From agent-almanac
Template for authoring Claude Code SKILL.md files with frontmatter description for auto-activation, usage triggers, inputs, bash-based procedures with expected outcomes and failure recovery, validation checklists, pitfalls, and examples. Use when creating new skills.
npx claudepluginhub pjt222/agent-almanacThis skill uses the workspace's default tool permissions.
---
Generates Claude Code skills and slash commands: interviews for requirements, selects type, crafts dense frontmatter with trigger phrases, initializes directories via Python script.
Guides creation, improvement, and structuring of skills for Claude Code plugins, including frontmatter metadata, workflows, scripts, references, and best practices.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Share bugs, ideas, or general feedback.
One paragraph: what this skill accomplishes and the value it provides.
Context sentence explaining what this step accomplishes.
# Concrete command or code the agent can execute
example_command --flag value
Expected: What success looks like. Be specific -- file created, output matches pattern, command exits 0.
On failure: Recovery action. What to check, what to retry, when to abort.
Context for this step.
next_command
Expected: Specific success indicator.
On failure: Recovery action.
Short worked examples showing the skill in action. Keep inline examples brief; move extended or multi-variant examples to references/EXAMPLES.md.
related-skill-name -- how it relates to this skillanother-skill -- how it relates