What is antwork-ideas?

A skill for generating social-media content ideas based on an account's past performance, writing style, brand context, and goals.

Use it when planning posts, hooks, or topics for social media, especially when you want ideas based on previous high-performing content.

It avoids generic brainstorming by grounding ideas in posts that have already worked for that account and in its established voice.

antwork-ideas — Skill for Claude Code by iker-gonzalez

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add iker-gonzalez/antwork-skills --skill antwork-ideas

Clone the repo

git clone --depth 1 https://github.com/iker-gonzalez/antwork-skills

Made for: Claude Code.

Or install antwork-skills, the plugin that ships this one along with the rest of its 12 skills, 5 agents, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-ideas/github.svg)](https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-ideas)

Your own site

<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-ideas"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-ideas/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-ideas"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-ideas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 683 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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.00683
Opus 5	$0.00051	$0.00342
Sonnet 5	$0.00020	$0.00137
Haiku 4.5	$0.00010	$0.00068

Measured 10d ago against content hash 0a156959b26c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

antwork-ideas 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 10d 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.

skills/antwork-ideas/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generating content ideas in Antwork

Generic brainstorming is worthless — the user can get "10 LinkedIn post ideas" from any chatbot. Antwork's edge is data: this account's real top performers and its captured voice. Ground every idea in both. Ideas should look like "more of what already worked for you," not a listicle.

1. Pull the evidence first — never ideate cold

Before generating anything, gather:

get_performance(limit) — the account's top posts by lifetime engagement. This is the proven lane.
get_post_context(platform, account_id) — the voice profile, brand context, and recent 3 posts. If voiceStale is true, hand to antwork-voice first; ideas in the wrong voice waste everyone's time.

If the account is new and has no performance history, say so plainly and ideate from voice + brand + the user's stated goals instead — but don't pretend you're being data-driven when you aren't.

2. Find the pattern, then extend it

Read the top performers and name why they worked — hook type (bold claim, contrarian take, question, personal story, useful list), topic cluster, format, length. Then generate ideas that reuse the winning mechanism on fresh material. "Your contrarian one-liners outperform — here are 6 more contrarian takes on adjacent topics" beats a random grab bag.

Mix the slate so it isn't one-note: ~60% in the proven lane, ~40% adjacent experiments to find the next winner.

3. Output a ranked, decision-ready list

Give a numbered list. Each idea is one row:

Hook — the actual opening line, written in the account's voice (not a topic label).
Platform — the account it fits, respecting that platform's norms.
Angle — the one-sentence shape of the post.
Why — the evidence: which past winner or voice trait it draws on.

Rank by expected payoff (proven-lane ideas first). Keep hooks tight and in-voice — apply the same anti-AI-tells rule the voice profile enforces (no "Here's the thing:", no "Let me break it down", no emoji-spray openers).

Read the full file on GitHub · 45 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.

10d ago First seen · 45 lines · 102 tokens per session scan A 0a156959b26c

Subscribe to this mod's changes

antwork-ideas is a skill published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 683 once invoked, about $0.0005 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.

Claude Code Marketing and SEO ai-agents antwork claude-skills mcp mcp-server

ib-trailing-stop

Server-side trailing stop management for stocks and naked LEAPS in IB. Places native TRAIL orders that auto-ratchet the stop as price climbs. Dry-run by default. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 49 tokens

ib-trades-history

Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 59 tokens

antwork-ideas