | 100 | Apache-2.0 |
| microsoft/hve-core | 95 | MIT |
| VoDaiLocz/kilo-kit-mcp | 95 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version f04a3d5fcd23 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95incident
Guide incident response, root cause analysis, and post-mortem documentation. Use when: production incident, outage response, post-mortem writing, RCA. Not for: designing retries and checkpoints before failure — use /durable; setting alert thresholds and Error Budget policy — use… - 84incident-response-assistant
引导事故响应、根因分析与事后复盘文档撰写。 Use when: 生产环境事故、服务中断响应、撰写事后复盘、根因分析(RCA)。 Not for: 在故障发生前设计重试与检查点——请用 /durable;设置告警阈值与 Error Budget 策略——请用 /slo。 Keywords: incident, outage, post-mortem, RCA, root cause, 事故, 服务中断, 事后复盘, 根因分析. - 90root-cause-fixer-workflow
Use when concrete failure evidence requires root-cause analysis, minimal patching, and regression proof as the Root Cause Fixer. - 100postmortem-writing
Writes blameless postmortems with root cause analysis, incident timelines, contributing factors, and action items. Use when conducting incident reviews or when the user mentions postmortem, root cause analysis, or blameless review. - 90cause-effect-chain-analysis
TRIZ Cause and Effect Chain Analysis (CECA) and Root Cause Analysis (RCA) — guides users through structured root cause analysis to identify root causes, key disadvantages, and contradictions in technical systems. Use this skill when the user mentions 'CECA', 'cause and effect… - 100rca-report
Use when investigating and documenting a production incident, outage, data corruption event, or post-mortem — guides evidence collection during the investigation AND produces a rich, reproducible Root Cause Analysis report. Trigger on phrases like "write an RCA", "post-mortem…