Skip to content
Back to skills

Finishing Task

ASecurity

Use only when the user explicitly asks to complete a tracked Local Task and the task needs a durable outcome.

  • 7 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 2, 2026
ai-agentssql

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add yishan-io/yishan-mono --skill finishing-task --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Finishing Task?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Finishing Task
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yishan-io-finishing-task/badge)](https://www.skillsdirectory.com/skills/yishan-io-finishing-task)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: finishing-task
description: Use only when the user explicitly asks to complete a tracked Local Task and the task needs a durable outcome.
---

# Finishing Task

Use this skill only when the user explicitly asks to complete a Local Task.

The SQLite-backed Local Task daemon owns task metadata and status. Pi uses the managed daemon through its configured endpoint. The daemon generates UUIDs. Imported IDs stay opaque.

## Preconditions

Before completion, make sure that:

- The requested work is implemented.
- Relevant verification passes.
- Important review feedback is resolved or accepted.
- The plan and notes contain useful task history.
- The outcome states only delivered work.

Use `task_read` for the synthetic, read-only brief. Use `task_list` or `task_search` to locate the task. Project scope uses `YISHAN_PROJECT_ID`. Without it, use global tasks only.

Use `task_update` for title, description, new, progressing, or cancelled status, priority, or tags. It cannot set done.

## Prepare the Outcome

Write a concise factual outcome. Include delivered behavior, meaningful files or configuration changes, and follow-up work when needed.

Use `task_write` for `plan`, `notes`, or `outcome`. Use `task_append_note` for task-specific facts. Do not write the synthetic brief.

## Complete the Task

After explicit user direction that all work is complete, perform the precondition self-checks. Then use `task_finish` with the factual outcome. Do not ask for confirmation again. The tool writes `outcome` and marks the task done.

## Boundaries

Do not complete a task without explicit user direction. Do not bypass the daemon. Do not create or parse task IDs. Do not use `task_update` for completion.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.