financeby nicepkg
US Market Bubble Detection Skill (Revised v2.1)
nicepkg/us-market-bubble-detector
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring.
What it changes
Passed 20 of 21 test cases with the skill, and 6 of 21 without it.
Without skill27%
With skill95%
Checks it passed that the model alone missed
- Recommends a risk budget of 20-30%.
- Classifies the risk phase as Euphoria.
- Uses a total final score scale bounded between 0 and 15 points.
and 16 more in the full report
15 fixed6 passed either way1 still failing0 broke
- Pass-rate lift
- +68 pp
- Tokens
- +197%
- Agent turns
- 0%
- Response time
- -37%
Model gemini-3.6-flashMeasured 8/24/2026v121 of 22 cases passed with skill · 21 comparable
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptAn evaluation yields a composite market bubble score of 11 out of 15. What risk phase is assigned, and what is the maximum risk budget recommended?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Classifies the risk phase as Euphoria. | Missed | Passed |
|---|
| Sets the recommended risk budget to 40-50%. | Passed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md540 lines7 filesincludes scripts
US Market Bubble Detection Skill (Revised v2.1)
Key Revisions in v2.1
Critical Changes from v2.0:
- ✅ Mandatory Quantitative Data Collection - Use measured values, not impressions or speculation
- ✅ Clear Threshold Settings - Specific numerical criteria for each indicator
- ✅ Two-Phase Evaluation Process - Quantitative evaluation → Qualitative adjustment (strict order)
- ✅ Stricter Qualitative Criteria - Max +3 points (reduced from +5), requires measurable evidence
- ✅ Confirmation Bias Prevention - Explicit checklist to avoid over-scoring
- ✅ Granular Risk Phases - Added "Elevated Risk" phase (8-9 points) for nuanced risk management
When to Use This Skill
Use this skill when:
English:
- User asks "Is the market in a bubble?" or "Are we in a bubble?"
- User seeks advice on profit-taking, new entry timing, or short-selling decisions
- User reports social phenomena (non-investors entering, media frenzy, IPO flood)
- User mentions narratives like "this time is different" or "revolutionary technology" becoming mainstream
- User consults about risk management for existing positions
Japanese:
- ユーザーが「今の相場はバブルか?」と尋ねる
- 投資の利確・新規参入・空売りのタイミング判断を求める
- 社会現象(非投資家の参入、メディア過熱、IPO氾濫)を観察し懸念を表明
- 「今回は違う」「革命的技術」などの物語が主流化している状況を報告
- 保有ポジションのリスク管理方法を相談
Evaluation Process (Strict Order)
Phase 1: Mandatory Quantitative Data Collection
CRITICAL: Always collect the following data before starting evaluation
Track record
Benchmark
20 / 21
test cases passed, vs 6 / 21 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importednicepkg / ai-workflow
workflows/stock-trader-workflow/.claude/skills/us-market-bubble-detector/SKILL.md
License MITImported 8/3/2026Version v1Bundled 6 files · scripts