---
name: reusable-skill-authoring
description: "Create a focused, portable skill package with useful triggers and complete references. Use when the user requests reusable skill authoring. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# Reusable Skill Authoring

Create a focused, portable skill package with useful triggers and complete references.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Intended tasks
- Representative examples
- Runtime ownership contract
- Redistribution requirements

## Methods

### Define the trigger

Identify the knowledge that actually changes the agent’s decisions. Write a concise trigger-oriented description and keep unrelated tasks outside its activation scope.

### Structure reusable knowledge

Keep essential guidance in SKILL.md and put detailed procedures in linked references. Include scripts only when deterministic execution adds value and test them with fixtures.

### Separate client truth

Remove client facts from names, examples, scripts, templates and metadata. Use live Workspace Context for client truth and canonical Runtime owners for execution rules.

### Validate the complete package

Validate archive structure and all relative references, test matching and unrelated requests, and compare resulting artifacts. Do not claim host installation merely because a package validator passed.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.