What is create-specifications?

A technical specification that turns an approved requirements document into a detailed plan for building the feature.

It describes system architecture, data models, API contracts, component responsibilities, and important sequences of operations.

It makes the planned architecture, data, interfaces, components, and system interactions clear before implementation.

create-specifications — Skill by tomzx

Install

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.

agentmods

npx agentmods add skills/tomzx/agents/create-specifications

Any agent

npx skills add tomzx/agents --skill create-specifications

Clone the repo

git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,457 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00025	$0.01457
Opus 5	$0.00013	$0.00728
Sonnet 5	$0.00005	$0.00291
Haiku 4.5	$0.00003	$0.00146

Measured 2d ago against content hash 5e44cc886e35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-specifications 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 2d 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.

skills/create-specifications/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Specifications

Produces a detailed technical specification from a requirements document, covering architecture, data models, API contracts, component design, and key sequences.

Prerequisites

Apply the shared SDLC conventions in skills/sdlc/references/shared.md.
If no argument is provided, locate the feature directory under .sdlc/features/ whose frontmatter issue field references $ISSUE_NUMBER.
.sdlc/features/N-<slug>/requirements.md (must have passed review with findings verdict approved), or a requirements document provided in context or as a file path ($1)
.sdlc/features/N-<slug>/existing-solutions.md (optional, if a prior-art survey was produced): adopt its recommendation and reuse the patterns it captured
.sdlc/features/N-<slug>/codebase-analysis.md (optional, if existing code was analyzed): honor each component's change disposition and its "must not change" constraints, and follow the migration path for any refactor or replace

Steps

Read and understand the requirements document, the existing solutions survey if present, and the codebase analysis if present.
Identify the major components and their responsibilities.
Define data models: entities, attributes, and relationships.
Specify API contracts: endpoints, request/response schemas, and error codes. When the feature defines an API surface, write the normative contract to .sdlc/features/N-<slug>/api.yaml (OpenAPI 3, template at skills/sdlc/templates/features/api.yaml) and keep only a summary table in specification.md, so the contract is lintable and diffable instead of prose.
Describe key sequences as Mermaid sequenceDiagram blocks (one per flow): user flows, system interactions, and async processes. A message with no receiver makes a missing step obvious before code exists.
Document technical decisions and their rationale.
Identify risks, unknowns, and deferred decisions.
Design data models, API contracts, and persisted state for evolution so future versions stay forward compatible (see Forward Compatibility below).
Validate best-effort: lint api.yaml with npx -y @stoplight/spectral-cli lint api.yaml and render each mermaid block with mmdc (or npx -y @mermaid-js/mermaid-cli) when available. A missing tool is not a failure; skip and note it. A validation failure is a defect to fix before handoff.
Write the output to .sdlc/features/N-<slug>/specification.md (plus api.yaml when the feature has an API surface).

Read the full file on GitHub · 99 lines

Changes

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.

2d ago First seen · 99 lines · 25 tokens per session scan A 5e44cc886e35

Subscribe to this mod's changes

create-specifications is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 1,457 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.

Backend and APIs Documents Frontend

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens