Borrowing it
Nothing to install: this file belongs to emilyLi2020/WAVE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/emilyLi2020/WAVE/main/.agents/skills/blog-writer/SKILL.mdgit clone --depth 1 https://github.com/emilyLi2020/WAVEWrote 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.
[](https://agentmods.dev/skills/emilyli2020/wave/blog-writer)<a href="https://agentmods.dev/skills/emilyli2020/wave/blog-writer"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/blog-writer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00072 | $0.02575 |
| Opus 5 | $0.00036 | $0.01288 |
| Sonnet 5 | $0.00014 | $0.00515 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
blog-writer 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Writer
Write a new blog post for the Hackathon Starter Kit site using the rich content block system. Every post is defined as structured data in lib/blog.ts and rendered automatically by app/blog/[slug]/page.tsx.
Step 1: Define the Topic
Ask the user (or determine from context):
- What is the blog post about?
- Who is the target reader?
- What primary search keyword should this rank for?
If the user is unsure, suggest 3 topic ideas based on gaps in the existing blog coverage. Check lib/blog.ts for the BLOG_POSTS array to see what already exists.
Step 2: Plan the Post Structure
Before writing any content, create an outline:
- Slug: URL-friendly, matches the target keyword (e.g.,
how-to-find-hackathon-teams) - Title: Keyword-rich, compelling, under 70 characters if possible
- Description: 150-160 characters with the primary keyword in the first sentence
- Keywords: 4-6 search terms this post targets
- Sections: 5-8 sections, each with a heading and a mix of content block types
- Reading Time: Estimate based on content length (e.g., "8 min read")
Present the outline to the user for approval before writing the full content.
Step 3: Write Using Content Blocks
Each section in BlogSection has a heading (string), paragraphs (string[], can be empty), and an optional blocks (ContentBlock[]) array. When blocks is present, the renderer uses it instead of paragraphs.
Available Block Types
Use the ContentBlock union type defined in lib/blog.ts. Here is every type with its fields and when to use it:
paragraph
Standard body text. Use for introductory context and transitions between visual blocks.
{ type: "paragraph", text: "Your paragraph text here." }
callout
Highlighted box with an icon. Four variants available.
{
type: "callout",
variant: "tip" | "warning" | "info" | "success",
title: "Optional custom title", // defaults to variant label if omitted
text: "The callout body text."
}
- tip (yellow, lightbulb icon): Actionable advice, shortcuts, pro tips
- warning (red, alert icon): Common mistakes, things to avoid
- info (purple, info icon): Background context, definitions, notes
- success (green, checkmark icon): Key takeaways, proven results
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.
- 8d ago First seen · 267 lines · 72 tokens per session scan A 1d9c2f461efa
blog-writer is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,575 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…