Skip to content
Skills Library
Finance & accounting · Analysis

value-complex

/value-complex

Avantis value-factor tracker — small-cap (AVUV) and large-cap (AVLV) value in one read, straight from TickerTrace's per-fund holdings. Groups by fund tier and by position lifecycle (new/exited, conviction tilt, up-streaks), ranked by weight, and surfaces the sector themes both funds agree on. Use when the user asks "what's the value factor doing", "what did AVUV/AVLV add", "new adds in value", "what are the value funds buying", "value complex", or wants the small-vs-large value read.

Licence
MIT
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/gather.mjs

What it does and when to use it

Avantis value-factor tracker — small-cap (AVUV) and large-cap (AVLV) value in one read, straight from TickerTrace's per-fund holdings. Groups by fund tier and by position lifecycle (new/exited, conviction tilt, up-streaks), ranked by weight, and surfaces the sector themes both funds agree on. Use when the user asks "what's the value factor doing", "what did AVUV/AVLV add", "new adds in value", "what are the value funds buying", "value complex", or wants the small-vs-large value read.

Triggers from the description

whatwhat did AVUV/AVLV addnew adds in valuewhat are the value funds buyingvalue complex
Original author description

Avantis value-factor tracker — small-cap (AVUV) and large-cap (AVLV) value in one read, straight from TickerTrace's per-fund holdings. Groups by fund tier and by position lifecycle (new/exited, conviction tilt, up-streaks), ranked by weight, and surfaces the sector themes both funds agree on. Use when the user asks "what's the value factor doing", "what did AVUV/AVLV add", "new adds in value", "what are the value funds buying", "value complex", or wants the small-vs-large value read.

How it works

  1. What it groups, and why
  2. How to run it
  3. Present it to Mike
  4. Notes / gotchas
Original SKILL.md headings · 79 lines, 626 words
SKILL.md preview
---
name: value-complex
description: >-
  Avantis value-factor tracker — small-cap (AVUV) and large-cap (AVLV) value in
  one read, straight from TickerTrace's per-fund holdings. Groups by fund tier and
  by position lifecycle (new/exited, conviction tilt, up-streaks), ranked by
  weight, and surfaces the sector themes both funds agree on. Use when the user
  asks "what's the value factor doing", "what did AVUV/AVLV add", "new adds in
  value", "what are the value funds buying", "value complex", or wants the
  small-vs-large value read.
---

# Value Complex — Avantis small + large value, by weight

This skill reads Avantis's two flagship value ETFs straight from TickerTrace's
**per-fund** endpoint (`/fund/<TICKER>`) and lays out what changed under the hood,
grouped the way the value factor actually moves:

- **AVUV** — small-cap value ($12.5B, ~794 holdings) — the flagship.
- **AVLV** — large-cap value ($3.2B, ~272 holdings).

> This is the per-fund holdings view that the daily **stock-recap** skill does
> *not* pull. stock-recap only hits TickerTrace's cross-fund aggregates
> (`/briefing`, `/institutional`, `/divergences`). This skill is the deep,
> by-weight, per-fund value read.

## What it groups, and why

For **each fund** (small tier → large tier), three lifecycle buckets:

1. **🆕 New / Exited** — positions TickerTrace flags `type=NEW` or `REMOVED`.
   Passive Avantis funds rarely open or close a name day-to-day, so when they do
   it's meaningful. This is the literal "new adds."
2. **📈 Conviction tilt** — active over/under-weighting, **inflow-stripped.**
   Every name in an inflow day shows a positive `sharesDelta` (new money buys the
   whole book pro-rata), so raw adds are noise. We compute each name's share growth
   `sharesDelta/previousShares`, take the **fund-wide median as the inflow tide,**
   and rank by the *excess* over that tide. Positive excess = the fund is genuinely
   leaning *into* the name beyond mechanical inflow; negative = leaning out.
3. **🔥 Up-streaks** — names on multi-day winning runs (TickerTrace `streaks`).
   This is the cleanest momentum signal — independent of fund mechanics entirely.

