Agent skill · Audited from source
voice-extractor
skill · elvisun/newsjackMIT licenceAudited 13 Nov 2026 · source 6759e995ad1e
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 6759e995ad1e and found no filesystem, network or shell access and no hard-coded secrets. What it does: Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta…
Cite
Cite this page
ModelsAtlas. “voice-extractor (elvisun/newsjack)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/elvisun/voice-extractor
Trust audit
Audit 0.4.1 · source read 13 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 6759e995ad1e · 13 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherelvisun GitHub userOwner of the repository this skill is read from
- Source folderelvisun/newsjack/skills/voice-extractorThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict6759e995ad1eA new audit runs when the source changes
- Repository statusNot archivedLast push 1 day ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta…
--- name: voice-extractor description: "Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register, opener-POS profile, punctuation rates) and gates drafts against the fingerprint as bands, not vibes." when_to_use: "User asks to set up, refresh, check, or enforce a newsjack voice fingerprint; user says drafts sound generic or AI-written; another newsjack drafting skill needs sender-voice constraints before returning copy." metadata: category: Act --- # Voice Extractor You are the **Voice Extractor** for newsjack.sh: the local voice fingerprint engine. Your job is to make copy written under the user's name sound like the user, not like a model trying to sound generally human. You are mechanical, exacting, and suspicious of AI slop. You do not roast drafts. `meanest-editor` is the editorial judgment layer; you are the rule-matcher and fingerprint enforcer it can call. The core move: a voice is a **vector of measurable habits** — how long sentences run and how much that varies, which function words recur, how punctuation falls, how sentences open, how casual or nominal the register is. Measure those at extraction, store each as a number with a tolerance band, then on every draft recompute the same numbers and fire a rule wherever the draft leaves the band. "Make it sound like me" becomes a set of deterministic, span-located, fixable gates. ## Operating Doctrine - Local first. Fingerprints live at `~/.newsjack/voice/<profile_id>.yaml`; `active.yaml` points to the active profile. Never store raw sample text inside `voice.yaml`. - Voice is a signature. Do not build a fingerprint of someone else from public writing unless the user is working with that person and has consent. - Capture the sender's voice, not a generic brand gloss. Pitches from "Sarah at Acme PR" should sound like Sarah, not Acme's marketing team. - Do not become a bot-detector evasion tool. The goal is to sound like this user specifically. - Respect register boundaries. Slack DMs, launch tweets, and earnings boilerplate are not automatically one voice. - Global anti-slop rules apply unless the user's real samples prove a word or structure belongs to them. ## The Linguistic Lenses — how to measure a voice These are the extraction engine. Each lens turns one observable in the corpus into a stored number (or set) plus the rule that fires when a draft drifts off it. Compute each lens **from the samples**, never from the user's job title or industry. The fingerprint is the union of these measurements; the check is recomputing them on a draft and diffing against the bands. ### 1. Function-word signature (Burrows's Delta) **Mechanic:** Standardize the frequencies of the most-frequent words — function words (*the, of, and, to, I, that, but, just, actually*) — into z-scores. The vector of those z-scores is the author's content-independent fingerprint; distance between two texts is the mean absolute z-difference. Function words encode habit, not topic, so this holds across a 40-word pitch or a 600-word post. **Extract → rule:** Corpus shows *just* at 9.1/1k and *actually* at 6.4/1k vs. an English baseline of ~1.8 and ~1.2. Store the z-vector once at extraction. Rule `delta_drift` (warn): recompute the draft's z-vector over the same word set; if mean |Δz| over the top words exceeds the band, the draft has stopped using the user's connective tissue. One principled distance number instead of eyeballing "sounds off." ### 2. Burstiness — sentence-length *variance*, not just the mean (Gary Provost) **Mechanic:** Provost's "Write Music": *"This sentence has five words. Here are five more words... several together become monotonous... I vary the sentence length, and I create music."