Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ddddjaak/se-skillsnpx agentmods add skills/ddddjaak/se-skills/requirements-decomposeWrote 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/ddddjaak/se-skills/requirements-decompose)<a href="https://agentmods.dev/skills/ddddjaak/se-skills/requirements-decompose"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/requirements-decompose/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/ddddjaak/se-skills/requirements-decompose"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/requirements-decompose.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 | $0.00123 | $0.05471 |
| Opus 5 | $0.00062 | $0.02736 |
| Sonnet 5 | $0.00025 | $0.01094 |
| Haiku 4.5 | $0.00012 | $0.00547 |
Grade A, and why
requirements-decompose 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 — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Decompose
Overview
Raw requirements arrive as a pile of heterogeneous documents — a PRD from marketing, a chip datasheet from the hardware team, an industry standard, a customer specification, a reference design. None of them speak the same language. None of them are structured for engineering traceability. None of them are complete on their own.
This skill transforms that pile into a single, structured system requirements document where every requirement is classified by domain and type, conflicts are resolved, gaps are identified, derived requirements are explicit, and ownership is assigned. Every downstream artifact — architecture, specifications, test plans — depends on this document. The quality of the entire project starts here.
This skill is to SE what stakeholder interviewing is to software development: it confronts ambiguity head-on before any design work begins.
When to Use
- A new chip or product project kicks off and requirements exist only as a PRD or datasheet
- Multiple input sources exist (datasheet + standard + customer spec) and need consolidation into one source of truth
- Requirements are implicit, scattered across documents, or contradict each other
- You need to assign ownership (HW / SW / System / Mechanical) to each requirement before design begins
- A downstream skill (
architecture-design,spec-authoring) detects incomplete or ambiguous requirements and invokes this skill inline
When NOT to use:
- Requirements are already fully decomposed and traceable in a structured document with IDs
- The ask is a single-module change with no new system-level impact
- Pure information lookup ("what does the datasheet say about register X?")
- The user explicitly asks for a quick answer without formal decomposition
The Process
PREPROCESS ──→ COLLECT ──→ CLASSIFY ──→ RESOLVE ──→ DERIVE ──→ ASSIGN ──→ VALIDATE
│ │ │ │ │ │ │
▼ ▼ ▼ ▼ ▼ ▼ ▼
Extract Gather Categorize Resolve Derive Assign Human
text/tables all raw by domain conflicts system- ownership review
from PDFs inputs & type & gaps level reqs (HW/SW/SYS) & sign-off
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 · 474 lines · 123 tokens per session scan A ef1ce77ffee3
requirements-decompose is a skill published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 5,471 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.