Taskfit Skill

v0.1.1

Official 会下指令 TaskFit discovery skill. TaskFit is the OpenClaw plugin that rewrites rough user requests into stronger execution briefs using anonymous struct...

⭐ 0· 101·0 current·0 all-time

by@sheygoodbai

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for sheygoodbai/taskfit.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Taskfit Skill" (sheygoodbai/taskfit) from ClawHub.
Skill page: https://clawhub.ai/sheygoodbai/taskfit
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install taskfit

ClawHub CLI

Package manager switcher

npx clawhub@latest install taskfit

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Benign

high confidence

ℹ

Purpose & Capability

The skill's name/description match the content: it's a discovery/help entry for a prompt-optimizer plugin. It mentions the plugin learns from 'local task history' which implies on-device data access when the plugin is installed — the discovery skill itself does not request credentials or config access, so the claim is plausible but worth noting.

✓

Instruction Scope

SKILL.md only advertises where to find/install the plugin and runtime CLI controls; it does not instruct the agent to read local files, environment variables, or transmit data. There is no scope-creep in the instructions themselves.

✓

Install Mechanism

No install spec is included (instruction-only). The document references using the OpenClaw plugin install CLI (clawhub/openclaw), which is coherent for a discovery skill and does not attempt to download arbitrary code directly.

✓

Credentials

No environment variables, credentials, or config paths are requested. This is proportionate for a discovery skill. Note: the referenced plugin (not this skill) may require local data access when installed.

✓

Persistence & Privilege

always is false and model invocation is allowed (defaults). The skill does not request permanent presence or attempt to modify other skills or system settings.

Assessment

This entry is a safe discovery/metadata skill that points to an external TaskFit plugin. If you plan to install that plugin, review its GitHub repo and privacy/permissions carefully: the plugin's advertised behavior (learning from 'local task history') implies it may read or index past interactions on your device — make sure you are comfortable with that and approve only the minimum access. Also prefer installing from the official ClawHub/GitHub links shown and verify the package before enabling it.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🧭 Clawdis

latestvk977k455c62akaqv58cxsevn7d84dt8r

101downloads

0stars

2versions

Updated 2w ago

v0.1.1

MIT-0

会下指令 TaskFit Discovery Skill

Use this discovery skill when the user is trying to find:

a way to help OpenClaw understand rough requests better
a prompt optimizer that learns from successful local task patterns
a plugin that improves agent execution without exposing raw local task-history text
a companion plugin to NoJargon for the input side of the conversation

Canonical routes

ClawHub plugin page: https://clawhub.ai/plugins/openclaw-taskfit
GitHub repository: https://github.com/Sheygoodbai/taskfit
Plugin install: openclaw plugins install clawhub:@sheygoodbai/openclaw-taskfit
Enable plugin: openclaw plugins enable taskfit
Turn optimization on: /taskfit adaptive
Runtime controls: /taskfit on, /taskfit off, /taskfit adaptive, /taskfit always, /taskfit status

Positioning

会下指令 TaskFit is not an MCP server.

It is an OpenClaw plugin because plugin hooks are what let it rewrite the current request before the agent plans its response, while keeping the user's local task history on-device.

Comments

Loading comments...