# Finfluencer Audit

> |

- **Type:** Skill
- **Install:** `agentstack add skill-faust-donf-finfluencer-audit-finfluencer-audit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Faust-Donf](https://agentstack.voostack.com/s/faust-donf)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Faust-Donf](https://github.com/Faust-Donf)
- **Source:** https://github.com/Faust-Donf/finfluencer-audit

## Install

```sh
agentstack add skill-faust-donf-finfluencer-audit-finfluencer-audit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Finfluencer Audit

Most "this guru has a 70% win rate" claims collapse under two questions: *win
rate on what fraction of their content?* and *versus what baseline?* This skill
answers both, reproducibly.

## Non-negotiables

1. **Freeze before you score.** Write the sample list and the claim ledger to
   disk *before* loading a single price. Otherwise you will unconsciously read
   ambiguous headlines in the direction the market went.
2. **Always report a baseline.** A hit rate without `always-long` next to it is
   marketing, not evidence. In a bull market, "just hold it" often beats the
   guru.
3. **Report the falsifiable rate.** If only 40% of videos contain a checkable
   claim, say so in the headline. Accuracy on a self-selected 40% is not
   accuracy.
4. **Right-censor, don't guess.** A 12-month call made 3 months ago is
   unresolved, not wrong.
5. **Grade the evidence tier.** Coding from titles is much weaker than coding
   from transcripts. Never let the reader assume you had transcripts.
6. **No accusations.** Report what was said and what the market did. Flag
   unverifiable credentials as *unverified*, not as *false*.

## Pipeline

```
fetch_archive → build_sample → fetch_content → code_claims
                                                     ↓  (freeze)
                                   report ← backtest ← fetch_market
```

Each step writes JSON into a run directory so any number can be traced back to
a video URL.

### 1. Build the sampling frame

```bash
python3 scripts/fetch_archive.py --platform bilibili --uid 25270495 \
  --since 2023-08-06 --until 2026-08-06 --out runs/
```

Bilibili's space archive needs a WBI signature, `dm_img_*` anti-bot fields, and
buvid cookies all at once — see [references/platforms.md](references/platforms.md)
for the failure codes and what each one means. For YouTube use
`--platform ytdlp --channel-url ...`.

### 2. Draw a pre-registered sample

```bash
python3 scripts/build_sample.py --run runs/ --margin 0.08 --seed 20260806 --two-phase
```

Sample size is Cochran's formula with a finite-population correction. Use
`--two-phase` when most titles are chit-chat: it screens for directional
language and oversamples that stratum, which is the difference between 42
scoreable claims and ~90 from the same budget.

Publish `sample.json` before continuing. Substitute only from
`alternates.json`, and only for deleted or unreadable videos.

### 3. Collect evidence

```bash
python3 scripts/fetch_content.py --run runs/ --transcribe whisper --transcribe-limit 30
```

Subtitles first, audio transcription second, title-only last. Check
`content_meta.json` — if `subtitle` + `transcript` coverage is near zero, your
audit is a headline audit and the report must say so.

### 4. Code claims, then freeze

```bash
python3 scripts/code_claims.py --run runs/ --dual-channel
```

Direction is resolved **per asset per clause**, because titles like
「原油暴跌，黄金后市可期」 are bearish oil *and* bullish gold. `--dual-channel`
runs a second stricter coder and reports Cohen's kappa; below 0.6, say plainly
that coding noise rivals the measured effect.

Coding rules and the claim taxonomy live in
[references/coding-protocol.md](references/coding-protocol.md).

### 5. Get prices

```bash
python3 scripts/fetch_market.py --run runs/ --start 2023-07-01 --end 2026-08-07
```

Every free source fails sometimes; the script walks Yahoo → Stooq → FRED and
records which one answered. See [references/market-data.md](references/market-data.md).

### 6. Backtest

```bash
python3 scripts/backtest.py --run runs/ --as-of 2026-08-06
```

Entry is the first close on or after the publish date. Outputs hit rate with a
Wilson interval, signed returns, MFE/MAE, and three baselines, cut by horizon,
asset, direction, and claim type.

### 7. Report

```bash
python3 scripts/report.py --run runs/ --name "BOSS墨" --profile-url https://space.bilibili.com/25270495/
```

Writes `report.md` and `canvas_payload.json`. For an interactive deliverable,
render the payload with the canvas skill.

## Beyond price accuracy

A reliability verdict needs more than a hit rate. Also check, and cite sources
for each:

- **Credentials** — is the self-described qualification independently findable
  (regulator registry, patent/trademark office, employer)? Record `verified`,
  `not_found`, or `unverified_hearsay` — never `false` without documents.
- **Track record** — brokerage statements or third-party audit, or hearsay?
- **Conflicts** — paid courses, private groups, referral links, token bags.
- **Error handling** — do they publish corrections, or only "as planned" recaps?
  A high `post_hoc_review` count with a low `ex_ante_prediction` count is a tell.
- **Selection** — do they delete losing calls? Compare archive count against the
  platform's reported total.

## Pitfalls

Read [references/pitfalls.md](references/pitfalls.md) before your first run. The
short version:

| Trap | Consequence |
| --- | --- |
| Whole-title direction voting | Multi-asset calls get inverted |
| No baseline | Bull-market drift reads as skill |
| Counting unmatured calls as misses | Recent calls drag the score down |
| Title-only coding presented as analysis | Overstated confidence |
| Sampling without a seed | Nobody can reproduce you |
| Scoring before freezing the ledger | Hindsight leaks into coding |

## Output contract

A finished audit answers, in this order:

1. What fraction of content was checkable at all?
2. Of that, what was the hit rate, with a confidence interval?
3. How does it compare to always-long, coin flip, and trend following?
4. Which specific calls hit and missed, with links?
5. What is unverifiable about the creator's own claims?
6. What would change the verdict?

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Faust-Donf](https://github.com/Faust-Donf)
- **Source:** [Faust-Donf/finfluencer-audit](https://github.com/Faust-Donf/finfluencer-audit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-faust-donf-finfluencer-audit-finfluencer-audit
- Seller: https://agentstack.voostack.com/s/faust-donf
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.