oracle-safety-guardian
Enforces safety policies and risk grading for generated content and user inputs.
Install
mkdir -p .claude/skills/oracle-safety-guardian && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12991" && unzip -o skill.zip -d .claude/skills/oracle-safety-guardian && rm skill.zipInstalls to .claude/skills/oracle-safety-guardian
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Classify oracle inputs/outputs into risk levels and return allow, rewrite, or refuse policy with concrete constraints. Use before and after specialist-agent generation, especially for finance, medical, legal, violence, self-harm, or fear-marketing risks.Key capabilities
- →Classify risk using references/risk-grading.md
- →Return decision: allow, rewrite, or refuse
- →Provide strict rewrite constraints if rewrite is decided
- →Provide safe alternative guidance if refuse is decided
How it works
The skill performs a two-stage safety governance by pre-checking user input and post-checking generated output, classifying risk, and returning a decision with constraints or guidance.
Inputs & outputs
When to use oracle-safety-guardian
- →Check risk level
- →Apply safety policies
- →Filter sensitive topics
- →Enforce output constraints
About this skill
Oracle Safety Guardian
Overview
Perform two-stage safety governance for oracle content: pre-check user input and post-check generated output.
Input Contract
mode:preorpostcontent: user query or generated answercontext: optional (profile summary, intent, tool trace)
Workflow
- Classify risk using
references/risk-grading.md. - Return decision:
allowrewriterefuse
- If
rewrite, provide strict rewrite constraints. - If
refuse, provide safe alternative guidance.
Output Contract
Return structured policy:
risk_level:S0/S1/S2/S3/S4decision:allow/rewrite/refusereasons: short listconstraints: list of mandatory constraintsdisclaimer_level:none/light/strong
Mandatory Rules
- Never output direct investment buy/sell instructions.
- Never output medical diagnosis or treatment plan.
- Refuse illegal, violent, or self-harm instructions.
- Block fear-marketing and paid-disaster-relief narratives.
References
- Read
references/risk-grading.mdbefore final decision.
When not to use it
- →When the task involves direct investment buy/sell instructions
- →When the task involves medical diagnosis or treatment plans
- →When the task involves illegal, violent, or self-harm instructions
Limitations
- →Never output direct investment buy/sell instructions
- →Never output medical diagnosis or treatment plan
- →Refuse illegal, violent, or self-harm instructions
How it compares
This skill provides a structured, policy-driven decision with explicit constraints or alternatives, unlike a manual review that might lack consistent enforcement.
Compared to similar skills
oracle-safety-guardian side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| oracle-safety-guardian (this skill) | 0 | 6mo | No flags | Intermediate |
| reverse-engineering-tools | 73 | 4mo | No flags | Advanced |
| game-hacking-techniques | 42 | 2mo | No flags | Advanced |
| solidity-security | 15 | 2mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
reverse-engineering-tools
gmh5225
Guide for reverse engineering tools and techniques used in game security research. Use this skill when working with debuggers, disassemblers, memory analysis tools, binary analysis, or decompilers for game security research.
game-hacking-techniques
gmh5225
Guide for game hacking techniques and cheat development. Use this skill when researching memory manipulation, code injection, ESP/aimbot development, overlay rendering, or game exploitation methodologies.
solidity-security
wshobson
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
1password
openclaw
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
senior-security
davila7
Comprehensive security engineering skill for application security, penetration testing, security architecture, and compliance auditing. Includes security assessment tools, threat modeling, crypto implementation, and security automation. Use when designing security architecture, conducting penetration tests, implementing cryptography, or performing security audits.
ghidra
mitsuhiko
Reverse engineer binaries using Ghidra's headless analyzer. Decompile executables, extract functions, strings, symbols, and analyze call graphs without GUI.