with one click
template-skill
Replace with the capability this skill provides.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Replace with the capability this skill provides.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Flags risky shell commands and unsafe tree ops.
Detects high-confidence security risks in code.
Surfaces the dojo's non-negotiable prime directives.
Activates the dojo framework at the start of a session.
Plans multi-step work before writing code.
Captures lessons and promotes recurring patterns.
| name | template-skill |
| description | Replace with the capability this skill provides. |
| tier | practical |
| category | workflow |
| created_by | human |
| platforms | ["windows","macos","linux"] |
| tags | [] |
| author | Your Name (@your-handle) |
Two to three sentences stating what this skill does AND what it deliberately does NOT do. The "does not" half is as important as the "does" half — it prevents over-triggering on adjacent tasks.
Specific triggers, keywords, and contexts that should activate the skill. Be slightly pushy — agents undertrigger more often than they overtrigger.
What must be true before the skill can run.
If a prerequisite is missing, the skill must fail loudly — never degrade silently.
One-screen overview of the canonical happy path. If the skill ships a script, show the command:
scripts/example.sh --flag value
| Action | Command / Tool | Notes |
|---|---|---|
| Common op 1 | view path | Use the Copilot view tool, not shell cat. |
| Common op 2 | grep pattern | Use the Copilot grep tool, not shell grep/rg. |
| Common op 3 | scripts/example.sh | Ships with the skill. |
The agent should be able to act from this table alone for routine cases.
Step-by-step detailed workflow. This is where the depth lives.
What the agent checks before acting.
The actual work. Reference real Copilot tools in backticks (view, edit, grep, glob, powershell, web_fetch, task). Do NOT instruct the agent to call bare shell utilities (cat, sed, find) that have a Copilot wrapper.
Intermediate verification before moving on.
Imperative "DO NOT" register of failure modes this skill prevents.
How the agent (or a reviewer) proves the skill worked.
scripts/verify.sh passes