skills/backup/skill-deployer/SKILL.md
This skill deploys skills from the workspace's source code directory for skill development to the corresponding agent skills directory. You should use this skill when the user requests to deploy, install, or synchronize a skill. Or, when the skill has undergone code optimization, you should inquire with the user about using this skill for installation and deployment.
npx skillsauth add sampx/agent-tools skill-deployerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Deploy AI agent skills from source to target directories.
# Deploy skill (copy mode)
python3 scripts/deploy-skill.py --source /path/to/my-skill --dest .agents/skills/
# Deploy with symlink (for development)
python3 scripts/deploy-skill.py --source /path/to/my-skill --dest .agents/skills/ --symlink
# List available skills in a directory
python3 scripts/list-skills.py --dir ~/my-skills
| Agent | Project Level | Global Level |
|-------|---------------|--------------|
| Universal | .agents/skills/ | - |
| Claude Code | .claude/skills/ | ~/.claude/skills/ |
| OpenCode | .opencode/skills/ | ~/.config/opencode/skills/ |
| Codex | - | ~/.codex/skills/ |
Deploy a skill from source to target directory.
python3 scripts/deploy-skill.py -s <source> -d <target> [options]
Options:
--source, -s - Source directory containing SKILL.md (required)--dest, -d - Target directory (required)--symlink, -l - Create symlink instead of copying--force, -f - Overwrite existing skill--name, -n - Custom skill name (defaults to source directory name)INBOX Auto-Move:
Skills deployed from INBOX/ are automatically moved to universal/ (sibling directory) after deployment, where universal/ stores accepted/installed universal skills. The version.json will record the new source path in universal.
List all skills in a directory.
python3 scripts/list-skills.py --dir <path> [--format json]
Skills can include a .skillignore file to exclude files from deployment (similar to .gitignore):
tests/
logs/
__pycache__/
*.pyc
Each deployed skill includes a version.json file for tracking:
{
"name": "skill-deployer",
"source_path": "projects/ontology/skills/my-skills/skill-deployer",
"content_hash": "a1b2c3d4...",
"deployed_at": "2026-02-28T14:15:00Z",
"deploy_type": "copy"
}
Fields:
name - Skill namesource_path - Source directory (relative to project root)content_hash - SHA256 hash of source contentsdeployed_at - Deployment timestamp (ISO 8601)deploy_type - copy or symlinkCheck which deployed skills have source updates:
# View sync status
python3 scripts/sync-skills.py
# Interactive update outdated skills
python3 scripts/sync-skills.py --update
# JSON output
python3 scripts/sync-skills.py --json
# Custom target directory
python3 scripts/sync-skills.py --dest ~/.claude/skills/
Options:
--dest, -d - Deployed skills directory (default: .agents/skills/)--json - Output in JSON format--update - Interactive update for outdated skillsSync States:
updated - Source has changed, needs redeploymentunchanged - No changes detectedorphaned - Deployed but source path no longer existsuntracked - No version.json (deployed before sync feature)--symlink during development for live updatestools
Configure ellamaka, a fork of OpenCode with wopal-space mode. MUST use for any task about ellamaka config, agent frontmatter, permission rules, model/provider selection, formatter settings, config loading order, or why config changes are ignored. Trigger on requests about ellamaka or opencode config files, agent permission overrides, restricting subagents, custom/plugin tool permissions (e.g. wopal_task_*), disabling tools, configuring providers or models, formatter setup, config precedence or layering, or debugging settings that do not take effect. Use this skill even when the user says "opencode" if the actual runtime, config path, or behavior is ellamaka. Prefer this skill whenever the answer depends on the difference between ellamaka and upstream opencode, including wopal-space config loading, plugin tool permissions, or agent frontmatter precedence.
development
Plan quality verification for dev-flow. Goal-backward analysis ensures plans WILL achieve their stated goal before execution burns context. ⚠️ MUST use when: (1) Reviewing Plan quality before approve (2) Wopal completes Plan writing and needs quality gate (3) User asks to "check plan", "verify plan", "review plan" (4) Plan enters planning status and needs pre-execution validation 🔴 Trigger automatically when Plan is ready for review, even if user doesn't explicitly say "review". Agent: rook (read-only verification subagent) Mode: verification, not execution
development
Review implementation results for goal achievement and code quality. Supports both Plan-backed review and planless diff review. ⚠️ MUST use when: (1) Wopal delegates rook to review fae implementation output, (2) Prompt contains "review_type: implementation", (3) Prompt contains changed code file list or Plan path + implementation scope, (4) Any code review request from Wopal. 🔴 Trigger even when user does not explicitly mention "review" if the task involves verifying implementation results. This skill is rook-exclusive (only rook agent can load it).
tools
Foundation rules for how Wopal collaborates with sub-agents such as fae and rook. ⚠️ MUST load before ANY delegation — covers delegation tool APIs, task lifecycle, notifications, status handling, and recovery. 🔴 Trigger: "delegate", "let fae implement", "fae task", "rook review", "check task status", "cancel task", "abort task", "agent collaboration", "委派", "让 fae 执行", "fae 任务", "rook 审查", "检查状态", or any intent to hand work to a sub-agent. 🔴 Never delegate without loading this skill first. Skipping it is serious negligence. Note: this skill does not include workflow-specific prompt templates such as dev-flow templates. Those belong to the corresponding workflow skills.