Then the payoff, **🔗 cross-tier synthesis:**
- **Sector convergence** — sectors that are streaking *and/or* tilting up in
  **both** the small and large fund. (Exact-ticker overlap is rare because the
  funds hold different cap tiers, so convergence is read at the sector/theme
  level — e.g. "transports leading in both.")
- **Flow tell** — all-buys with zero trims = **inflows into value** (creations,
  risk-on); a genuine mix of adds and trims = active rebalancing.

## How to run it

```bash
node "$HOME/.claude/skills/value-complex/scripts/gather.mjs"
```

- Writes `runs/<date_time>/report.md` + `raw/fund_AVUV.json`, `raw/fund_AVLV.json`.
- Prints the report to stdout and a final JSON line with `{reportPath, rawDir}`.
- No key needed — `/fund/<TICKER>` is public on TickerTrace. Presents a browser
  User-Agent (the edge WAF 403s a bare Node UA). ~5–10s.
- Override the base with `TICKERTRACE_API_URL`; funds with `VC_FUNDS=AVUV,AVLV,AVMV`.

## Present it to Mike

Read the generated `report.md` and give a tight read, in this order:

1. **The flow tell first** — are both funds taking inflows (value getting bought)
   or net trimming? That frames everything.
2. **New / Exited** names per fund — rare, so always call them out by name.
3. **Conviction tilt** — the inflow-stripped over-weights. These are the names the
   fund is actually leaning into, not just buying with the tide. Name the top 3–4
   per tier and what sector they're in.
4. **Streaks** — the momentum leaders, longest runs first.
5. **The cross-tier theme** — the one or two sectors strong in *both* small and
   large value. This is the headline ("the whole value complex is leaning into X").
   Tie it to the tape: what's it rotating *out of* (usually mega-cap growth).

## Notes / gotchas

- **`weightDelta` is not a clean signal on its own** — it blends price drift with
  share-count change. The report leads with the **inflow-stripped excess** instead;
  it shows weightDelta as secondary context only. Don't present weightDelta as
  "conviction" without the excess check.
- **Data is daily and can lag** — the report prints TickerTrace's `asOfDate`;
  surface it so Mike knows how fresh it is.
- **Cross-tier convergence is sector-level, not ticker-level** — small and large
  funds rarely share a ticker; agreement shows up as a shared *theme*.
- Each run is a point-in-time snapshot under `runs/`; nothing is overwritten and
  old folders are safe to delete (gitignored under `.claude/`).
Files in this package (2)
  • SKILL.md 5 KB
  • scripts/gather.mjs 11 KB

Versions

The database has no other skills named value-complex.

Database snapshot: 13.11.2026 · package version 480e32b5af74 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100grad-fama-french
    Apply the Fama-French three-factor model to decompose asset returns into market, size, and value factors. Use this skill when the user needs to explain cross-sectional return differences, evaluate fund performance beyond CAPM alpha, assess small-cap or value tilts in a…
  • 100institutional-holdings-13f
    Show what a US institutional investor owns and what it changed last quarter, from its 13F filings with the SEC - top holdings by value and weight, new positions, the largest increases and decreases, and exits. Use when the user asks what a hedge fund or well-known investor…
  • 100carta-portfolio-ownership
    Show investment firms their ownership by portfolio company and by underlying fund: shares held, outstanding and fully diluted ownership %, and share counts, as of today or a past date. Answers in chat, or builds a live ownership table in Cowork with each company expanded into…
  • 100artha-xray
    Finds stock and sector overlap across an Indian mutual fund portfolio — which funds hold the same stocks, how many rupees you really have in each stock and sector through all funds combined, and which fund pairs largely duplicate each other. Use when the user asks about fund…
  • 10013f-fund-analysis
    Analyze SEC 13F fund holdings data given an accession number. Use this skill when you have an accession_number and need to extract fund details including AUM, number of holdings, and detailed position data. Works with Q2 and Q3 2025 filings.
  • 100factor-investing
    Apply factor models to portfolio construction and fund evaluation, from CAPM through the Fama-French 3- and 5-factor models plus momentum. Use when the user asks about 'Fama-French', 'value factor', 'smart beta', 'factor tilt', 'momentum exposure', or the 'factor zoo', wants to…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.