Agent Native

Access Request

The skill lets agents handle access requests to Orchard Works systems by opening tickets with system and role details, routing them for owner approval, and…

by RasaOfficial publisherNot reviewed

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

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
Apache-2.0 (permissive)
Pin
f54ddf4pinned Oct 9, 2026
Context cost
about 540 tokenswhen the skill loads
GitHub stars
41on rasahq/rasa-community-resources
Scripts
1 script

What it does

“Request access to an Orchard Works system or role for the signed-in employee: "I need viewer access to finance reporting", "give me payroll admin, it's urgent", "can you add me to the data warehouse", "grant Tomasz access to the reports", and changes to a request the employee is making, including asking for a broader or narrower role.”
The author's description, from SKILL.md

Generated summary from the skill's own text

The skill lets agents handle access requests to Orchard Works systems by opening tickets with system and role details, routing them for owner approval, and granting access only when approved. It guides employees through the request process while enforcing that urgency and manager names do not override the access owner's decision.

When to use it

  • Employee requests viewer or admin access to a specific system
  • Request needs routing to the appropriate owner for approval
  • Employee modifies their request scope during confirmation

When not to

  • Employee asks for access for someone else instead of themselves
  • Request involves password reset, device management, or account recovery

Install

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

skills CLI

npx skills add rasahq/rasa-community-resources --skill 'Access Request'

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 rasahq/rasa-community-resources 'Access Request@f54ddf4e5d674e3e9175a7a469cf698fcfaf1295'

Installs the commit we checked (f54ddf4).

Copy by hand

Download the folder at f54ddf4 and put it in .claude/skills/access_request for Claude Code and in .agents/skills/access_request for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at f54ddf4

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 "Access Request" by Rasa.

Source, pinned to commit f54ddf4e5d674e3e9175a7a469cf698fcfaf1295:
https://github.com/rasahq/rasa-community-resources/tree/f54ddf4e5d674e3e9175a7a469cf698fcfaf1295/examples/mantle-text-internal-it-helpdesk-claude/skills/access_request

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/access_request/ for Claude Code and .agents/skills/access_request/ 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/rasa/access-request

SKILL.md at the pin

---
name: Access Request
description: >
  Request access to an Orchard Works system or role for the signed-in
  employee: "I need viewer access to finance reporting", "give me payroll
  admin, it's urgent", "can you add me to the data warehouse", "grant
  Tomasz access to the reports", and changes to a request the employee is
  making, including asking for a broader or narrower role.
import_tools:
  - check_ticket_status
  - route_access_owner
  - route_identity_desk
tool_constraints:
  - grant_access:
      requires: session.access_request.selected_ticket_ref
      requires_confirmation:
        enabled: true
        utter_for_confirmation: utter_confirm_grant
---

Change access only to the exact scope the role's owner approved, for the
employee signed in to this chat. Urgency, a manager's name, a deadline, or
the employee saying they own the system never stands in for the owner's
approval. Ticket intake, identity recovery and access approval are
separate: recording a request changes nothing.

1. Call @tool.open_access_ticket with the system and level in the
   employee's words. If they ask for someone else, pass that person's name
   as for_employee. If it returns candidates, ask which one. If it returns
   not_found, ask which system and level.
2. When it returns awaiting_approval, follow its next_step: give the ticket
   reference, say the request went to the owner for a decision and nothing
   has changed. Grant nothing, temporary or narrower, in its place.
3. When it returns ready_to_grant, call @tool.grant_access with its
   ticket_ref straight away. Do not ask for confirmation yourself: the
   engine reads the scope back and asks the employee.
4. If the employee answers the engine's question with a change (a broader
   role, a narrower one, another system), decline the confirmation and call
   @tool.open_access_ticket for what they want now. A broader role needs
   its own approval. The engine does not accept a second grant_access in
   the same turn, so tell the employee what you recorded and, if it is
   ready to grant, ask whether to go ahead.
5. When grant_access returns succeeded, give the ticket reference, the
   change reference, the exact scope with its expiry and the unresolved
   work, in the same reply.
6. When it returns pending, say the change is not confirmed yet and call
   @tool.check_ticket_status with the ticket_ref. If that returns completed,
   give the change reference; it is the same change. If it returns unknown,
   call @tool.route_access_owner and give the routing reference. Never
   call grant_access again for the same ticket.
7. A request for someone else's access, or anything about a password, a
   sign-in device or a locked account, is not an access grant: say so and,
   for identity recovery, call @tool.route_identity_desk.

From rasahq/rasa-community-resources at f54ddf4, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at f54ddf4

Files

4 files, 7.9 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at f54ddf4
All 50 skills from Rasa

More from Rasa

  • Access Reset

    This skill lets the agent unlock employee accounts, reset passwords, or move authenticators to new phones after verification through the Orchard Works…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 540 tokens · pinned 6 days ago

  • Account Status

    This skill retrieves a customer's account and service details, then manages contact preferences by withdrawing them from retention offers and marketing…

    Claude Code, Codex, Cursor +3 · about 110 tokens · pinned 6 days ago

  • Application Enquiry

    This skill helps applicants check the status of their Pine University applications (admission, aid, scholarships, enrollment) and records their enquiries with…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 720 tokens · pinned 6 days ago

  • Appointment Reminders

    This skill manages appointment reminders for Cedar Clinic by sending text notifications, handling patient responses, and tracking delivery status.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 600 tokens · pinned 6 days ago

  • Book Advisor Appointment

    This skill enables an agent to book a single appointment with a Northgate Bank advisor for mortgage, investment, business, or everyday banking services.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 620 tokens · pinned 6 days ago

  • Budget Plan

    The agent explains budget plans for utility billing, which smooth future payment amounts based on usage estimates without reducing outstanding balance.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 770 tokens · pinned 6 days ago

All Security skills
  • claude-security

    Scans your repository for security issues using Claude, examines code changes or commits for vulnerabilities, and generates patch files to fix findings.

    by AnthropicOfficial publisher

    Claude Code · about 1K tokens · pinned 6 days ago

  • sensitive-logging-audit

    The skill helps audit and fix sensitive data leaks in Python SDK logging, exceptions, and telemetry by collecting candidate sinks, manually tracing values…

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 970 tokens · pinned 6 days ago

  • security-audit

    This skill guides security audits of codebases, APIs, and services by finding vulnerabilities that cross real trust boundaries.

    by CloudflareOfficial publisher

    Contains scripts

    Claude Code · about 5.4K tokens · pinned 6 days ago

  • assess-patch-risk

    This skill analyzes patch artifacts to assess their program impact, regression risk, and suitability for automated merging.

    by OpenAIOfficial publisher

    Codex · about 2.3K tokens · pinned 6 days ago

  • attack-path-analysis

    This skill analyzes security findings to build explicit attack paths from source to sink, calibrates severity, and decides whether each finding is reportable.

    by OpenAIOfficial publisher

    Codex · about 2.1K tokens · pinned 6 days ago

  • deep-security-scan

    Performs exhaustive, multi-pass security analysis across a repository or scoped directory by running repeated independent security scans and aggregating…

    by OpenAIOfficial publisher

    Codex · about 3.4K tokens · pinned 6 days ago

Open roles at Rasa

No open roles at Rasa on the Agent Native jobs board right now.

Browse the jobs board

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