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 easyzoom/aix-skills --skill skill-writing-guidegit clone --depth 1 https://github.com/easyzoom/aix-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/easyzoom/aix-skills/skill-writing-guide)<a href="https://agentmods.dev/skills/easyzoom/aix-skills/skill-writing-guide"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/skill-writing-guide/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/easyzoom/aix-skills/skill-writing-guide"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/skill-writing-guide.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 | $0.00017 | $0.00666 |
| Opus 5 | $0.00009 | $0.00333 |
| Sonnet 5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
skill-writing-guide 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Writing Guide
Overview
Use this guide to create Agent Skills that are easy to discover, quick to load, and reliable in repeated use. A skill should teach an agent how to perform a task, not record how one person solved it once.
When To Use
Use this skill when:
- Creating a new
skills/<name>/SKILL.md. - Reviewing a pull request that adds or changes a skill.
- Turning repeated agent behavior into reusable instructions.
- Deciding whether content belongs in a skill, a script, or regular documentation.
Do not use it for one-off project notes, private runbooks, or generic documentation that agents can already infer from standard tools.
Workflow
-
Define the trigger. Write the frontmatter
descriptionas aUse when...sentence that describes the situation where the skill should load. -
Keep the skill operational. Prefer short instructions, decision points, verification steps, and concrete examples. Avoid essays and background stories.
-
Separate heavy material. Keep
SKILL.mdfocused. Move long API references, generated examples, or reusable scripts into supporting files beside the skill. -
Add one strong example. Use a realistic example that demonstrates the workflow end-to-end. Do not add several shallow examples.
-
Add verification. Explain how the agent should prove the skill was used correctly before claiming completion.
-
Run repository validation. Run
python3 scripts/validate-skills.pybefore opening a pull request.
Skill Checklist
- Folder name uses lowercase kebab-case.
SKILL.mdstarts with YAML frontmatter.- Frontmatter includes
nameanddescription. - Frontmatter
namematches the folder name. - Description starts with
Use when. - Body explains workflow and verification.
- Public examples contain no secrets or private data.
Verification
Before publishing a new or updated skill:
- Run
python3 scripts/validate-skills.pyand confirm zero errors. - Confirm the frontmatter
namematches the folder name exactly. - Confirm the
descriptionstarts withUse whenand describes the trigger situation. - Confirm at least one realistic example and one verification section exist in the body.
- Confirm no secrets, internal URLs, or private tool assumptions are in the public skill.
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 · 86 lines · 17 tokens per session scan A 8dccdba26779
skill-writing-guide is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 666 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
resume-writer
Rewrite and enhance resumes using a persistent library of principles harvested from real recruiters, hiring managers, and HR professionals. Always trigger immediately when the user's message starts with "rw". Also trigger on "resume writer", "rewrite my resume", "enhance my resume", "fix my resume", "review my…
trip-email-html-itinerary
Extract trip logistics from pasted travel emails, booking confirmations, forwarded messages, reservation notes, or raw itinerary text, research useful restaurant and activity suggestions for each destination, and generate one polished, self-contained offline HTML itinerary file for sharing with family or other…
idea-forge
Run any raw idea through a multi-stage R&D pipeline that interprets, expands, scores, and converts it into an actionable engineering plan. Always trigger immediately when the user's message starts with "idea". Also trigger on "ideaforge", "analyze this idea", "expand this concept", "assess this invention", "explore…
facebook-post
Write and polish Facebook posts on any topic. Trigger on requests to draft, rewrite, polish, improve a Facebook post, or create cross-platform Facebook, X, and LinkedIn bundles, especially when the user starts with fbp.
fitness-log
Track workouts, log fitness progress, adjust the training program, and generate Facebook posts from workout data. Trigger on workout logging, PR updates, program questions, and fitness progress summaries.
food-analyzer
Analyze food photos, nutrition labels, and ingredient lists. Trigger on food images, nutrition label scans, macro questions, glycemic questions, medication interaction checks, and similar food-analysis requests.