- Home
- Skills
- Agents & Orchestration
- skilled task executor
Works with the AI Agents you already use
skilled task executor
Draft, track, and execute development tasks through a tool-agnostic workflow integrated with your tracker.
Free
skilled task executor
Example session with this skill installed
Break down the new user authentication feature into tasks for Jira and draft the implementation plan.
- Read your context and instructions
- Compiled the skilled task executor
I have analyzed the authentication requirements and mapped out the necessary tasks. I will act in the project-manager role to draft these items for Jira.
Task Breakdown: User Authentication Feature
| Task Title | Description | Acceptance Criteria | Priority |
|---|---|---|---|
| AUTH-001: Set up JWT middleware | Implement JSON Web Token verification for API routes. | Middleware rejects requests without valid tokens; 401 status returned. | High |
| AUTH-002: Create Login Endpoint | Develop POST /api/login to validate credentials and return JWT. | Validates against user DB; returns signed token; handles bcrypt comparison. | High |
| AUTH-003: User Registration Flow | Implement POST /api/register with input validation. | Validates email format; hashes passwords before storage; prevents duplicates. | Medium |
| AUTH-004: Auth Unit Testing | Write unit tests for middleware and token generation logic. | 100% coverage on auth utility functions; mock DB calls. | Medium |
Implementation Plan
- Discovery: Inspect
src/middlewareandsrc/controllersfor existing patterns. - Branching: Create
feature/user-auth-foundationbranch. - Execution: Implement AUTH-001 and AUTH-002 sequentially, moving Jira status to 'In Progress' for each.
- Validation: Run
npm testand verify token persistence in local storage.
Next steps
- Confirm if these drafts should be published to your Jira project via the
jira.task.createtool. - Identify if there is an existing User model I should reference before drafting the registration logic.
- Specify if you want me to initiate the implementation of AUTH-001 immediately.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing the gap between task trackers and your local development environment often leads to fragmented workflows. This skill bridges that gap by providing a tool-agnostic system for planning, creating, and executing software tasks directly within your IDE or agent runtime. It eliminates the need to manually toggle between browser tabs to update ticket statuses or search for acceptance criteria.
What it does
- Task creation and planning translates high-level feature requests into structured tickets with clear acceptance criteria and subtasks.
- Bi-directional sync ensures your local progress, branch state, and PR status are reflected in your task tracker without manual data entry.
- Workflow enforcement manages the implementation lifecycle from discovery and requirement analysis to validation and state transitions.
- Platform integration maps conceptual capabilities to specific MCP tools or connectors for live data access and publication.
- Verification and validation runs local tests and records truthful results against the task requirements before marking items as complete.
How it works
- Discovery identifies the requested role and identifies available platform connectors through the runtime's tool registry.
- Analysis retrieves task data or repository context to understand requirements, linked artifacts, and current git state.
- Execution gate triggers a state change in the tracker to "In Progress" once implementation begins, ensuring the team sees active work.
- Implementation applies code changes within the task scope while adhering to defined branch and commit checkpoint policies.
Frameworks & tools
This tool-agnostic skill works with any task platform providing an MCP connector, such as Jira, Linear, Asana, or GitHub Issues. It integrates with standard git workflows, CI pipelines, and local testing frameworks exposed through your agent's runtime tools.
Why this beats prompting it yourself
Generic prompts often hallucinate ticket IDs or skip critical state transitions like moving a task to "In Progress" before editing code. This skill provides a rigid execution gate and semantic state mapping that ensures your tracker remains a source of truth without manual intervention.
Use cases
- Break down a monolithic feature request into a series of actionable Jira tickets.
- Search for existing bugs in Linear and implement a fix tracked against the ticket.
- Automatically update a GitHub issue comment with validation results after a test run.
- Draft a project plan as a PM without committing changes to the live tracker.
Known limitations
Does not support direct API calls or credential extraction; requires an active MCP connector for live platform operations. Execution is restricted to the tools and permissions exposed by the host environment.
Requires pre-configured MCP connectors for live platform sync. Cannot bypass host security to access credentials or perform direct HTTP calls.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 28 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts