~ / rigs / jefrnc / quant-llm-skills

jefrnc/quant-llm-skills

Skills for quant research with LLMs that don't fall for the traps nobody talks about. Lookahead bias, ATM detection, survivorship, transaction-cost realism — 10 skills + 11 reproducible evals showing 8 of them measurably improve Haiku outpu

↗ GitHub ★ 1 MIT updated 2mo ago collection Cursor Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~843 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit jefrnc/quant-llm-skills/skills ./rig-quant-llm-skills/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit jefrnc/quant-llm-skills/skills/atm-detection .claude/skills/atm-detection
$ npx degit jefrnc/quant-llm-skills/skills/bank-tier-classification .claude/skills/bank-tier-classification
$ npx degit jefrnc/quant-llm-skills/skills/code-review-for-quant .claude/skills/code-review-for-quant
$ npx degit jefrnc/quant-llm-skills/skills/dilution-event-scoring .claude/skills/dilution-event-scoring
$ npx degit jefrnc/quant-llm-skills/skills/insider-dedup .claude/skills/insider-dedup
$ npx degit jefrnc/quant-llm-skills/skills/lookahead-safety .claude/skills/lookahead-safety
$ npx degit jefrnc/quant-llm-skills/skills/sec-filing-types .claude/skills/sec-filing-types
$ npx degit jefrnc/quant-llm-skills/skills/survivorship-bias .claude/skills/survivorship-bias
$ npx degit jefrnc/quant-llm-skills/skills/transaction-cost-modeling .claude/skills/transaction-cost-modeling
$ npx degit jefrnc/quant-llm-skills/skills/xbrl-fallbacks .claude/skills/xbrl-fallbacks

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (10)

Cursor rules (10)

atm-detectionbank-tier-classificationcode-review-for-quantdilution-event-scoringinsider-deduplookahead-safetysec-filing-typessurvivorship-biastransaction-cost-modelingxbrl-fallbacks

Similar rigs

copied ✓