template-skill

Codex compatibility note:

• Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author .claude/**; mirrors are generated.
• Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
• Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

Quick Summary

Goal: [One sentence — what this skill achieves].

Workflow:

1. [Step 1] — [description]
2. [Step 2] — [description]

Key Rules:

• [Most critical constraint]
• [Second constraint]

[Skill Title]

[Insert instructions below]

---

[IMPORTANT] Before multi-step work, track a few outcome/dependency tasks with one active task and a final consistency check. Use the host task tools or an equivalent tracker.

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Prerequisites: Select additional protocols for the new skill's actual procedures; adopt code-discovery guidance only for a code surface, through the skill-creator owner.

Protocol guides — Apply each protocol only when its read-when condition holds. If a protocol's text is not in your context, read its file below before you act on it.

• evidence-based-reasoning — Ground every material claim in file:line, config or source evidence, with stated confidence; making any claim, finding or recommendation → .claude/skills/shared/protocols/evidence-based-reasoning.md

IMPORTANT MUST ATTENTION cite file:line evidence for every claim; never speculate. Confidence >80% to act, <60% = do NOT recommend; "not enough evidence" is valid output.

Closing Reminders

IMPORTANT MUST ATTENTION track multi-step work by outcomes and dependencies before starting IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Keep task state current and verify the final result against the requested outcome.