market-valuation
Skill3 starsChanged 4 months agoMITView on GitHub
SP500 Shiller CAPE z-score (single asset). Ticker-agnostic cross-asset context, identical in shape to market-macro. Returns a ValuationSignal with regime (OVEREXTENDED/ELEVATED/FAIR/DEPRESSED/OVERSOLD) and the regime_note for narration. Use as a soft tag for L3 ideas or to set the morning brief's structural context. NOT for entry/exit decisions alone.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Shubhamkumartrichy/claude-trading-skills-indiatheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Shubhamkumartrichy/claude-trading-skills-india★ 64same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- beadsSkill
- backtest-engineSkill
- backtest-pipelineSkill
- backtest-trend-minerSkill
- bug-scanSkill
- daily-trade-pickSkill
- execution-kraken-perpsSkill
- execution-kraken-spotSkill
- l3-conviction-scanSkill
- market-accumulationSkill
- market-basisSkill
- market-breadthSkill
- market-breakoutSkill
- market-emaSkill
- market-exhaustionSkill
- market-fibonacciSkill
- market-liquidity-sweepSkill
- market-macdSkill
- market-macroSkill
- market-moversSkill
- market-notesSkill
- market-overviewSkill
- market-rsiSkill
- market-snapshotSkill
- market-squeezeSkill
- market-s-rSkill
- market-stateSkill
- market-trend-qualitySkill
- market-trendSkill
- market-volatilitySkill
- market-volumeSkill
- market-watchlistSkill
- portfolio-mgmtSkill
- position-watchdogSkill
- risk-engineSkill
- run-all-l2Skill
- run-all-l3Skill
- run-watchlistSkill
- strategy-accumulation-swingSkill
- strategy-breakout-confirmSkill
- strategy-exhaustion-fadeSkill
- strategy-fitness-heatmapSkill
- strategy-funding-carrySkill
- strategy-liquidity-sweepSkill
- strategy-mean-reversionSkill
- strategy-trend-followSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
No positional ticker — same ticker-agnostic shape as market-macro.
- Very specific: line 100
All sources down → inputs all None, regime.regime="UNKNOWN", errors[] lists every failure.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
market-valuation
SP500 fair-value context via Shiller CAPE z-score. The single asset class with academically validated valuation framing.
When NOT to use
- For a single-ticker trade decision — CAPE is SP500-only cross-asset context, not a directional call on an individual asset. Use market-* / strategy-* skills for the ticker.
- As a standalone trade signal — it is narrate-only by design; no L3 strategy hard-vetoes on CAPE (at most a soft
veto_reasonstag). Treat the regime as background, not a trigger. - For non-SP500 valuation (BTC/oil/DXY) — deliberately out of scope; there is no defensible model shipped.
Quick Start
uv run skills/market-valuation/scripts/run.py --jsonNo positional ticker — same ticker-agnostic shape as
market-macro. Default TTL is 3600s
(CAPE updates monthly, much slower-moving than price); running it
back-to-back is free.
Flags
| Flag | Default | Notes |
--json | human | Emit the ValuationSignal as JSON to stdout. |
--ttl=N | 3600 | In-process cache lifetime in seconds. 0 disables the cache. |
--no-cache | off | Alias for --ttl=0. |
--no-history | off | Skip the ring-buffer append to $XDG_DATA_HOME/market-skills/valuation_history.json. |
Sources
- Shiller CAPE — multpl.com meta-tag scrape (single HTML fetch)
- SP500 spot — yfinance
^GSPCviafast_info
Either source failure lands in errors[] and the corresponding input
is None; the call does not crash.
What it returns
{
"timestamp": "2026-07-07T08:27:46+00:00",
"inputs": {
"sp500": 7537.43,
"cape": 41.97,
"cape_mean_50y": 21.0,
"cape_std_50y": 9.0
},
"regime": {
"cape_zscore": 2.33,
"regime": "OVEREXTENDED"
},
"errors": [],
"incomplete": false,
"regime_note": "Valuation: CAPE 42.0 (+2.33σ) — overextended."
}Regime bands
cape_zscore = (cape − 21.0) / 9.0. Bands:
| z-score | regime |
| ≥ 2.0 | OVEREXTENDED |
| ≥ 1.0 | ELEVATED |
| ≥ −1.0 | FAIR |
| ≥ −2.0 | DEPRESSED |
| < −2.0 | OVERSOLD |
| n/a | UNKNOWN (any source failed) |
The 50y constants are hardcoded in analysis/valuation.py. Spot-check
against Yale's monthly Shiller CSV before bumping.
How L3 strategies consume it
strategy-mean-reversion reads the z-score and attaches a soft
veto_reasons tag — see
strategy-mean-reversion/SKILL.md.
The tag is informational; the LLM agent brain decides whether to act
on it (ADR-0002). No L3 strategy hard-vetoes on CAPE.
Edge cases
- multpl down →
cape=None,cape_zscore=None,regime="UNKNOWN", error recorded. The skill never crashes on a single bad source. - All sources down →
inputsallNone,regime.regime="UNKNOWN",errors[]lists every failure. - The signal is narrate-only. There is no
conviction_modifier()ordirectional_filter()inanalysis.valuation— by design.
Cron / pre-market context
The regime_note is the one-liner for the morning brief. The full
ring buffer is at $XDG_DATA_HOME/market-skills/valuation_history.json
(200-entry cap) and lets the agent brain answer "what was the CAPE
z-score 12h ago?" without re-fetching.
Scope
CAPE is the only fair-value model the skill ships. BTC/oil/DXY regression models are deliberately out of scope — their out-of-sample R² on rolling fits is too low to trust, and a placeholder signal that the LLM agent brain would treat as authoritative is worse than no signal. Reassess if a future analysis demonstrates a defensible statistical case.
Output envelope (AXI)
--json output follows the canonical AXI envelope — {data, count, errors, help[]}. Default schema is the per-skill minimal fields (3-6 essentials); pass --fields=<csv> to project or --full for the full payload. count is the item count, help[] is contextual next-step command templates. Lib.py return shapes (L1Result / L2Result / L3Result / L3Idea / RegimeSignal) are unchanged — the envelope wraps them at the scripts/run.py boundary.
Home view (no-arg mode)
No-arg mode prints the home view from $XDG_DATA_HOME/market-skills/<skill>_last.json (last successful run). Errors are not cached.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

