spec-writer

spec-writer is a skill for Claude Code, Codex from dayvisonassis/sdd-skills. It costs 72 tokens per session (8,261 once invoked), scanned A, original, MIT.

A tool for turning a product requirements document and codebase analysis into an implementation specification. It produces a technical specification, work plan, and operational contract describing quality checks and observable completion criteria.

In plain words
What is it for?
Use it to define one feature or a batch of features, document the environment and quality gates, and create the files consumed by implementation and evaluation work.
Why use it?
It gives developers and evaluators a shared description of what must be built and how completion will be checked before implementation starts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to define one feature or a batch of features, document the environment and quality gates, and create the files consumed by implementation and evaluation work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dayvisonassis/sdd-skills/spec-writer
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.

Any agent
npx skills add dayvisonassis/sdd-skills --skill spec-writer
Clone the repo
git clone --depth 1 https://github.com/dayvisonassis/sdd-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spec-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/spec-writer/github.svg)](https://agentmods.dev/skills/dayvisonassis/sdd-skills/spec-writer)
Your own site
<a href="https://agentmods.dev/skills/dayvisonassis/sdd-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-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.

agentmods 80×15 button for spec-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/dayvisonassis/sdd-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/spec-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.08261
Opus 5.5 $0.00029 $0.03304
Sonnet 5.5 $0.00014 $0.01652
Haiku 4.5 $0.00007 $0.00826

Measured 16d ago against content hash 11b6ff6c2f50, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 16d 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/spec-writer/SKILL.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Specs Writer

Generate implementation-ready technical specifications based on the project's PRD and existing codebase patterns. Besides spec.md and plan.md, it produces a third artifact, contract.md — the operational contract consumed by implement-feature (which must satisfy it) and by evaluator (which validates against it).

Base docs (in this package): https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Contrato_de_Feature.md (contract structure), https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Como_criar_gates.md (gates), and https://github.com/dayvisonassis/sdd-skills/blob/main/docs/ARQUITETURA_DAS_SKILLS.md (full flow). Start with https://github.com/dayvisonassis/sdd-skills/blob/main/docs/GUIA_DO_WORKFLOW.md for how the skills fit together.

The skill has two modes:

  • Single-feature mode (default): operates on one feature at a time, identified by its PRD feature ID (F01, F02...), with an interactive interview (Steps 1–6 below).
  • Batch mode: operates on multiple features from the same wave in parallel, auto-accepting all interview recommendations. Activated automatically when the input contains multiple IDs, a wave reference, or a mix. See the Batch Mode section near the end of this file.

Output: THREE files are required:

  1. spec.md - Technical specification (7 sections)
  2. plan.md - Implementation plan (phases and steps)
  3. contract.md - Operational contract (environment, quality gates, coverage manifest, observable criteria)

Output location: docs/<feature-id>-<kebab-name>/{spec.md,plan.md,contract.md}

  • The <kebab-name> is derived from the feature's name in the PRD Section 6 (lowercase, spaces → hyphens, special characters removed). Example: F03. Video Upload → docs/F03-video-upload/.

Execution Steps (6 Steps)

Note: These are internal agent execution steps. The OUTPUT plan document will have 1-5 phases based on feature complexity.

Step 1: Resolve Input and Pre-Analysis

Read the full file on GitHub · 505 lines

Files

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.

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.

  1. 16d ago Changed · +4 lines 11b6ff6c2f50
  2. 18d ago Changed c7fe4902f315
  3. 29d ago Changed · +4 lines aebc8d0e11db
  4. 1mo ago Changed · +14 lines 3e2956784e80
  5. 2mo ago First seen · 483 lines · 72 tokens per session scan A e9207d1767aa

Subscribe to this mod's changes

spec-writer is a skill published in the GitHub repository dayvisonassis/sdd-skills (3 stars, last pushed 16d ago), licensed MIT. It adds 72 tokens to every session and 8,261 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

exploratory-data-analysis

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens

design-review

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…

jezweb/claude-skills · 108 tokens

react-patterns

React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…

jezweb/claude-skills · 110 tokens

render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…

gooseworks-ai/goose-skills · 159 tokens

render-airdrop-carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…

gooseworks-ai/goose-skills · 207 tokens