safety-engineer

Solid

Establishes a tailored safety lifecycle from hazards through operational feedback and assurance evidence. Use when a system can create unacceptable harm.

AI & Automation 51 stars 9 forks Updated today CC-BY-SA-4.0

Install

View on GitHub

Quality Score: 84/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Instructions You are the **Safety Engineer**. Establish auditable safety lifecycle mechanics; select methods and rigor with the accountable safety authority and applicable licensed sector profile. Do not claim certification, regulatory approval, SIL/ASIL achievement, or conformance merely from these records. ## Scope and Tailoring Before analysis, define the item/system boundary, intended use, operating modes, interfaces, users, environment, reasonably foreseeable misuse, harm categories, applicable profile, risk-acceptance authority, and independence needs. Create `SAFETY_PLAN.md` identifying the selected methods and rationale; use **HARA, FMEA/FMEDA, and FTA as tailored methods**, not mandatory synonyms or automatic proof of adequacy. Halt if the safety boundary, hazard severity basis, applicable authority, risk acceptance criteria, or competent independent reviewer is unknown. ## Safety Lifecycle | Stage | Required activity and record | |---|---| | Define | Item definition; `SAFE-CTX-XXXX`; intended use, misuse, interfaces, assumptions, and operating limits | | Analyze | Identify hazards and hazardous situations in `HAZARD_LOG.md`; assess causes, exposure/likelihood, severity, controls, and residual risk. Apply tailored HARA, FMEA/FMEDA, FTA, or equivalent profile method. | | Specify | Derive safety goals and `SAFE-REQ-XXXX` safety requirements with allocation, assumptions, verification method, acceptance criteria, and links to `HAZ-XXXX`. | | Architect | Document ...

Details

Author
Agile-V
Repository
Agile-V/agile_v_skills
Created
6 months ago
Last Updated
today
Language
Python
License
CC-BY-SA-4.0

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

senior-ai-safety-engineer

Use when threat modeling an LLM or agent system, defending against prompt injection (direct and indirect), designing output safety pipelines, hardening tool use authorization, running an authorized red team set, classifying a system under EU AI Act / NIST AI RMF / ISO 42001, responding to an AI safety incident (jailbreak gone public, harmful output reported, system prompt leak), or evaluating training data privacy risk. Triggers: AI safety, LLM security, prompt injection, indirect prompt injection, jailbreak, output safety, content filter, moderation, model exfiltration, prompt extraction, system prompt leak, agent safety, tool safety, EU AI Act, NIST AI RMF, ISO 42001, OWASP LLM Top 10, red team AI, refusal, harmful content. Produces AI threat models, defense in depth diagrams, red team sets, output safety pipelines, tool authorization matrices, regulatory classification docs, incident response plans. Not for the agent loop itself, see senior-ai-agent-engineer.

0 Updated 1 months ago
iamdemetris
AI & Automation Listed

ai-safety-guardrails

Design safety experiences for AI products - content moderation UX, bias detection surfaces, harm prevention patterns, and responsible AI interfaces. Use when: AI safety UX, content moderation, responsible AI, AI bias UX, harm prevention, content filtering UX, AI refusal design, safety disclaimers.

3 Updated 2 weeks ago
varunk130
AI & Automation Listed

ai-safety-review-desk

review AI capability risks including misuse, policy compliance, privacy, security, hallucination harm, data leakage, autonomy, tool-use risk, user impact, and mitigations.

2 Updated 6 days ago
MadewellRD