voice-card
Skill1.3k starsChanged 23 days agoMITView on GitHub
Builds or updates a voice card from a company blog ("extract our blog voice") or how an account or person actually writes, measured from about 8 or more of their real posts (length, casing, emoji, openings, pet phrases, opinions with their source). When there are too few posts, it runs a short interview instead. It ends with a test that checks a draft against the card. The brand's rules always beat the card. Use alone when you already have the account's posts or the person on hand; otherwise run the playbook for the job (e.g. run-organic-social, write-outreach, email-lifecycle).
2 other projects use a version of this.
Trending
More talk lately.about the whole repository
Most recently taken up by
- athina-ai/goose-skillsword for word, first seen Nov 9, 2026
- jacquardlabs/voice-suitetheir own version, first seen Jul 11, 2026
Who's talking about gooseworks-ai/goose-skills
- akhmadilham/pinax-registry“[Skill Proposal]: goose-skills”GitHub · Nov 3, 2026
- sudosubin/agents.nix“agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-20 → 0-unstable-2026-10-23”GitHub · Oct 23, 2026
- gooseworks-ai/gooseworks“Route focused marketing requests to existing playbook steps”GitHub · Oct 22, 2026
- sudosubin/agents.nix“agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-17 → 0-unstable-2026-10-20”GitHub · Oct 20, 2026
- sudosubin/agents.nix“agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-16 → 0-unstable-2026-10-17”GitHub · Oct 17, 2026
The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 20
Talked about on GitHub (20 times).
On GitHub · 20
- Nov 3, 2026[Skill Proposal]: goose-skills — akhmadilham/pinax-registry0 reactions · 1 comment
- Oct 23, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-20 → 0-unstable-2026-10-23 — sudosubin/agents.nix0 reactions
- Oct 22, 2026Route focused marketing requests to existing playbook steps — gooseworks-ai/gooseworks0 reactions
- Oct 20, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-17 → 0-unstable-2026-10-20 — sudosubin/agents.nix0 reactions
- Oct 17, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-16 → 0-unstable-2026-10-17 — sudosubin/agents.nix0 reactions
15 more on GitHub
- Oct 16, 2026[Candidate] gooseworks-ai/goose-skills - large collection (295 SKILL.md files) — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 16, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-12 → 0-unstable-2026-10-16 — sudosubin/agents.nix0 reactions
- Oct 13, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-06 → 0-unstable-2026-10-12 — sudosubin/agents.nix0 reactions
- Oct 6, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-05 → 0-unstable-2026-10-06 — sudosubin/agents.nix0 reactions
- Oct 5, 2026agent-skills.github.gooseworks-ai.goose-skills: 92b02ac → f76cec4 — sudosubin/agents.nix0 reactions
- Oct 5, 2026agent-skills.github.gooseworks-ai.goose-skills: 80b0c5e → 92b02ac — sudosubin/agents.nix0 reactions
- Oct 5, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-04 → 0-unstable-2026-10-05 — sudosubin/agents.nix0 reactions
- Oct 4, 2026agent-skills.github.gooseworks-ai.goose-skills: 0-unstable-2026-10-03 → 0-unstable-2026-10-04 — sudosubin/agents.nix0 reactions
- Oct 4, 2026agent-skills.github.gooseworks-ai.goose-skills: af5944c → 770e3c2 — sudosubin/agents.nix0 reactions
- Oct 3, 2026agent-skills.github.gooseworks-ai.goose-skills: init at 0-unstable-2026-10-03 — sudosubin/agents.nix0 reactions
- Oct 2, 2026Preserve angle evidence through local video script planning — gooseworks-ai/gooseworks0 reactions
- Aug 5, 202622 skills have links.github pointing at something that is not a skill directory — gaia-research/gaia-skill-tree0 reactions · 7 comments
- Jul 16, 2026Skill submission: goose-skills (growth/GTM library by GooseWorks) — numman-ali/n-skills0 reactions
- Jul 16, 2026Add goose-skills to Collections — BehiSecc/awesome-claude-skills0 reactions · 1 comment
- May 3, 2026Import skill: linkedin-post-research — jettyio/agent-runbooks0 reactions
Other versions2 projects use a version of this.
