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 boparaiamrit/skills-by-amrit --skill writing-skillsgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/writing-skills)<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/writing-skills"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/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/boparaiamrit/skills-by-amrit/writing-skills"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/writing-skills.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 | $0.00030 | $0.05073 |
| Opus 5 | $0.00015 | $0.02537 |
| Sonnet 5 | $0.00006 | $0.01015 |
| Haiku 4.5 | $0.00003 | $0.00507 |
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 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 — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
Overview
Skills are the building blocks of this system. A well-written skill makes AI assistants genuinely better. A poorly-written skill adds noise.
Core principle: If following the skill doesn't produce measurably better results, the skill shouldn't exist.
Master reference: All skills inherit from _rules/SKILL.md. Read it before writing any skill.
The Iron Law
EVERY SKILL MUST HAVE A CLEAR IRON LAW, DEFINED ACTIVATION CONDITIONS, AND A VERIFIABLE PROCESS.
When to Use
- Creating a new skill for the library
- Enhancing an existing skill
- Reviewing a skill's quality
- Standardizing skill format
When NOT to Use
- Applying an existing skill (use
using-skills) - The intended behavior is better captured as a workflow, not a skill
- The behavior is a one-off checklist, not a repeatable process
Anti-Shortcut Rules
YOU CANNOT:
- Create a skill without an Iron Law -- if it has no non-negotiable rule, it's advice, not a skill
- Write "Use when..." descriptions that are vague -- "Use when coding" activates for everything
- Include "it depends" in a skill -- skills are prescriptive, not suggestive
- Skip the Common Rationalizations section -- every process has excuses people make to skip it
- Write a process with vague steps -- "make sure it's good" is not a verifiable step
- Create a skill that duplicates another skill's scope -- check existing skills first
- Skip the Anti-Shortcut Rules -- they prevent the most common ways the skill gets bypassed
- Write Iron Questions that can be answered without evidence -- "Did you check?" != "What was the output?"
- Omit the Red Flags section -- without observable violation indicators, the skill cannot self-enforce
- Skip the Integration section -- isolated skills are broken skills
Common Rationalizations (Don't Accept These)
| Rationalization | Reality |
|---|---|
| "This skill is too short to need all sections" | Short skills still need structure. Sections prevent shortcuts. |
| "The process is self-explanatory" | To you, maybe. To an LLM following instructions literally, no. |
| "Iron Questions are overkill" | They're the accountability mechanism. Without them, skills get skipped. |
| "Not every skill needs rationalizations" | Every process has excuses for skipping it. Document them. |
| "I'll add the missing sections later" | Later never comes. Complete the skill now. |
| "This is a simple skill" | Simple skills with poor structure produce poor results. |
| "I'll just copy another skill and modify it" | Copying without understanding produces cargo-cult skills. Understand the WHY. |
| "The Red Flags are obvious" | If they were obvious, people wouldn't violate them. Write them down. |
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 · 562 lines · 30 tokens per session scan A a528b42aee6e
writing-skills is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 5,073 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 2026-09-03.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…