# Send Skill Father to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-father",
    "name": "Skill Father",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/moodykong/skill-father",
    "canonicalUrl": "https://clawhub.ai/moodykong/skill-father",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/skill-father",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-father",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "skill-father",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T17:58:35.234Z",
      "expiresAt": "2026-05-10T17:58:35.234Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-father",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-father",
        "contentDisposition": "attachment; filename=\"skill-father-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "skill-father"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/skill-father"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-father",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-father",
    "agentUrl": "https://openagent3.xyz/skills/skill-father/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-father/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-father/agent.md"
  }
}
```
## Documentation

### Skill Father

This skill is Boss’s opinionated, authoritative standard for creating/updating skills.

It is based on the upstream skill-creator guidance, with extra requirements:

Always include Prerequisites checks (fail fast).
Keep skills portable/shareable: do not bake machine-specific settings into SKILL.md.
Always include Initialization / Installation / Onboarding that prompts the user when needed.
Make skills reproducible for other people/machines.

### Core principles (from skill-creator)

Concise is key: minimize context bloat.
Progressive disclosure: keep SKILL.md short; put big docs in references/, deterministic code in scripts/.
Avoid extra docs (README/CHANGELOG/etc.).

### 1) Prerequisites

Include a short section with concrete checks/commands.

Examples:

1Password-backed workflows:

op whoami must succeed (or, if service accounts are used, required env vars like OP_SERVICE_ACCOUNT_TOKEN must be set).


External CLIs:

command -v <tool> must exist; include install guidance if missing.

### 2) Configuration (portable)

Rules:

Never hardcode machine/user-specific paths, usernames, tenant IDs, tokens, etc. inside SKILL.md.
Prefer skill-local config files stored next to SKILL.md, e.g.:

config.env (dotenv-style KEY="VALUE")
config.json (structured)


Config must be split into two files:

config.env.example (or config.json.example) — checked-in/shareable example; never mutated by onboarding
config.env (or config.json) — real machine-specific values written/updated during onboarding


SKILL.md documents:

where config lives
required keys + defaults
which file is the example vs real
how to run onboarding to generate/update the real config

### 3) Initialization / Installation / Onboarding

Provide a guided first-run flow.

If setup is trivial and safe: can be silent.
Otherwise: ask the user for choices + confirmation.
Persist outcomes into the real skill-local config file (not into SKILL.md; do not modify the example file).
Prefer discovery + confirmation over assumptions.

Prefer an onboarding helper script when setup touches real machine state.

### Chat-first onboarding (Telegram-friendly)

When the primary interface is chat (e.g. Telegram), do not rely on TTY-style interactive prompts.

Requirement: Every child skill should explicitly document a “Preferred (chat-first)” onboarding path.

Preferred pattern:

Agent asks the user the required onboarding questions in chat.
Agent writes/updates the real skill-local config file.
Agent runs a smoke test and reports results.

If you do ship an interactive script, treat it as an optional convenience for users running it in a real terminal (document as “Optional (terminal)”).

Recommended onboarding script behaviors:

Generate/update the real config file from prompts and/or auto-discovery.
If editing an existing system config file (e.g. ~/.config/openclaw/env, ~/.ssh/config):

detect whether the target file exists; create if missing
for each key/entry that would change, show current vs new
prompt the user per item: keep / override / skip
for secrets/tokens, mask values in prompts


If a restart/reload is required:

first detect whether the service manager is available (e.g. systemctl --user status <svc>)
ask the user for confirmation before restarting
if not detectable/available, print clear manual instructions

Examples of onboarding steps:

Detect candidate paths/resources.
Present options.
Ask for confirmation.
Write config.
Validate config by running a quick self-test.

### 4) Reproducibility

The skill should work for other people with minimal edits.
Prefer parameterization/config + prompts.
Avoid environment-specific assumptions unless explicitly documented.

### 5) Executables / bin placement

Any executable scripts/binaries required by the skill should live inside the skill folder (or inside the relevant plugin’s folder).
For convenience, you may create a symlink into a common PATH location (e.g. ~/.local/bin/<name>), but the canonical copy should remain in the skill/plugin directory.

### Resource layout

Use the standard skill layout:

skill-name/
├── SKILL.md
├── config.env.example    # example (shareable)
├── config.env            # real machine-specific config (generated/updated by onboarding)
├── scripts/              # deterministic code
└── references/           # optional docs, loaded on demand

### Process checklist (for the agent)

Understand the task and collect concrete usage examples.
Plan resources (scripts/, references/, assets/) only if they reduce repetition or increase reliability.
Create/confirm required sections: Prerequisites, Config, Installation/Onboarding.
Implement the smallest working version.
Validate with a smoke test.
Iterate.

### Example expectations: ssh-op skill

Prereqs: confirm op whoami works (or service account env is set) and ssh/ssh-add/ssh-agent exist.
Onboarding: proactively discover/confirm:

vault name
SSH key item
host + host aliases stored in the 1Password item


Integration: check whether aliases exist in ~/.ssh/config; if missing, offer to add/update entries.
Config: store vault/item/host/aliases in a skill-local config file.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: moodykong
- Version: 0.1.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-03T17:58:35.234Z
- Expires at: 2026-05-10T17:58:35.234Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/skill-father)
- [Send to Agent page](https://openagent3.xyz/skills/skill-father/agent)
- [JSON manifest](https://openagent3.xyz/skills/skill-father/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/skill-father/agent.md)
- [Download page](https://openagent3.xyz/downloads/skill-father)