resilience-classify
Research and classify stablecoins for resilience sub-factor overrides (chainRisk, collateralQuality, custodyModel). Run after types/defaults are implemented to identify coins needing explicit overrides.
Best use case
resilience-classify is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Research and classify stablecoins for resilience sub-factor overrides (chainRisk, collateralQuality, custodyModel). Run after types/defaults are implemented to identify coins needing explicit overrides.
Teams using resilience-classify should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/resilience-classify/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How resilience-classify Compares
| Feature / Agent | resilience-classify | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Research and classify stablecoins for resilience sub-factor overrides (chainRisk, collateralQuality, custodyModel). Run after types/defaults are implemented to identify coins needing explicit overrides.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Resilience Classification Skill
Identify stablecoins where the default inference (from backing + governance) is incorrect and apply overrides.
## When to Invoke
- After the resilience types and default inference are implemented
- When a new stablecoin is added to the tracker
- When auditing resilience scores for accuracy
## Process
### Step 1 — Identify candidates
Read all coins from `src/lib/stablecoins.ts`. For each, apply the default inference rules (see `inferResilienceDefaults()` in `src/lib/report-cards.ts`). Flag coins where the default is likely wrong based on:
- `collateral` text containing keywords: "Solana", "tBTC", "WBTC", "delta-neutral", "perpetual", "CEX", "off-exchange", "Copper", "Ceffu", "Fireblocks", "bridged"
- `pegMechanism` text containing: "Solana", "Bitcoin L2", "not Ethereum", "Tron"
- `contracts[]` listing only non-Ethereum chains
- `backing` = `crypto-backed` but collateral text mentions RWAs, bridges, or exotic strategies
- Coins on this known-override list: HYUSD, USDe, meUSD, USDD, sUSD (Synthetix), USDJ
### Step 2 — Research each candidate
For each flagged coin, in parallel:
- `WebFetch` official docs for collateral composition, custody arrangement, and chain architecture
- `WebSearch` for `"{coin name}" stablecoin collateral custody chain` to find independent analysis
- Cross-reference with existing `collateral` and `pegMechanism` text fields
### Step 3 — Classify
For each coin, determine the correct tier:
| Sub-factor | Question | Tiers |
|---|---|---|
| `chainRisk` | Where does the core protocol live and where is collateral held? | `ethereum` (100), `stage1-l2` (66), `established-alt-l1` (33), `unproven` (0) |
| `collateralQuality` | What are the trust assumptions in backing assets? | `native` (100), `eth-lst` (66), `alt-lst-bridged-or-mixed` (33), `exotic` (0) |
| `custodyModel` | Who holds the collateral and can it be verified on-chain? | `onchain` (100), `institutional` (50), `cex` (0) |
**Classification rules:**
- **chainRisk**: Based on where the protocol's smart contracts and collateral vaults live, NOT where the token is bridged to
- **collateralQuality**: For mixed collateral, use the tier of the riskiest significant component (>15% of backing). Stablecoin portions don't count here (handled by dependency risk)
- **custodyModel**: If ANY significant portion is held off-chain by a non-institutional custodian, classify as `cex`
- When uncertain between two tiers, choose the riskier (lower score) tier
### Step 4 — Present findings
For each coin needing an override, present:
```
## {Name} ({Symbol}) — ID: {id}
### Default inference
- chainRisk: {inferred} — {correct/wrong because...}
- collateralQuality: {inferred} — {correct/wrong because...}
- custodyModel: {inferred} — {correct/wrong because...}
### Proposed overrides
- {field}: {value} — {justification with source URL}
### No override needed
- {fields where default is correct}
```
### Step 5 — Apply
After user approval, edit `src/lib/stablecoins.ts` to add only the override fields that differ from defaults. Example:
```typescript
usd("123", "Example", "EX", "crypto-backed", "decentralized", {
// ... existing fields ...
chainRisk: "established-alt-l1",
collateralQuality: "alt-lst-bridged",
}),
```
Run `npm run build` to verify.Related Skills
analyze-copper-stock-resilience-dependency
用跨資產訊號(全球股市韌性 + 中國利率環境)評估銅價能否突破關卡或進入「回補/回踩」到支撐的機率與路徑。
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
self-subagent
Orchestrate parallel sub-tasks by spawning non-interactive instances of your own CLI as subagents. Use when you need to parallelize work across multiple files, run independent investigations simultaneously, or delegate heavy multi-step tasks. Works with ANY AI coding CLI agent (Amp, Claude Code, Codex, Cursor, OpenCode, aider, Cline, Roo, goose, Windsurf, Copilot CLI, pi, etc.). Triggers on "run in parallel", "subagent", "delegate", "fan out", "concurrent tasks", or any complex task that benefits from parallel execution.
self-improving-ai
Understanding and using StickerNest's self-improving AI system. Use when the user asks about AI self-improvement, prompt versioning, reflection loops, AI evaluation, auto-tuning prompts, or the AI judge system. Covers AIReflectionService, stores, and the improvement loop.
second-brain
Personal intelligence system for capturing thoughts, managing knowledge, and surfacing insights. Use when user wants to capture an idea, task, or note during conversation; query their knowledge base; check their inbox; review digests; or update task status. Triggers include "remember this," "add a task," "what did I say about," "show my inbox," or "mark complete."
searching-message-history
Search Telegram conversation history and stored links. Use when finding past messages, what someone said, or links shared in chats.
screpcombiningexpression
Combine scTCR/BCR repertoire data with scRNA-seq expression data using `scRepertoire::combineExpression()`. This process integrates immune receptor information (CDR3 sequences, V(D)J genes, clonotypes) into a Seurat object's metadata, enabling clonotype-aware gene expression analysis.
scrapegraph-ai-automation
Automate Scrapegraph AI tasks via Rube MCP (Composio). Always search tools first for current schemas.
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
scientific-papers-to-dataset
Build structured datasets from academic papers. Use when the user wants to extract structured data from scientific literature, traverse citation graphs, search OpenAlex for papers, or create datasets from PDFs for research purposes.
scholarag
Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA screening (50% or 90% threshold), vector database creation (ChromaDB), or research conversation interface. Supports knowledge_repository (comprehensive, 15K+ papers, teaching/exploration) and systematic_review (publication-quality, 50-300 papers, meta-analysis) modes. Conversation-first workflow with 7 stages.
savestate
Time Machine for AI. Encrypted backup, restore, and cross-platform migration for your agent's memory and identity. Supports OpenClaw, ChatGPT, Claude, Gemini, and more. AES-256-GCM encryption with user-controlled keys.