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 cuongtl1992/vibe-skills --skill spec-writergit clone --depth 1 https://github.com/cuongtl1992/vibe-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/cuongtl1992/vibe-skills/spec-writer)<a href="https://agentmods.dev/skills/cuongtl1992/vibe-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/spec-writer/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/cuongtl1992/vibe-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/spec-writer.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 | $0.00125 | $0.01988 |
| Opus 5 | $0.00063 | $0.00994 |
| Sonnet 5 | $0.00025 | $0.00398 |
| Haiku 4.5 | $0.00013 | $0.00199 |
Grade A, and why
spec-writer 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 11d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Writer
Write high-quality feature specs through structured conversation, then produce a complete PRD document ready for engineering handoff and BDD scenario generation.
Core Philosophy
A good spec answers three questions before anything else:
- Who has the problem? (not the persona using the software — the human experiencing pain)
- What pain do they have right now, without this feature?
- Why does solving it matter to the business?
Everything else — requirements, metrics, scope — flows from clear answers to these three questions. If the "who/what/why" is fuzzy, the spec will be fuzzy too.
The output format is deliberately structured for two audiences:
- Engineering — to know what to build and what's out of scope
- QA / BDD — to extract business rules and generate Gherkin scenarios (via
prd-to-gherkinskill)
Workflow: Interview → Draft → Refine
Phase 1 — Scoping Interview (always start here)
Never jump straight to writing. Conduct a brief interview first.
Start with one opening question, then follow up based on answers. Do not dump all questions at once — feel like a conversation, not a form.
Opening question:
"Trước khi viết spec, mình cần hiểu rõ vấn đề. Bạn có thể mô tả: người dùng nào đang gặp vấn đề gì, và hiện tại họ đang xử lý như thế nào?"
(Adapt language to match user — Vietnamese or English based on how they write)
Follow-up questions (ask only what's still missing after the opening answer):
| If missing | Ask |
|---|---|
| Who exactly | "Đây là loại user nào? Role, subscription level, use case cụ thể?" |
| Current pain | "Hiện tại họ giải quyết vấn đề này bằng cách nào? Pain point cụ thể là gì?" |
| Business value | "Tại sao feature này quan trọng với business? KPI nào bị ảnh hưởng?" |
| Scope clarity | "Có gì chắc chắn không nằm trong scope lần này không?" |
| Success definition | "Làm sao biết feature này thành công? Metric nào thay đổi?" |
Stop asking when you have: a clear user, a concrete pain point, a measurable outcome, and a rough sense of the main requirements. Usually 3–5 exchanges.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 253 lines · 125 tokens per session scan A 6e5b15d752cb
spec-writer is a skill published in the GitHub repository cuongtl1992/vibe-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 1,988 once invoked, about $0.0006 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…
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…