agentmods.dev

write-a-skill

write-a-skill is a skill for Claude Code, Codex from andrewsrigom/agent-skills. It costs 40 tokens per session (457 once invoked), scanned A, original, MIT.

A guide for creating or improving AI skills—reusable instructions that teach an agent how to handle a specific type of work.

In plain words
What is it for?
Writing skill instructions, deciding whether to add references or scripts, and checking a skill before publishing it.
Why use it?
It helps define clear triggers, boundaries, supporting files, and validation steps so a skill remains focused and installable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 7mo ago A scan 40 tokens original MIT

Good fit Writing skill instructions, deciding whether to add references or scripts, and checking a skill before publishing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrewsrigom/agent-skills/write-a-skill
View source ↗ andrewsrigom/agent-skills andrewsrigom.github.io
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 andrewsrigom/agent-skills --skill write-a-skill
Clone the repo
git clone --depth 1 https://github.com/andrewsrigom/agent-skills

Made for: Claude Code, Codex.

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 write-a-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/write-a-skill/github.svg)](https://agentmods.dev/skills/andrewsrigom/agent-skills/write-a-skill)
Your own site
<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/write-a-skill"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/write-a-skill/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 write-a-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/write-a-skill"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/write-a-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 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 $0.00040 $0.00457
Opus 5.5 $0.00016 $0.00183
Sonnet 5.5 $0.00008 $0.00091
Haiku 4.5 $0.00004 $0.00046

Measured 2mo ago against content hash 741b2d6ec5fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-a-skill 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 2mo 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.

skilling/write-a-skill/SKILL.md · 70 lines

What it actually says

Write A Skill

Use this skill when shaping a new skill or improving an existing one.

Scope

  • defining what the skill does and when it should trigger
  • writing concise name and description frontmatter
  • splitting core instructions from optional references
  • deciding when scripts are worth bundling
  • keeping packs coherent instead of overlapping

Default path

  1. Name the capability in terms of one clear job.
  2. Write the description so trigger conditions are obvious.
  3. Keep SKILL.md focused on workflow, routing cues, and guardrails.
  4. Move detail into references/ only when the core file starts bloating.
  5. Add scripts/ only when deterministic automation is genuinely useful.
  6. Validate the final skill before publishing it.

When to deviate

  • Split one skill into several only when routing quality clearly improves.
  • Keep detail in the main file only when it is essential to the core workflow.
  • Add scripts only when they reduce repetitive deterministic work, not just because code is possible.

Guardrails

  • Do not make the description vague.
  • Do not turn one skill into a whole framework catalog.
  • Do not duplicate the same instruction across multiple packs.
  • Prefer one strong workflow over a large pile of examples.
  • Keep references one level away from SKILL.md.

Avoid

  • vague names and descriptions
  • turning one skill into a whole framework catalog
  • duplicating coverage across multiple packs
  • adding scripts or references with weak justification

Verification checklist

  • the skill has one clear job
  • trigger wording is explicit
  • core workflow stays in SKILL.md
  • references and scripts are justified
  • the finished skill validates cleanly

Output Shape

When answering with this skill, prefer:

  • skill purpose
  • trigger cues
  • scope
  • workflow
  • guardrails
  • validation step

Good Triggers

  • write a skill, create a skill, improve this skill, skill description, skill structure
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. 2mo ago First seen · 70 lines · 40 tokens per session scan A 741b2d6ec5fd

Subscribe to this mod's changes

write-a-skill is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 457 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents
Related

write-a-skill compared with skills from other repositories

write-a-skill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
write-a-skillandrewsrigom/agent-skillsSkill27mo agoMITA40Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex