技能详情(站内镜像,无评论)
作者:Ali Aghareza @aghareza
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v0.1.3
统计:⭐ 1 · 563 · 2 current installs · 2 all-time installs
⭐ 1
安装量(当前) 2
🛡 VirusTotal :良性 · OpenClaw :良性
Package:aghareza/taskwarrior
安全扫描(ClawHub)
- VirusTotal :良性
- OpenClaw :良性
OpenClaw 评估
The skill is a narrow, workspace-scoped wrapper around the Taskwarrior CLI and its requirements and instructions are consistent with that purpose.
目的
Name and description match the requested artifact: the skill requires the 'task' (Taskwarrior) binary and performs only Taskwarrior operations scoped to the active workspace. Requested binaries and declared capabilities are proportional to the stated task-management purpose.
说明范围
SKILL.md instructs only Taskwarrior commands and workspace-local file operations (creating .openclaw/taskwarrior/, writing a taskrc there, using TASKRC/TASKDATA env vars). It does not read unrelated system files or exfiltrate data to external endpoints. It explicitly forbids writing global ~/.task unless explicitly requested.
安装机制
No bundled code is present; install metadata references package managers (brew/apt) which is reasonable for obtaining the Taskwarrior binary. The skill itself states it will not perform runtime installs. This is coherent for a CLI-wrapper skill, though there is a small metadata mismatch (SKILL.md metadata includes apt and brew, while registry install spec lists only brew) — a minor documentation inconsistency, not a security issue.
证书
The skill requires no credentials or sensitive environment variables. It optionally reads standard workspace-related env vars (OPENCLAW_WORKSPACE, WORKSPACE, PROJECT_DIR, REPO_ROOT) to resolve the workspace root — reasonable and scoped. No unexpected secrets or unrelated services are requested.
持久
always:false and no modifications to other skills or system-wide settings. The skill writes only to the workspace-scoped .openclaw/taskwarrior/ area (its own data), which is appropriate for a task-management skill. Autonomous invocation is the platform default but is not in itself a red flag here.
综合结论
This skill is a thin wrapper around the Taskwarrior CLI and appears to be what it claims: it requires the 'task' binary and will store all data under <workspace>/.openclaw/taskwarrior/. Before installing/use: 1) Ensure you trust the environment image (that 'task' is the official Taskwarrior binary). 2) Confirm you are comfortable with the skill writing task state into the workspace directory (it will not touch your global ~/.task or ~/.taskrc …
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「taskwarrior」。简介:Workspace-local task management powered by Taskwarrior. Add, organize, and trac…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/aghareza/taskwarrior/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: taskwarrior
description: >
Workspace-local task management powered by Taskwarrior. Add, organize,
and track tasks by project, tags, due dates, and priority with all data
stored inside the active workspace.
metadata: |
{
"openclaw": {
"requires": {
"bins": ["task"]
},
"install": [
{
"kind": "apt",
"bins": ["task"],
"packages": ["taskwarrior"]
},
{
"kind": "brew",
"bins": ["task"],
"packages": ["task"]
}
]
}
}
---
# Taskwarrior (Workspace-Local Tasks) — AgentSkill
## Skill name
taskwarrior
## Purpose
Manage tasks using Taskwarrior as the backend with data stored inside the current workspace. This skill provides a safe, workspace-scoped wrapper for common Taskwarrior operations (add/list/modify/done/projects/tags/due/priority/annotations).
## Runtime requirements (ClawHub)
This skill **requires Taskwarrior to already be available** in the runtime environment (e.g., included in the base image).
- Validation: run `task --version`
- If missing: report the dependency and instruct the environment owner to install system package **taskwarrior** (some distros package it as **task**).
This skill **does not perform system-level installs** (no `apt`, `brew`, `dnf`, etc.).
## Workspace root resolution (portable)
The skill resolves the workspace root at runtime:
1) If set, use the first available of:
- OPENCLAW_WORKSPACE
- WORKSPACE
- PROJECT_DIR
- REPO_ROOT
2) Otherwise, fallback to the current working directory.
All Taskwarrior data is stored under:
`<workspace>/.openclaw/taskwarrior/`
## Workspace-local Taskwarrior home
- taskrc: `<workspace>/.openclaw/taskwarrior/taskrc`
- data dir: `<workspace>/.openclaw/taskwarrior/.task/`
Every Taskwarrior command MUST run with:
- `TASKRC=<workspace>/.openclaw/taskwarrior/taskrc`
- (optional) `TASKDATA=<workspace>/.openclaw/taskwarrior/.task`
Never write to global `~/.task` or `~/.taskrc` unless the user explicitly asks to use global storage.
## Core workflow
1) **Check dependency**
- Run: `task --version`
- If missing: stop and return dependency instructions (see references/clawhub_notes.md).
2) **Initialize workspace storage**
- Ensure directories exist:
- `<workspace>/.openclaw/taskwarrior/`
- `<workspace>/.openclaw/taskwarrior/.task/`
- Ensure `<workspace>/.openclaw/taskwarrior/taskrc` contains at least:
- `data.location=<workspace>/.openclaw/taskwarrior/.task`
- `confirmation=off`
- `verbose=off`
3) **Execute requested operations**
- Prefer stable/common commands (see references/taskwarrior_cheatsheet.md).
4) **Verify results**
- After any mutation, show a focused `task <id> info` or filtered `task <filter> list`.
## Supported operations (useful subset)
- Add tasks: `task add ...`
- List tasks: `task list`, `task <filter> list`
- Modify tasks: `task <id> modify ...`
- Complete tasks: `task <id> done`
- Start/stop: `task <id> start|stop` (if desired)
- Projects/tags: `task projects`, `task tags`, `project:<name>`, `+tag`, `-tag`
- Due/priorities: `due:<date>`, `priority:H|M|L`
- Notes: `task <id> annotate "..."`
## Safety
Follow `references/safe_command_policy.md`.
Highlights:
- No delete/purge unless explicitly requested.
- Avoid broad bulk changes without previewing the matching set.
- No global config writes by default.
## References
- references/workspace_data_layout.md
- references/taskwarrior_cheatsheet.md
- references/safe_command_policy.md
- references/examples.md
- references/clawhub_notes.md