Adobe Skills is a collection of skills, plugins, agents, and MCP servers that extend AI coding agents with workflows for Adobe products and other tasks. Developers use it to help coding agents work with Adobe analytics and application-building tools. The catalogue entries are the repository’s own skills, plugins, agents, and MCP integrations.
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 adobe/skills --skill workfront-actionsgit clone --depth 1 https://github.com/adobe/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/adobe/skills/workfront-actions)<a href="https://agentmods.dev/skills/adobe/skills/workfront-actions"><img src="https://agentmods.dev/badge/skills/adobe/skills/workfront-actions.svg" alt="Measured on agentmods" 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 | $0.00200 | $0.01814 |
| Opus 5 | $0.00100 | $0.00907 |
| Sonnet 5 | $0.00040 | $0.00363 |
| Haiku 4.5 | $0.00020 | $0.00181 |
Grade A, and why
workfront-actions 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 3d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workfront Runtime actions
Actions are the back end — small functions Adobe runs in its cloud on demand ("serverless"; Adobe I/O Runtime, built on OpenWhisk). The front end (SPA, see workfront-ui-extension) calls them via actionWebInvoke; they hold the credentials and call external APIs. The browser must never call Workfront/Adobe APIs directly — that is the action's job, so login tokens never reach the user's browser.
For generic action patterns and templates (webhook receiver, database CRUD, custom event provider, journaling consumer, large-payload redirect, action sequence, Asset Compute worker) and the App Builder SDKs (State/Files/Events/DB), use
appbuilder-action-scaffolder. This skill is the Workfront-specific layer: the{data,error}contract, IMS passthrough, and Workfront's own Public API.
Anatomy
actions/<name>/index.js # exports main(params)
- CommonJS only — export your function as
exports.main. (App Builder supports only CommonJS, not ES Modules.) - Register every action in
app.config.yaml, or in an extension'sext.config.yaml(which compiles intoapp.config.yaml), following the OpenWhisk wskdeploy YAML spec.
async function main (params) {
// ...
return { statusCode: 200, body: { data, error: null } }
}
exports.main = main
Response shape
Always return { data, error } in the body; the UI checks error before using data.
return { statusCode: 400, body: { data: null, error: 'missing parameter(s) ...' } }
Auth & inputs
require-adobe-authis a per-action choice, off by default (the platform default) — decide deliberately, don't blanket-enable it. Whentrue, Adobe validates the user's IMS token at the gateway before your code runs.- Turn it on when the action itself is the security boundary (privileged work, or nothing downstream authorizes the caller).
- Leave it off when the downstream API enforces its own authorization — e.g. the action just forwards the user's
imsTokento Workfront/Planning, which rejects bad tokens — or unless explicitly asked to enable it.
- The UI passes
imsToken(→Authorization: Bearer …) and the Workfront instance URL as params; never hardcode them. - The IMS org id is in the shared context at
auth.imsOrgID(capitalID— notimsOrgId/imsOrg; that casing trap costs hours). The front end readssharedContext.get('auth').imsOrgIDand passes it down; the action usesparams.imsOrgId/ thex-gw-ims-org-idheader. Two traps: (1) reject the strings"undefined"/"null"/empty — an empty front-end value becomes the header string"undefined"(→401 "Org Id undefined is not in the list of user org Ids"); (2) withrequire-adobe-auth: truethe gateway validates the org header before your code runs. - Inputs flow
.env→ actioninputs(in config) →params. Do NOT readprocess.envat runtime. Underaio app devactions run in-process, soprocess.envmay appear to work locally but will be empty once deployed. Wire keys/secrets asinputsand read them fromparams.
What ships with it
3 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.
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.
- 3d ago First seen · 78 lines · 200 tokens per session scan A d054ed5aeaa1
workfront-actions is a skill published in the GitHub repository adobe/skills (178 stars, last pushed today), licensed Apache-2.0. It adds 200 tokens to every session and 1,814 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 2026-09-03.
Other skills, from other repositories
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
new
Create a new project to start development quickly.
skd-edit
A focused editor for 1C data composition schemas, the report definitions that describe queries, fields, filters, totals, and parameters. It changes an existing Template.xml file through specific operations.
skd-info
A structure reader for 1C data composition schemas, the report definitions that contain queries, fields, parameters, and display variants. It gives a compact summary instead of requiring you to read the raw XML.