Skip to content

docs: add agent skill (SKILL.md) for the Apify CLI#1233

Open
patrikbraborec wants to merge 14 commits into
masterfrom
feat/apify-cli-agent-skill
Open

docs: add agent skill (SKILL.md) for the Apify CLI#1233
patrikbraborec wants to merge 14 commits into
masterfrom
feat/apify-cli-agent-skill

Conversation

@patrikbraborec

Copy link
Copy Markdown
Contributor

What

Adds skills/apify/SKILL.md — an agent-discoverable skill for the Apify CLI, mirroring the GitHub CLI's skills/gh/SKILL.md.

It's a markdown file (YAML frontmatter + guidance) that coding agents auto-load when a task touches the Apify CLI. It doesn't change CLI behavior — it encodes the non-obvious operational knowledge needed to drive apify reliably from automation.

Contents

  • Non-interactive use — bypassing the create/init/login wizards; -y/--yes confirmations.
  • AuthAPIFY_TOKEN for automation; apify info to verify; apify auth token.
  • Structured output--json on list/info commands; --limit/--offset; apify datasets get-items --format json.
  • Core workflowscreate → run → push; apify call / apify actors start; runs/builds wait, info, log.
  • Storage — datasets and key-value stores.
  • Escape hatchapify api with --list-endpoints / --describe.

Every flag and command was verified against docs/reference.md. The skill points to docs/reference.md and apify help <command> for exhaustive detail rather than duplicating it.

Notes

  • Doc-only addition in a new skills/ folder — no command registration or update-docs regeneration needed.
  • Formatted with Prettier (passes prettier --check).

Closes #1232

🤖 Generated with Claude Code

Ships skills/apify/SKILL.md, an agent-discoverable skill that teaches
coding agents how to drive the Apify CLI reliably from automation:
non-interactive use, auth via APIFY_TOKEN, --json structured output,
core create/run/push and call workflows, storage access, and the
`apify api` escape hatch. Mirrors the layout of the gh CLI's skill.

Closes #1232

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
patrikbraborec and others added 7 commits June 29, 2026 12:19
Add a "Start here" section telling agents to run `apify -h` (and
`apify <command> -h`) first as the source of truth for commands and flags.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add an "Agent skill" section with `npx skills add apify/apify-cli`
install instructions (project-level and global).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace the create/run/push flow in the quick start with a single
`apify call apify/hello-world --output-dataset` example so new users
can run an Actor and see results immediately. The create wizard is
still mentioned for building your own Actor.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

@l2ysho l2ysho left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems nice. I got some nits from my review with this skill, mainly it suggest to not provide a list of option as part of skill, rather let agent get the actual list by him self. Seems legit for me, but nonblocking.

Comment thread skills/apify/SKILL.md Outdated
Comment thread skills/apify/SKILL.md Outdated
patrikbraborec and others added 3 commits June 29, 2026 14:43
Co-authored-by: Richard Solar <solar.richard@gmail.com>
Co-authored-by: Richard Solar <solar.richard@gmail.com>
@patrikbraborec

Copy link
Copy Markdown
Contributor Author

Thanks @l2ysho! Good comments.

Add a `--skills` flag to `apify help` that prints the bundled
`skills/apify/SKILL.md`, so agents always get guidance matching the
installed CLI version. Ship the `skills/` directory in the package,
update the README install instructions (Claude Code, Codex/.agents), and
expand the skill with Actor discovery, pricing, and scheduling workflows.

Co-authored-by: Cursor <cursoragent@cursor.com>
@patrikbraborec patrikbraborec requested a review from szaganek as a code owner June 30, 2026 08:34
Co-authored-by: Cursor <cursoragent@cursor.com>
Comment thread docs/reference.md
ARGUMENTS
commandString The command to get help for.

FLAGS

@DaveHanns DaveHanns Jun 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggestion: the --skills read as if it should list all available skills or provide a skills for a certain command. It is a bit misleading.

What about --agent-guide?
-> apify help --agent-guide

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Or, to be at least in sync with mcpc, it should be singular --skill.
https://apify.slack.com/archives/C0ANU2AFS3D/p1782748998055599?thread_ts=1782728951.631509&cid=C0ANU2AFS3D

Comment thread docs/reference.md
Executes Actor remotely using your authenticated account.
Reads input from local key-value store by default.
Inspect the input schema first with "apify actors info <actor> --input".
To inspect the input schema before creating a JSON input, use "apify actors

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Super nit: is this really better? 🤔

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That was my suggestion, so I can answer: jumping from "executes" and "reads" to an imperative creates some dissonance. We still have human readers :D

Co-authored-by: Cursor <cursoragent@cursor.com>
Comment thread README.md
Comment on lines +29 to +39
mkdir -p ~/.claude/skills/apify
apify help --skills > ~/.claude/skills/apify/SKILL.md
```

### Codex and other agents

Codex and most other agents follow the [Agent Skills open standard](https://developers.openai.com/codex/skills), which loads skills from `.agents/skills` (per repo) or `~/.agents/skills` (per user):

```bash
mkdir -p ~/.agents/skills/apify
apify help --skills > ~/.agents/skills/apify/SKILL.md

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: the skill should be named more specific, e.g.: ~/.claude/skills/apify-cli and ~/.agents/skills/apify-cli or even apify-cli-agentic-guide or apify-cli-agentic-help.

Comment thread src/commands/help.ts

const parent = dirname(dir);

if (parent === dir) {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: worth adding a comment here that that dirname of the root (/ in UNIX and C:\) returns the root itself.

Comment thread skills/apify/SKILL.md

## Auth

- Preferred for automation: set `APIFY_TOKEN` in the environment (no `apify login` needed). Get a token at https://console.apify.com/settings/integrations.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggestion: this might be potentially dangerous. If user, for any reason, has the APIFY_TOKEN already present in their environment, it would use it implicitly and possibly silently.

Overall, we should, instead, refer to https://apify.com/auth.md here.

Additional instructions on authentication bellow are fine, but also not ideal as we are going to have 2 sources of truth. The auth.md should have a CLI section instead (working on one currently).

Comment thread skills/apify/SKILL.md

Run `apify actors search -h` to see the available filters (pricing model, category, username, sort order, pagination) and their accepted values.

Pricing matters: prefer a `FREE` Actor when one covers the task. Check an Actor's pricing before running it with `apify actors info <actor> --json` (look at `currentPricingInfo`).

@DaveHanns DaveHanns Jun 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

prefer a FREE Actor when one covers the task.

Might lead to agents picking FREE over well supported, popular and well rated Actors. We might need more clarification that it is a combination of all above that matters.

@DaveHanns DaveHanns left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mostly nits, some suggestions (mainly the flag name).
Otherwise looks good 🚀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Ship an agent skill (SKILL.md) for the Apify CLI

5 participants