Skill Creator

What it does

When your agent uses it

• Users want to turn a workflow
• Repeatable multi-step process into a permanent reusable skill that future sessions can invoke reliably

Example prompts

• “create a skill for...”
• “把这个流程存下来”
• “以后都这样做”
• “/skill-creator”

Requirements

• Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Check for existing skill
2. 2Write SKILL.md
3. 3Register in load_skills.yaml
4. 4Verify
5. 5Return result

What it can do on your machine

Read from SKILL.md and the folder at commit d5cfc79. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 7 files in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Creator loads about 1.6k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 172 tokens; SKILL.md has 600 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~172

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from kid0317/crewai_mas_demo at commit d5cfc79, republished under its Apache-2.0 licence (© kid0317). 600 words, ~1,586 tokens.

name

skill-creator

description

Create new skills and save them to the project's shared skills directory. Use this skill when users want to turn a workflow, SOP, or repeatable multi-step process into a permanent reusable skill that future sessions can invoke reliably. Activate when: user says "保存为技能" / "create a skill for..." / "把这个流程存下来" / "以后都这样做" / "make this repeatable" / "turn this into a skill". Also activate proactively when a complex multi-step workflow is described in conversation and standardized, reliable execution would clearly benefit the user. Do NOT activate for: simple facts or preferences (use memory-save), one-time tasks, or things that don't need to run consistently every time.

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter (name, description required)
│   └── Markdown instructions
└── Bundled Resources (optional)
    ├── scripts/    - Executable code for deterministic/repetitive tasks
    ├── references/ - Docs loaded into context as needed
    └── assets/     - Files used in output (templates, icons, fonts)

## Commit message format
**Example:**
Input: Added user authentication with JWT tokens
Output: feat(auth): implement JWT-based authentication

## Report structure
Use this template:
# [Title]
## Executive summary
## Key findings
## Recommendations

mkdir /mnt/skills/<skill-name>/
write /mnt/skills/<skill-name>/SKILL.md  ← the drafted content

  - name: <skill-name>
    path: ./<skill-name>
    type: task        # spawns Sub-Crew in AIO-Sandbox
    enabled: true

{
  "errcode": 0,
  "errmsg": "success",
  "skill_name": "<skill-name>",
  "path": "/mnt/skills/<skill-name>/SKILL.md",
  "trigger": "one-line summary of when this skill activates"
}

© kid0317, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 17 other files (scripts, references, assets) in skills/skill-creator of kid0317/crewai_mas_demo.

• SKILL.md
• LICENSE.txt
• agents/analyzer.md
• agents/comparator.md
• agents/grader.md
• assets/eval_review.html
• eval-viewer/generate_review.py
• eval-viewer/viewer.html
• references/schemas.md
• scripts/__init__.py
• scripts/aggregate_benchmark.py
• scripts/generate_report.py
• scripts/improve_description.py
• scripts/package_skill.py
• scripts/quick_validate.py
• scripts/run_eval.py
• … and 2 more

Open the folder on GitHubat commit d5cfc79