Skills Creator

What it does

When your agent uses it

• You need to summarize a workflow into a skill
• Write it into the fixed user skills root
• Refine a skills references for LiveAgents SkillsManager flow

Example prompts

• “s references for LiveAgent”
• “/skills-creator”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm the target skill name, trigger description, captured workflow, and any required reference/helper files.
2. 2Read references/agent-skill-format.md and references/authoring-patterns.md through file tools before shaping long instructions. Use…
3. 3Draft the SKILL.md body in imperative form. Keep frontmatter to name and description unless a compatibility reason requires an optional key.
4. 4Move deterministic or reusable details into files only when they are truly needed; keep explanatory material in references/; keep…
5. 5Use SkillsManager(action=create) to write the skill into the fixed user skills root. Keep conflict=fail unless the user explicitly wants…
6. 6Use SkillsManager(action=validate) after creation. Fix validation errors before packaging.
7. 7Use SkillsManager(action=package) only after validation passes and a distributable archive is required.
8. 8After creation, the new skill is enabled for the current conversation automatically; ask LiveAgent to rescan skills or reopen the Skills…

What it can do on your machine

Read from SKILL.md and the folder at commit 85029b5. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  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

Skills Creator loads about 821 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 361 words of instructions outside code blocks.

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

~62

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

~821

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

~2.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Stack-Cairn/LiveAgent at commit 85029b5, republished under its MIT licence (© Stack-Cairn). 361 words, ~821 tokens.

name

skills-creator

description

Create or update LiveAgent runtime skills. Use when you need to summarize a workflow into a skill, write it into the fixed user skills root, validate it, package it, or refine a skill's references for LiveAgent's SkillsManager flow.

SkillsManager(action=create, name=my-skill, description=..., body=...)
SkillsManager(action=validate, name=my-skill)
SkillsManager(action=package, name=my-skill)

© Stack-Cairn, MIT. 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 2 other files (references) in crates/agent-gui/src-tauri/prompt/skills/skills-creator of Stack-Cairn/LiveAgent.

• SKILL.md
• references/agent-skill-format.md
• references/authoring-patterns.md

Open the folder on GitHubat commit 85029b5