skills-registration
- Repo stars 340
- License Complete terms in LICENSE.txt
- Author updated Live
- Author repo agentkit-samples
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @bytedance · Complete terms in LICENSE.txt
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Required · Vendor-specific
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- Env read
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skills-registration
description: Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to…
category: ai
runtime: Python
---
# skills-registration output preview
## PART A: Task fit
- Use case: Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to publish, upload, or register a skill they have created. This skill registers a local skill directory to the AgentKit platform. It zips the directory, uploads it to TOS, and calls the CreateSkill API. requires Vendor-specific API key; runs on Python. Works with ….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / Requirements / Example” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to publish, upload, or register a skill they have created. This skill registers a local skill directory to the AgentKit platform. It zips the directory, uploads it to TOS, and calls the CreateSkill API. requires Vendor-specific API key; runs on Python. Works with …”.
- **02** When the source has headings, the agent prioritizes “Usage / Requirements / Example” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, read environment variables; may access external network resources; requires Vendor-specific API keys.
## Running Rules
- read files, write/modify files, read environment variables; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, read environment variables.
Validate with a small run
Start with a small task and check whether the result follows “Usage / Requirements / Example”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skills-registration
description: Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to…
category: ai
source: bytedance/agentkit-samples
---
# skills-registration
## When to use
- Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to publish, upload, or re…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Usage / Requirements / Example” and keep inference separate from source facts.
- read files, write/modify files, read environment variables; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skills-registration" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / Requirements / Example
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files, read environment variables | may access external network resources
guardrails -> requires Vendor-specific API keys + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}AgentKit Skill Registration
This skill registers a local skill directory to the AgentKit platform. It zips the directory, uploads it to TOS, and calls the CreateSkill API.
Usage
To register a skill, run the following command:
python3 scripts/skills_register.py <path_to_skill_directory>Replace <path_to_skill_directory> with the path to the folder containing your SKILL.md.
Requirements
veadkpython package installed.- Environment variables:
VOLCENGINE_ACCESS_KEYVOLCENGINE_SECRET_KEYSKILL_SPACE_ID(required, comma-separated list of skill space IDs)AGENTKIT_TOOL_REGION(optional, defaults to cn-beijing)
Example
python3 scripts/skills_register.py ./my-new-skillError Handling
- IF the script raises the error
VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY are not set in environment variables., inform the user that they need to provide theVOLCENGINE_ACCESS_KEYandVOLCENGINE_SECRET_KEYenvironment variable. Write it to the environment variable file in the workspace. If the file already exists, append it to the end. Ensure the environment variable format is correct, make the environment variable effective, and retry the task that just failed.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review