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 gnurio/nurijanian-skills --skill make-requirements-greatgit clone --depth 1 https://github.com/gnurio/nurijanian-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/gnurio/nurijanian-skills/make-requirements-great)<a href="https://agentmods.dev/skills/gnurio/nurijanian-skills/make-requirements-great"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/make-requirements-great/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/gnurio/nurijanian-skills/make-requirements-great"><img src="https://agentmods.dev/badge/skills/gnurio/nurijanian-skills/make-requirements-great.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00196 | $0.06227 |
| Opus 5 | $0.00098 | $0.03113 |
| Sonnet 5 | $0.00039 | $0.01245 |
| Haiku 4.5 | $0.00020 | $0.00623 |
Grade A, and why
make-requirements-great 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 12d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Requirements Great
Requirements decide what gets built. Bad requirements waste engineering time, generate disputes between analysts, developers and stakeholders, and at worst cause the wrong thing to be built. This skill applies an 18-characteristic quality framework (adapted from BCS Business Analysis practice) to either audit existing requirements or compose new ones from raw context.
Inputs
Two input modes. Detect which applies before doing anything else.
Mode A — Review. Input is one or more existing requirements. Audit them against the 18 characteristics. Return a defect log and rewrites.
Mode B — Author. Input is raw context — notes, transcripts, threads, pitches, problem statements. Extract requirements and write them so they meet the 18 characteristics from the start.
Mixed input: extract requirements from the loose context, then audit the union as one set.
Do not impose a format the user did not ask for. Match whatever format the requirements already use, or whatever format the user requests. If the user offers no preference, write each requirement as a single sentence and only add structure when a characteristic (Owner, Source, Acceptance criteria) demands it.
Level of abstraction — read this before applying any characteristic
Requirements live at different altitudes. Confusing the altitudes is the most common failure mode of a quality review and produces exactly the wrong kind of feedback — demanding solution-level precision from a high-level statement, or accepting business-level vagueness in a solution-level statement.
Three common levels (names vary by methodology; what matters is the distinction):
- Business / strategic. Why the work exists. The outcome the organisation wants. Owned by the sponsor. Example: "The organisation shall reduce preference-related customer complaints by 40% within twelve months."
- Stakeholder / user. What a stakeholder needs the system to do for them, expressed at the level of intent. Owned by the affected stakeholder group. Example: "Customers shall be able to update their communication preferences from any product surface and have those preferences respected everywhere."
- Solution / functional. How the system behaves. Owned by the delivery team. Example: "The Preference Service shall propagate writes to all subscribed channels within 5 seconds at the 95th percentile."
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.
- 12d ago First seen · 360 lines · 196 tokens per session scan A 39788461bde3
make-requirements-great is a skill published in the GitHub repository gnurio/nurijanian-skills (107 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 6,227 once invoked, about $0.0010 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…
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…