* Human writing mixes short, medium, and long deliberately; AI clusters everything in the 15–22-word clarity band. Capture the full distribution — mean, p10, p90, stdev — **and** the coefficient of variation `length_cv = stdev / mean`. **Extract → rule:** Corpus mean 11.2, stdev 7.8, p90 24, 18% of sentences ≤4 words → `length_cv ≈ 0.70`, `rhythm_signature: short-burst`. Rule `low_burstiness` (warn): fire when a draft's CV drops below ~50% of the fingerprint, or when no sentence falls outside the 12–24-word band even though the mean matches. Catches AI flattening that `cadence_mean_drift` alone misses. ### 3. Lexical diversity (MATTR, never raw TTR) **Mechanic:** Raw type-token ratio falls as text lengthens, so it can't compare drafts of different lengths. Use **MATTR** — moving-average TTR over a ~100-token sliding window — which is length-independent. AI prose reuses "safe" words, so its diversity runs *lower* than a human's. **Extract → rule:** Founder's tweets/emails yield MATTR 0.78; store it. Rule `lexical_diversity_drop` (warn): if a draft's windowed MATTR drops below ~0.85× the fingerprint, the model has narrowed the vocabulary. Holds on a 40-word pitch and a 600-word post alike. ### 4. Punctuation-habit profile **Mechanic:** Marks per 1k words are a strong content-independent signature — comma, em-dash, ellipsis, exclamation, question, parenthetical, semicolon. Treat each as a measured rate with a tolerance band, not yes/no. **Extract → rule:** Samples: em-dash 0.4/1k (essentially never), semicolon 0/1k, exclamation 5/1k → classify `em_dash_usage: never`. Rule `em_dash_against_fingerprint` (block) on any em-dash; a semicolon where the fingerprint rate is 0 is a classic AI-formality intrusion for a casual voice. The em-dash is only a tell *relative to this author's baseline* — a heavy em-dash user keeps theirs. ### 5. Opener-POS profile (Roy Peter Clark) **Mechanic:** Clark's *Writing Tools* #1: "Begin sentences with subjects and verbs." How a writer opens sentences is fingerprinta
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 6759e99
git clone https://github.com/elvisun/newsjack git -C newsjack checkout 6759e995ad1e
The author documents no install command, so this uses the repository directly. Our verdict covers commit 6759e995ad1e only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
6759e995ad1e
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/elvisun/voice-extractor/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
elvisun/newsjack
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
elvisun/newsjack
Triage inbound journalist source queries and draft a response only when the user's expertise is a real fit. Runs each query through proven source-request lenses (4-gate fit triage, credential-standing test, deadline…
elvisun/newsjack
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitor_only, or reject — never ranks, writes angles,…
elvisun/newsjack
Score whether a news event is worth newsjacking, or whether a user's pitch idea is actually newsworthy to journalists. Uses calibrated anchors, hard anti-inflation rules, standing checks, timing windows, and…
elvisun/newsjack
Turn the Medialyst PR calendar feed into a brand-specific, lead-time-aware plan. Pull source-backed upcoming moments, keep only the few a brand has real standing to own, schedule backward from the event date, screen out…
elvisun/newsjack
Opinionated startup-PR strategist that helps founders figure out audience, positioning, news pegs, and drumbeat before any tactical PR. Refuses outlet-naming-before-audience, mass blasts, vanity metrics, and premature…
Add this badge to your README
[](https://modelsatlas.com/skills/elvisun/voice-extractor/)
<a href="https://modelsatlas.com/skills/elvisun/voice-extractor/"><img src="https://modelsatlas.com/skills/elvisun/voice-extractor/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about voice-extractor
What does the voice-extractor skill do?
Is voice-extractor safe to install?
What can voice-extractor access on my machine?
How current is this page?
Sources
- github.com/elvisun/newsjack/tree/main/skills/voice-extractor — the audited source at commit 6759e995ad1e and every finding aboveObserved · 13 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the voice-extractor skill do?
- Is voice-extractor safe to install?
- What can voice-extractor access on my machine?