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 Notysoty/openagentskills --skill ai-feature-spec-writergit clone --depth 1 https://github.com/Notysoty/openagentskillsWrote 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/notysoty/openagentskills/ai-feature-spec-writer)<a href="https://agentmods.dev/skills/notysoty/openagentskills/ai-feature-spec-writer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/ai-feature-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/notysoty/openagentskills/ai-feature-spec-writer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/ai-feature-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 | $0.00029 | $0.02270 |
| Opus 5 | $0.00015 | $0.01135 |
| Sonnet 5 | $0.00006 | $0.00454 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
AI Feature 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Feature Spec Writer
What this skill does
This skill writes a complete product and engineering spec for an AI-powered feature. Unlike a standard feature spec, AI features require additional sections: model selection rationale, prompt strategy, fallback behavior when the model produces bad output, latency and cost budgets, evaluation criteria, and a plan for handling model updates. The output is a spec detailed enough to guide implementation and evaluation without requiring additional design sessions.
Use this before building any feature that incorporates an LLM, image model, or other AI component — especially when the feature will be customer-facing or when the output quality directly affects the user experience.
How to use
Claude Code / Cline
Copy this file to .agents/skills/ai-feature-spec-writer/SKILL.md in your project root.
Then ask:
- "Use the AI Feature Spec Writer skill to write a spec for our AI-powered email drafting feature."
- "Write a product spec for adding AI summarization to our dashboard using the AI Feature Spec Writer skill."
Provide:
- A description of the feature you want to build
- The target user and their goal
- The AI capability you plan to use (text generation, classification, summarization, etc.)
- Your tech stack and any existing AI integrations
- Any constraints (latency requirements, cost budget, compliance needs)
Cursor
Add the instructions below to your .cursorrules or paste them into the Cursor AI pane with the feature description.
Codex
Provide the feature description and context. Ask Codex to follow the instructions below to produce the spec.
The Prompt / Instructions for the Agent
When asked to write an AI feature spec, produce a document covering all of the following sections:
Section 1 — Feature Overview
- Feature name and one-line description
- Problem being solved: What user pain does this address? What is the current workaround?
- Target user: Who will use this feature?
- Success metrics: How will we know if this feature is successful? (Quantitative: "X% of users engage with AI suggestions"; Qualitative: "users rate suggestions as helpful")
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 · 173 lines · 29 tokens per session scan A 819e6a0744b0
AI Feature Spec Writer is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 2,270 once invoked, about $0.0001 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
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
AI & LLM Security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…