Agent Native

spec

The spec skill builds comprehensive pre-migration documentation by analyzing a live website across ten stages, capturing pages, blocks, redirects, 404s…

by Adobe, Inc.Official publisherNot reviewed

Identity proven by GitHub's verified organisation badge (adobe)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
Apache-2.0 (permissive)
Pin
940b879pinned Oct 9, 2026
Context cost
about 1,200 tokenswhen the skill loads
GitHub stars
197on adobe/skills
Scripts
29 scripts

What it does

“Build the pre-migration spec of a website — pages, redirects, 404s, layout variants, the EDS blocks each page needs with reuse verdicts, dynamic features, martech and open decisions — as documented knowledge files for people and a migration agent. Use when someone asks to scope, estimate or plan a migration, wants "which pages use block X / which blocks does page Y need", a redirect or 404 inventory, or the facts behind a migration brief. Not the migration itself (replica, migrate, rollout).”
The author's description, from SKILL.md

Generated summary from the skill's own text

The spec skill builds comprehensive pre-migration documentation by analyzing a live website across ten stages, capturing pages, blocks, redirects, 404s, layout variants, martech and open decisions into knowledge files for planning and agents. It gathers evidence from the site itself, then applies documented judgement rules to produce block inventories, reuse verdicts, feature assessments and migration defaults without performing the actual migration.

When to use it

  • Planning a website migration and estimating scope or effort
  • Discovering which pages use a specific block or which blocks a page needs
  • Creating redirect and 404 inventories for migration planning
  • Documenting layout variants and block families before building replicas

When not to

  • Executing the actual website migration or building the new site
  • Working with sites behind bot challenges without allow-listing the crawler
  • Migrating without access to the live origin or real-user telemetry domains

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add adobe/skills --skill spec

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install adobe/skills spec@940b8795c0df3e25de68ce3881dc90855129b215

Installs the commit we checked (940b879).

Copy by hand

Download the folder at 940b879 and put it in .claude/skills/spec for Claude Code and in .agents/skills/spec for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 940b879

Claude Code plugin

/plugin install adobe-for-creativity@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "spec" by Adobe, Inc..

Source, pinned to commit 940b8795c0df3e25de68ce3881dc90855129b215:
https://github.com/adobe/skills/tree/940b8795c0df3e25de68ce3881dc90855129b215/plugins/stardust/skills/spec

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/spec/ for Claude Code and .agents/skills/spec/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/adobe-inc/spec

SKILL.md at the pin

---
name: spec
description: Build the pre-migration spec of a website — pages, redirects, 404s, layout variants, the EDS blocks each page needs with reuse verdicts, dynamic features, martech and open decisions — as documented knowledge files for people and a migration agent. Use when someone asks to scope, estimate or plan a migration, wants "which pages use block X / which blocks does page Y need", a redirect or 404 inventory, or the facts behind a migration brief. Not the migration itself (replica, migrate, rollout).
license: Apache-2.0
compatibility: Requires Node 20+, and Playwright with Chromium resolvable from the project for the capture stages. Real-user data needs an AEM Operational Telemetry domain key.
---

# stardust:spec — the migration spec, before the migration

The spec answers the people planning a migration (what to build, reuse, fix or decide) and the agent that runs it
(archetypes, block backlog, contracts, redirects, a default for every decision). The agent builds it stage by stage.

## Principles

- **Evidence, then judgement.** Stages S1–S6 and S8 measure the live site; S7 and S9 are judgement (mapping, reuse,
  features, questions) recorded in `judgement/` with a rationale per decision.
- **Blind judgement.** Judge from the source site only (reference/judgement.md); state the provenance in
  `implementation.json#provenance`.
- **Variants, not templates.** CMS templates are loose; plan, capture and QA by layout variant (S8).
- **Every open question ships a default.** A hands-off migration applies it; a recorded answer replaces it.
- **Computed, never typed.** Every figure in findings, feature reach and question impact is a rule
  (reference/knowledge.md § Rules) the knowledge stage evaluates.

## Setup

`stardust/spec/spec.config.json` (reference/config.md): `origin`, `scopePath`, `template` rule, `parser` profile
(`aem-classic`, `aem-core`, or `generic` for any other site) + main selector, optional `maxPages`, `rum`,
`referenceBlocks`. Copy the spec, diff and dynamics scripts to `stardust/scripts/spec/`, `stardust/scripts/diff/` and
`stardust/scripts/dynamics/` (S1, S2, S6 and S9 import them).

## Stages

| # | Stage | Command (from the project root) | Output |
|---|---|---|---|
| S1 | Inventory | `spec-inventory.mjs` | `<work>/inventory/` |
| S2 | Fetch | `spec-fetch.mjs` | `<work>/fetch/` |
| S3 | Parse | `spec-parse.mjs` | `<work>/parse/` |
| S4 | Links | `spec-links.mjs`, then `spec-fetch.mjs --urls <work>/links/pages.txt --out <work>/links/pages.jsonl` and `spec-parse.mjs --fetch <work>/links/pages.jsonl --out <work>/links` | `<work>/links/` |
| S5 | Real-user data (optional) | `spec-rum.mjs` (key from `$RUM_DOMAIN_KEY`) | `<work>/rum/rum.json` |
| S6 | First capture | `spec-pick.mjs --components-only`, `spec-capture.mjs` | `<work>/media/` |
| S7 | Judgement: mapping | `spec-profile.mjs`, `spec-sheet.mjs <component>`, write `judgement/mapping.json`, `spec-map.mjs` | `<work>/map/page-blocks.jsonl` |
| S8 | Variants + visuals | `spec-variants.mjs`, `spec-pick.mjs`, `spec-capture.mjs` | `<work>/map/variants.json`, `<work>/media/` |
| S9 | Implementation | `dynamics-detect.mjs --urls <reps> --out <work>/dynamics`, `spec-martech.mjs`; write `judgement/catalog.json`, `implementation.json`, `findings.json`, `search-probes.json` | `<work>/`, `judgement/` |
| S10 | Knowledge | `spec-knowledge.mjs` | `knowledge/` |

