Add wealthville-pool-scoring skill

[amitesh-m]

Adds one skill under skills/, plus the regenerated docs/README.skills.md row.

What it does

Answers "should I provide liquidity to this pool?" with a number, a verdict, and the evidence for how often that verdict has been right — rather than leaving the model to interpret raw TVL and APR.

• Coverage — ~68,800 Solana pools (Meteora DLMM, Orca Whirlpool, Raydium AMM/CLMM/CPMM) and 575 EVM pools across Ethereum, Arbitrum, Base, Optimism, Polygon and BSC (Uniswap v2/v3/v4, Aave, Morpho, Pendle, Curve, Compound, Aerodrome).
• Output — a 0-100 score and an Enter/Hold/Exit/Reduce/Avoid verdict, with confidence calibrated per protocol rather than pooled.

Safety

The skill is read-only and installs nothing. It documents GET requests against a public API and nothing else — no transactions, no wallet, no seed phrase or private key, no curl | sh bootstrap, and no API key (the API takes no authentication; an optional free key only raises a rate limit).

On honesty

The skill deliberately documents its own weak spots rather than hiding them, because a skill that overstates its accuracy is worse than no skill:

• prefer calibrated_confidence over the raw value,
• treat a fee APR above 500% as a display bound rather than a measurement,
• and the REDUCE verdict class currently has a 0.00 hit rate on n=16 — if the model surfaces a REDUCE, the skill instructs it to say so.

It also tells the model to fetch /track-record rather than quoting numbers from the file, since they move.

Checks

npm run skill:validate → "All 393 skills are valid". npm run build regenerated docs/README.skills.md; that file's diff is exactly one added line, and no other generated output changed. Every endpoint cited in the skill returns 200 as of this PR.

Disclosure: I maintain the service this skill documents.

[github-actions]

🔴 Contributor Reputation Check: HIGH risk

Check	Risk
Profile	HIGH
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔒 PR Risk Scan Results

Scanned 2 changed file(s).

Severity	Count
🔴 High	1
🟠 Medium	2
ℹ️ Info	0

Severity	Rule	File	Line	Match
🟠	package-exec-command	docs/README.skills.md	31	| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` | Run the AgentRC readiness assessment on the curre
🔴	autoyes-package-exec	skills/wealthville-pool-scoring/SKILL.md	151	claude mcp add wealthville -- npx -y @​​wealthville/mcp-server
🟠	package-exec-command	skills/wealthville-pool-scoring/SKILL.md	151	claude mcp add wealthville -- npx -y @​​wealthville/mcp-server

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	npm warn EBADENGINE Unsupported engine {
ℹ️	npm warn EBADENGINE package: '[email protected]',
ℹ️	npm warn EBADENGINE required: { node: '>=22.12.0' },
ℹ️	npm warn EBADENGINE current: { node: 'v20.20.2', npm: '10.8.2' }
ℹ️	npm warn EBADENGINE }
ℹ️	npm warn deprecated [email protected]: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
ℹ️	✅ wealthville-pool-scoring (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.

Full linter output

### Linting skills/wealthville-pool-scoring
npm warn EBADENGINE Unsupported engine {
npm warn EBADENGINE   package: '[email protected]',
npm warn EBADENGINE   required: { node: '>=22.12.0' },
npm warn EBADENGINE   current: { node: 'v20.20.2', npm: '10.8.2' }
npm warn EBADENGINE }
npm warn deprecated [email protected]: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
✅ wealthville-pool-scoring (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

[Copilot]

Pull request overview

This PR contributes a single new Agent Skill, wealthville-pool-scoring, which documents a read-only public HTTP API (and equivalent MCP tools) for scoring DeFi liquidity pools and returning Enter/Hold/Exit/Reduce/Avoid verdicts with a published, miss-inclusive track record. It fits the repository's community-driven skill collection under skills/, with the auto-generated README row added. The author discloses they maintain the documented service.

Changes:

• Add skills/wealthville-pool-scoring/SKILL.md describing the pool-scoring API endpoints, verdict semantics, honesty/limitations guidance, and MCP alternative.
• Add the corresponding generated row to docs/README.skills.md.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
skills/wealthville-pool-scoring/SKILL.md	New skill defining valid front matter and read-only API usage guidance for DeFi pool scoring; passes skill validation.
docs/README.skills.md	Adds the auto-generated skills index row for the new skill (single line, correctly ordered).

[aaronpowell]

Sorry, this doesn't fit with the objectives of awesome copilot at the moment.