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 xiaolai/nlpm --skill writing-skillsgit clone --depth 1 https://github.com/xiaolai/nlpmWrote 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/xiaolai/nlpm/writing-skills)<a href="https://agentmods.dev/skills/xiaolai/nlpm/writing-skills"><img src="https://agentmods.dev/badge/skills/xiaolai/nlpm/writing-skills/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/xiaolai/nlpm/writing-skills"><img src="https://agentmods.dev/badge/skills/xiaolai/nlpm/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 7 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00061 | $0.01968 |
| Opus 5 | $0.00030 | $0.00984 |
| Sonnet 5 | $0.00012 | $0.00394 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
writing-skills 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 10d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
Scope: covers SKILL.md authoring. SKILL.md is the cross-tool open standard (agentskills.io) — the same file works in Claude Code (
.claude/skills/), Codex CLI (.agents/skills/), and Antigravity (.agent/skills/). Onlynameanddescriptionare required by the spec; per-tool extras (Claude'smodel:/allowed-tools:, Codex'sagents/openai.yamlsidecar) live in[[nlpm:conventions-claude]]/[[nlpm:conventions-codex]]/[[nlpm:conventions-antigravity]]. For agent writing, see [[writing-agents]]. For plugin architecture, see [[writing-plugins]].
1. The Description is Everything
The description field determines when Claude loads this skill. It is not a summary -- it is a trigger mechanism.
Bad (score 55):
description: "Helpful skill for React development"
Good (score 95):
description: "Use when building React components, debugging re-renders, optimizing performance with useMemo/useCallback, or fixing hook dependency arrays"
Description Checklist
| Criterion | Test |
|---|---|
| 3+ trigger phrases | Count distinct action phrases separated by commas |
| Action-oriented | Starts with "Use when..." or "How to..." |
| Includes tool/framework name | The technology name appears explicitly |
| Matches real queries | Would a user's actual question contain any of your trigger words? |
Trigger Phrase Construction
Map real user queries to trigger phrases:
| User says | Trigger phrase to include |
|---|---|
| "My component re-renders too much" | "debugging re-renders" |
| "How do I memoize this?" | "optimizing performance with useMemo/useCallback" |
| "My useEffect runs in a loop" | "fixing hook dependency arrays" |
| "I need a new component for..." | "building React components" |
Rule: if you can't list 3 real user queries that match your description, rewrite it.
2. Body Structure
Section Order
- Scope note (if related skills exist) -- tells Claude when to use THIS skill vs another
- Most commonly needed patterns -- what users ask about 80% of the time
- Decision matrices -- when to use A vs B (tables)
- Worked examples -- before/after with scores
- Common mistakes -- anti-patterns to avoid
- References -- links to deep dives
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.
- 10d ago First seen · 236 lines · 61 tokens per session scan A e10e75613740
writing-skills is a skill published in the GitHub repository xiaolai/nlpm (136 stars, last pushed today), licensed ISC. It adds 61 tokens to every session and 1,968 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 2026-08-30.
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…