agentleFS
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/orthogonal/SKILL.md

orthogonal

Skill9 starsChanged 6 months agoMITView on GitHub

Access premium APIs and curated skills via Orthogonal marketplace. Use when you need external data (scraping, enrichment, search), want to discover new capabilities, or need to call third-party services. For tasks like: find an API, enrich a lead, scrape a website, send SMS, verify email, research a company.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you need to perform a task that requires external data or services:

    line 13
  2. Very specific:

    After installing a skill, read its SKILL.md for usage instructions.

    line 36
  3. Distinctive:

    If integration returns HTTP 428 — user needs to connect account at https://orthogonal.com/dashboard/integrations

    line 71
  4. Distinctive:

    Search is semantic — describe what you want to do

    line 75
  5. Very specific:

    Always check orth api show before first call to an endpoint

    line 77
  6. Very specific:

    Use --dry-run to preview cost

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Orthogonal — Skills & API Marketplace

Access premium APIs and curated agent skills via the orth CLI.

Decision Flow

When you need to perform a task that requires external data or services:

  1. Check installed skills first — look through your available skills
  2. Search for skills — orth skills search "<task>" to find a dedicated skill. Always search before repurposing a general skill.
  3. Fall back to API search — only if no skill covers the use case: orth api search "<task>"
  4. Check parameters before calling — orth api show <slug> <path> to see parameter names and types. Never guess parameter names.

Discover Skills

# Search by keyword
orth skills search "lead enrichment"

# List all available skills
orth skills list

# Show skill details
orth skills show <slug>

# Install a skill (goes to ~/.openclaw/skills/)
orth skills add <slug> --agent openclaw

After installing a skill, read its SKILL.md for usage instructions.

Discover & Call APIs

# Search for APIs
orth api search "web scraping"

# Get API details and endpoints
orth api info <api-slug>

# Show endpoint parameters (ALWAYS do this before first call)
orth api show <api-slug> <path>

# Call an API
orth run <api-slug> <path> --body '{"param": "value"}'

# Dry run (check cost without executing)
orth run --dry-run <api-slug> <path> --body '{"param": "value"}'

OAuth Integrations (free, user-connected)

IntegrationSlugKey Actions
Gmailgmail/send-email, /list-emails, /get-email
Google Calendargoogle-calendar/create-event, /list-events
Slackslack/send-message, /list-channels
GitHubgithub/create-issue, /list-repos, /create-pr
Notionnotion/create-page, /search
Google Drivegoogle-drive/find-file, /create-file
Google Sheetsgoogle-sheets/create-spreadsheet, /add-row, /get-values

Example: orth run gmail /send-email --body '{"recipient_email": "user@example.com", "subject": "Hello", "body": "Hi"}'

If integration returns HTTP 428 — user needs to connect account at https://orthogonal.com/dashboard/integrations

Tips

  • Search is semantic — describe what you want to do
  • APIs are pay-per-use ($0.001 - $0.10 per request)
  • Always check orth api show before first call to an endpoint
  • Use --dry-run to preview cost
  • Skills are installed to ~/.openclaw/skills/<slug>/

Related Skills

  • exa-company-research, exa-people-research, exa-lead-gen (Exa-based research — use for web search and content discovery)
  • web-browser (browser automation — use for interactive browsing)
  • posthog-analytics (product analytics — use for internal metrics)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.