claude-code-plugin-lite/skills/add-task/SKILL.md
Create a new task file following the taskmd specification. Use when the user wants to add a new task to the project.
npx skillsauth add driangle/taskmd add-taskInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a new task file — no CLI required.
The user's task description is in $ARGUMENTS.
Parse the user's input from $ARGUMENTS to extract:
Read configuration:
.taskmd.yaml if it exists for: task dir (default: tasks), id config (strategy, prefix, padding, length), and phases.taskmd.yaml for configured phases and use the matching id. If the phase doesn't exist yet, add it to the phases array in .taskmd.yaml (see SPEC_REFERENCE.md for the phases config format)Determine the group based on the task's domain:
--group, use thatcli, web/frontend → web, or root for cross-cutting)Generate the task ID:
.taskmd.yaml (default: sequential)Glob for <task-dir>/**/*.md to determine used IDspadding width (default 3). E.g., if highest is 042, next is 043dr-001, dr-002length (default 6) containing at least one digitCreate the task file using Write:
<task-dir>/<group>/<ID>-<slug-title>.md (or <task-dir>/<ID>-<slug-title>.md if no group)---
id: "<ID>"
title: "<title>"
status: pending
priority: <priority if provided>
effort: <effort if provided>
type: <type if provided>
tags: [<tags if provided>]
dependencies: [<deps if provided>]
parent: "<parent if provided>"
owner: "<owner if provided>"
phase: "<phase if provided>"
created: <today's date YYYY-MM-DD>
---
# <Title>
## Objective
<Description derived from user's input>
## Tasks
- [ ] <Subtask 1>
- [ ] <Subtask 2>
## Acceptance Criteria
- <Criterion derived from the task>
Only include optional frontmatter fields that were specified or can be inferred. Don't include empty fields.
Confirm the created file path and ID to the user
See SPEC_REFERENCE.md (in the plugin root) for valid field values, ID strategies, and frontmatter schema.
data-ai
Pick up a task and execute it using subagents to parallelize independent workstreams. Use when the user wants to work on a task with maximum concurrency.
tools
Mark a task as completed. Use when the user wants to mark a task as done or complete.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).