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.
npx skills add Gerg/ai_agent_skills --skill skill-writinggit clone --depth 1 https://github.com/Gerg/ai_agent_skillsWrote 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/gerg/ai_agent_skills/skill-writing)<a href="https://agentmods.dev/skills/gerg/ai_agent_skills/skill-writing"><img src="https://agentmods.dev/badge/skills/gerg/ai_agent_skills/skill-writing/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.
<a href="https://agentmods.dev/skills/gerg/ai_agent_skills/skill-writing"><img src="https://agentmods.dev/badge/skills/gerg/ai_agent_skills/skill-writing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.02933 |
| Opus 5 | $0.00026 | $0.01466 |
| Sonnet 5 | $0.00010 | $0.00587 |
| Haiku 4.5 | $0.00005 | $0.00293 |
Grade A, and why
skill-writing 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 9d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Writing Skill
A meta-skill for creating effective skill documents using progressive disclosure.
When using this skill, begin by stating: "I'm using the skill-writing skill, which enforces: <500-line SKILL.md, conditional reference loading with explicit 'when to read' conditions, and sharpness — guidance must change agent behavior or it doesn't belong."
Context: This skill covers skill authoring for all skill types (core, extension, reference files). Read references on demand — see the References section at the bottom for when to load each one.
What is a Skill?
A skill is a reusable knowledge document that provides structured guidance on how to accomplish a specific type of task. Skills are designed to be:
- Focused - Cover one concern or outcome
- Extensible - Support variants through references and optional extensions
- Prescriptive - Provide clear, actionable guidance
- Generic - Avoid project-specific details
- Reusable - Apply across multiple contexts
- Concise - Respect the shared context window
Skill Design Principles
1. Concise is Key
The context window is a shared resource. Skills compete for context with system prompts, conversation history, other skills, and the user's actual request.
Default assumption: Agents are already capable. Only add context the agent doesn't already have. Challenge each piece of information:
- "Does the agent really need this explanation?"
- "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Target: Keep SKILL.md under 500 lines. When approaching this limit, split content into reference files.
2. Sharp and Opinionated Over Generic
Skills must change agent behavior. If an agent would do the same thing without the skill, the skill has no value.
Two questions to ask:
- Effectiveness: "Would an agent behave differently with this skill?" (If no → skill is too generic)
- Efficiency: "Does the agent already understand this concept?" (If yes → explanation is redundant)
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 278 lines · 51 tokens per session scan A d1ff170a7e13
skill-writing is a skill published in the GitHub repository Gerg/ai_agent_skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 2,933 once invoked, about $0.0003 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…