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 andrewsrigom/agent-skills --skill write-a-skillgit clone --depth 1 https://github.com/andrewsrigom/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/andrewsrigom/agent-skills/write-a-skill)<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="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 | $0.00040 | $0.00457 |
| Opus 5 | $0.00020 | $0.00229 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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 7d 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.
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
nameanddescriptionfrontmatter - splitting core instructions from optional references
- deciding when scripts are worth bundling
- keeping packs coherent instead of overlapping
Default path
- Name the capability in terms of one clear job.
- Write the description so trigger conditions are obvious.
- Keep
SKILL.mdfocused on workflow, routing cues, and guardrails. - Move detail into
references/only when the core file starts bloating. - Add
scripts/only when deterministic automation is genuinely useful. - 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
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.
- 7d ago First seen · 70 lines · 40 tokens per session scan A 741b2d6ec5fd
write-a-skill is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 457 once invoked, about $0.0002 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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…