Word for word · 1
- athina-ai/goose-skills★ 1.3k100% same
Edited · 0
None found.
Wrote their own version · 1
- jacquardlabs/voice-suite★ 3same 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 repository180 other files it gives its agents.
- goose-adsSkill
- goose-product-photosSkill
- goose-video-localSkill
- goose-videoSkill
- gooseworksSkill
- make-custom-videoSkill
- ad-policy-checkSkill
- analyze-performance-call-and-learnSkill
- analyze-performance-diagnoseSkill
- analyze-performance-intakeSkill
- analyze-performance-rank-and-readSkill
- analyze-performance-revenue-joinSkill
- analyze-performanceSkill
- claims-gateSkill
- email-lifecycle-broadcast-plannerSkill
- email-lifecycle-flow-writerSkill
- email-lifecycle-lifecycle-auditSkill
- email-lifecycle-offer-mathSkill
- email-lifecycle-send-checkSkill
- email-lifecycleSkill
- honest-reviewSkill
- improve-search-visibility-citation-checkSkill
- improve-search-visibility-entity-footprintSkill
- improve-search-visibility-fix-writerSkill
- improve-search-visibility-page-and-foundation-checkSkill
- improve-search-visibility-question-setSkill
- improve-search-visibilitySkill
- improve-search-visibility-store-listing-auditSkill
- make-content-content-briefSkill
- make-contentSkill
- make-content-source-to-unitsSkill
- make-content-two-pass-editSkill
- make-static-ads-ad-copySkill
- make-static-ads-claims-extractSkill
- make-static-ads-composeSkill
- make-static-ads-concept-gridSkill
- make-static-ads-copy-variantsSkill
- make-static-ads-find-referencesSkill
- make-static-ads-fix-rejectedSkill
- make-static-ads-graphic-requestSkill
- make-static-ads-render-reviewSkill
- make-static-adsSkill
- marketing-data-accessSkill
- marketing-guideSkill
- outcomes-ledgerSkill
- plan-campaign-brief-and-assetsSkill
- plan-campaign-budget-and-testsSkill
- plan-campaign-channel-decisionSkill
- plan-campaign-goal-chainSkill
- plan-campaignSkill
- research-audience-account-sourcingSkill
- research-audience-fit-definitionSkill
- research-audience-people-and-contactsSkill
- research-audience-score-segment-qaSkill
- research-audience-segment-passSkill
- research-audience-signals-and-hooksSkill
- research-audienceSkill
- research-competitors-category-passSkill
- research-competitors-edge-casesSkill
- research-competitors-rival-passSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
If the brand marker says voice: provisional, every card built on it is provisional too.
- Distinctive: line 70
Every mechanic within the card's range.
- Distinctive: line 71
Swap test: put a competitor's name in.
≈ “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
voice-card
The brand voice (kit voice plus the brand's rules: every dont and must in its learnings) says what the brand may say and how it sounds overall. A voice card says how one account or person actually writes: lowercase or not, how long, which emoji, how they open. Adjectives ("warm, playful") don't stop generic copy; a card measured from real posts does.
Choose the source
Used alone: first do the marketing-guide skill (../marketing-guide/SKILL.md) §1–2 (connection, brand and brain rules). Called from a writing job: reuse its setup. A company-blog or long-form voice ask follows references/blog-voice.md and returns; social posts and personal voice follow Build below. A blog guide is usable without releasing the full brand intake playbook.
Where it lives
- One file per account or person:
brand/voices/<handle>.md, brand coworker scope (coworker_agent_idfrom thegooseworks:brand_readlist; no coworker → default workspace, path prefixedbrands/<brand-slug>/). - Handle: lower-case, hyphens, no
@:brand(the brand's own voice across its accounts),ig-<account>,tiktok-<account>,linkedin-<first-last>,founder-<first-last>,blog-<brand-slug>(company long-form writing). One card per account where mechanics differ; accounts that write the same way sharebrand. - Read before you write (
gooseworks:file_read;file_writereplaces the file). Save with thesave-to-brainskill (../save-to-brain/SKILL.md) (versioned: supersede, titleVoice card <handle> — <Brand> — <YYYY-MM-DD>, tags[voice-card, voice-<handle>]) so it is findable from any host. The tags name this atom, not the playbook that ran it: for save-to-brain's supersede rule, the creator is the first tag (voice-card), so any writer's newer card supersedes an older one.
