voc-synthesize

voc-synthesize is a skill for Claude Code from aatirar/voc-claude-skills. It costs 77 tokens per session (1,423 once invoked), scanned A, original, MIT.

A set of instructions for developing Claude Code skills in a repository. It defines naming, file structure, metadata, permitted tools, and checks for documenting limitations.

In plain words
What is it for?
Use it when creating or reviewing skills under .claude/skills, especially their frontmatter, allowed tools, repository structure, and required “what this gets wrong” sections.
Why use it?
It reduces inconsistent skill files and helps prevent skills from using undeclared or overly broad tools.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/synthesize.js outputs/voc/synthesis/clusters.json.

Good fit Use it when creating or reviewing skills under .claude/skills, especially their frontmatter, allowed tools, repository structure, and required “what this gets wrong” sections.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/aatirar/voc-claude-skills
agentmods
npx agentmods add skills/aatirar/voc-claude-skills/voc-synthesize

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for voc-synthesize

README.md
[![agentmods](https://agentmods.dev/badge/skills/aatirar/voc-claude-skills/voc-synthesize/github.svg)](https://agentmods.dev/skills/aatirar/voc-claude-skills/voc-synthesize)
Your own site
<a href="https://agentmods.dev/skills/aatirar/voc-claude-skills/voc-synthesize"><img src="https://agentmods.dev/badge/skills/aatirar/voc-claude-skills/voc-synthesize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for voc-synthesize

Your own site · 80×15
<a href="https://agentmods.dev/skills/aatirar/voc-claude-skills/voc-synthesize"><img src="https://agentmods.dev/badge/skills/aatirar/voc-claude-skills/voc-synthesize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01423
Opus 5 $0.00039 $0.00711
Sonnet 5 $0.00015 $0.00285
Haiku 4.5 $0.00008 $0.00142

Measured 11d ago against content hash a0166a85743e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

voc-synthesize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/voc-synthesize/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voc-synthesize — Cross-Source Pattern Detection

One mention is an anecdote. Three mentions across three different channels is a pattern. That distinction is the entire product, and this skill is built so it cannot be quietly relaxed.

Clustering is a judgment task, so subagents do it. Counting is not, so code does it. The confirmation rule lives in scripts/synthesize.js reading config/thresholds.json, and nowhere else. If you find yourself reasoning about whether something "feels confirmed," you have left the rule behind.

Requires

What Value
Input outputs/voc/profiled/*.json, plus the call analysis and review briefs
Config config/thresholds.json
Cost Subagent tokens. Five clustering agents per run.

Phase 1 — Gather

Collect everything in the window (default from windows.default_days):

Source Path
Profiled signals outputs/voc/profiled/*.json
Call intelligence outputs/calls/analysis/call-intelligence-*.md
Review briefs outputs/voc/sources/reviews/brief-*.json
Chat, notes, CRM, surveys, tickets outputs/voc/sources/<channel>/*

Do not read the quarantine folder. Tier-U signals are excluded by design.

Report which sources were empty. A source that returned nothing because its connector is broken looks identical to a source where nothing happened, and the difference matters — say which you believe it was and why.


Phase 2 — Cluster in parallel

Spawn one subagent per dimension, all in a single message:

pain · request · praise · objection · competitive

Each subagent receives the full corpus and returns clusters for its dimension only:

Group signals in the corpus below into themes for the "<dimension>" dimension.

Cluster on underlying meaning, not wording. "Export is slow", "downloads time out"
and "can't get data out for big events" are ONE theme. Err toward merging: two
themes that should have been one is a worse error than one theme that should have
been two, because splitting hides frequency.

Return ONLY this JSON:
{"clusters":[{
  "theme": "short specific name, written as the customer would recognize it",
  "dimension": "<dimension>",
  "signals": [{"channel":"...","weight_tier":"...","company":"...",
               "date":"YYYY-MM-DD","verbatim":"exact quote","source_file":"..."}]
}]}

Rules:
- Copy verbatim quotes EXACTLY. Do not clean up grammar or trim for length.
- Every signal keeps its original channel and weight_tier. Do not reassign them.
- Do not invent signals to strengthen a cluster.
- A signal may appear in only one cluster within your dimension.
- If a quote is ambiguous between two themes, put it in the more specific one.
CORPUS:
[...]

Read the full file on GitHub · 160 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 160 lines · 77 tokens per session scan A a0166a85743e

Subscribe to this mod's changes

voc-synthesize is a skill published in the GitHub repository aatirar/voc-claude-skills (0 stars, last pushed 25d ago), licensed MIT. It adds 77 tokens to every session and 1,423 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

bdr-enablement-generator

Generates account research briefs, personalized outreach sequences, persona-specific talk tracks, and objection handling frameworks for B2B SaaS BDR teams. Use when preparing BDR outreach for target accounts, building prospecting sequences, creating call scripts, developing objection responses, onboarding new BDRs, or…

Stallin-Sanamandra/b2b-saas-marketing-skills · 131 tokens

competitive-battlecard-generator

Generates and maintains competitive battlecards from win/loss data, competitor intel, G2 reviews, and sales feedback. Use when building battlecards for a specific competitor, updating existing battlecards with new intel, preparing BDRs or AEs for competitive deals, analyzing win/loss patterns against a competitor, or…

Stallin-Sanamandra/b2b-saas-marketing-skills · 153 tokens

marketing-ops-sop-generator

Generates standard operating procedures for B2B SaaS marketing operations: campaign naming conventions, UTM governance, tool administration, workflow QA, data hygiene, lead routing, and incident response playbooks. Use when setting up or auditing marketing ops processes, onboarding a new marketing ops hire…

Stallin-Sanamandra/b2b-saas-marketing-skills · 160 tokens

abm-program-orchestrator

End-to-end ABM program design and orchestration for B2B SaaS mid-market and enterprise motions. Use when building a target account list, designing account tiering criteria, planning ABM channel orchestration, coordinating BDR outreach with marketing campaigns, defining ABM measurement frameworks, or running an ABM…

Stallin-Sanamandra/b2b-saas-marketing-skills · 148 tokens

ceo-monthly-revenue-report-generator

Generates the monthly revenue-accountable marketing report that B2B SaaS marketing leaders deliver to CEOs, CFOs, executive teams, and boards. Use when preparing the monthly CEO report, drafting the marketing section of a board deck, defending budget decisions, diagnosing pipeline gaps, or transitioning marketing from…

Stallin-Sanamandra/b2b-saas-marketing-skills · 121 tokens

account-research-brief-generator

Generates sourced, BDR-ready account research briefs for named target accounts in B2B SaaS ABM and outbound motions. Use after a target account list is built and before outreach sequences are written. Best for Tier 1, Tier 2, and intent-qualified accounts where BDRs need a clear "why this account, why now, why this…

Stallin-Sanamandra/b2b-saas-marketing-skills · 122 tokens