Each stage logs start and end to `stardust/status.jsonl` (`ledger.mjs spec s1-inventory start`). `<work>` is `stardust/.work/spec/`, never committed. Large sites: S2 runs at 4 parallel requests and is resumable —
start it, then write config and judgement scaffolding while it runs. One browser job at a time (S6/S8/S9), two tabs.

## Judgement (S7, S9)

Start from `templates/`. `mapping.json` and `catalog.json`: reference/judgement.md. `implementation.json`:
reference/implementation.md. `findings.json`: 6–10 plain-text `{ title, text }` headlines. Recorded answers go in
`judgement/answers.json`.

## Outputs

`judgement/` and `knowledge/` in `stardust/spec/`, committed; reference/knowledge.md is the contract. Raw material,
captures and crops stay in `<work>`.

## Gates

- S7 passes when `spec-map.mjs` reports no unmapped component and every block in the page blocks is in `catalog.json`
  (`spec-knowledge.mjs` warns otherwise).
- S10 passes when `spec-knowledge.mjs` exits 0 (every rule computed) and every open question has a default.
- A blocked origin (S1 or S2 exit 3: bot challenges or refusals on 10% or more) stops the build: ask the user to
  allow-list the crawler, or to choose `--headed` (the plugin's stealth real-Chrome tier from the diff skill's
  `live-session.mjs`, as replica uses) or `--archive <date>` (Internet Archive captures, which the provenance and a
  finding must disclose). Never choose for them, and never work around a block another way.
- Before sharing: no customer secret, internal evaluation or other migration's name in the project or the output.

## References

- reference/config.md — `spec.config.json`, template rules, parser profiles.
- reference/judgement.md — the blind rule, mapping rules, contact sheets, block families, reuse verdicts.
- reference/implementation.md — features, martech, data layer, metadata, indexes, locales, open questions.
- reference/knowledge.md — the output contract: files, fields, the rule format.
- reference/evaluation.md — scoring a spec against a delivered migration; blind re-judgement.

From adobe/skills at 940b879, shown as plain text under its license: Apache-2.0 (permissive). The license text is in plugins/stardust/skills/spec/SKILL.md.

View SKILL.md on GitHub at 940b879

Files

40 files, 235 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 940b879
All 50 skills from Adobe, Inc.

More from Adobe, Inc.

  • adobe

    This skill provides an onboarding tour of the Adobe for creativity connector, displaying available capabilities, example workflows, and which Adobe product…

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago

  • adobe-anydocx

    This skill routes DOCX conversion tasks that have a PDF source to Adobe's pdf_export tool with the appropriate format setting.

    Claude Code, Codex, Cursor +4 · about 680 tokens · pinned 6 days ago

  • adobe-anyexcel

    This skill routes PDF-to-Excel conversion tasks to the Adobe pdf_export tool with xlsx target format.

    Claude Code, Codex, Cursor +4 · about 690 tokens · pinned 6 days ago

  • adobe-anypdf

    This skill routes PDF tasks to Adobe Acrobat tools for higher fidelity than local Python libraries.

    Claude Code, Codex, Cursor +4 · about 2.1K tokens · pinned 6 days ago

  • adobe-anypptx

    This skill routes PowerPoint conversion tasks that have a PDF source to Adobe's pdf_export tool with PPTX output format.

    Claude Code, Codex, Cursor +4 · about 670 tokens · pinned 6 days ago

  • adobe-batch-edit-photos

    This skill applies consistent visual adjustments to a set of photos so they appear edited together as a cohesive collection.

    Claude Code · about 9.9K tokens · pinned 6 days ago

All Docs and writing skills
  • n8n-docs-assistant

    This skill answers questions about n8n configuration, setup, credentials, nodes, and troubleshooting by retrieving information from current n8n documentation.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 450 tokens · pinned 6 days ago

  • algodocs-automation

    This skill automates Algodocs document processing tasks through Composio's toolkit via the Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • remotion-docs

    This skill enables agents to search and retrieve Remotion documentation via the Algolia API and fetch pages as Markdown.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago

  • remotion-docs

    This skill searches the Remotion documentation using the Algolia API and retrieves documentation pages as Markdown.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago

  • receipts

    This skill generates a personal Claude Code usage report from local session transcripts stored in ~/.claude/projects, mining activity across projects without…

    by AnthropicOfficial publisher

    Contains scripts

    Claude Code · about 4.1K tokens · pinned 6 days ago

  • solo

    This skill enables an agent to work through a single difficult mathematics problem independently within one session.

    by AnthropicOfficial publisher

    Claude Code · about 1.4K tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use