Precedence (non-negotiable)
- The brand's rules win: every
dontandmust(never-say, banned words, terminology, not public), the claims contract (theclaims-gateskill (../claims-gate/SKILL.md)), and the rules in the confirmed brand voice (what it never does, how it treats customers). - A person's or account's card wins on style: mechanics, openings, lexicon, humour. The brand voice's style gives way to a founder's own card when writing as that founder.
- Real posts beat any description of the voice. Example lines in the kit voice are evidence of style only; a claim inside them is not proof.
- If the brand marker says
voice: provisional, every card built on it is provisional too.
Read
gooseworks:file_read brand/voices/<handle>.md. Missing, or built more than 90 days ago, or older than the account's last 8 posts → build or update. A card marked status: provisional is usable, and drafts from it say so.
Build
- Sources, by weight:
- the account's own real posts: TikTok/Instagram from
gooseworks:brand_readsections: ["organic"](own_posts); other platforms through the proxy (themarketing-data-accessskill,../marketing-data-access/SKILL.md) or, when not reachable, 10–20 posts the human pastes. For a founder, a few of their replies and comments too (the least polished, so the truest voice); - the kit
voice,tone, and learnings (do/dont/must); - the buyers' words (research-audience's voice-of-customer bank,
research/audience/voc-bank.md) for hooks only; it is not the brand's voice.
- the account's own real posts: TikTok/Instagram from
- Minimum corpus: about 8 real posts. Below it, run a 5-minute voice interview instead (or take a voice note via
gooseworks:media_upload+gooseworks:media_analyze): 3 things you've written that sound like you; 3 words you'd never use; who you write for; a belief about the category others don't share; what makes you cringe in other brands' posts; emoji yes/no and which; lowercase or proper; one story you tell often; off-limits topics; who approves posts in your name. Save the cardstatus: provisional. - Measure, with numbers, not adjectives: words per sentence and per post (median, range); casing; line breaks; rates of em-dash, ellipsis, exclamation and question marks; emoji rate and the exact set; symbols used for words; fragment and typo tolerance; opening moves with 5–10 verbatim first lines; closings; pet phrases and nicknames; jargon and swearing level; how they name customers and rivals; humour; for people who take positions, a stance ledger (each opinion with its source post); never-says (moves absent from the corpus that AI reaches for); top 5 and bottom 5 posts against the account median with the likely why. Leave out captions that come back cut off.
- Write the card:
Voice card — <handle> · <Brand> · built <YYYY-MM-DD> from <n> posts (<sources>) · status: <confirmed | provisional>
Rules with numbers: …
Openings that are theirs: <5 verbatim>
Pet phrases: … · Never-says: …
Stance ledger: <opinion> — <source post> (people only)
Humour: …
Brand rules that apply (from learnings): …
5 real posts, annotated (why each one sounds like them)
3 wrong → right rewrites (a generic draft vs the same idea in their voice)
What performed: top 5 / bottom 5 with the likely why- Confirm. Show the card ("does this sound like you?"). A person's card needs that person's yes; until then it is
provisional. Their corrections go into the card in their words.
Update
Append new posts, re-measure when at least 8 new ones exist, keep the stance ledger growing, bump the date, save a new version. Never drop a confirmed rule without the person's yes.
Match test (on every draft before it is shown)
- Every mechanic within the card's range; emoji set, casing and punctuation habits match exactly.
- Swap test: put a competitor's name in. If the draft still reads true, add the detail only this brand or person could say.
- Read aloud: would they say it?
- Line-up: mix the draft with three real posts; if someone holding only the card can pick out the draft, rewrite it.
- Then the
claims-gateskill (../claims-gate/SKILL.md) on the draft.
Named people
Never invent first-person experience, a habit, product use, a number or an opinion for a founder, ambassador, employee or customer. An opinion must trace to the stance ledger or to their own words in this conversation. Leave a marked gap ([NAME: the time a customer caught a bug before you did]) for material they haven't given; a gap with no material behind it is cut.
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.

