pelagornis/styleguide / .agents/skills/pelagornis-skill-authoring
pelagornis-skill-authoring
VerifiedCreate, review, or improve portable Agent Skills using the Pelagornis conventions and the open Agent Skills specification. Use when adding or maintaining a reusable agent workflow.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.3 KB |
| references/trigger-evals.md | markdown | 1.6 KB |
SKILL.md
View on GitHub---
name: pelagornis-skill-authoring
description: Create, review, or improve portable Agent Skills using the Pelagornis conventions and the open Agent Skills specification. Use when adding or maintaining a reusable agent workflow.
---
# Pelagornis skill authoring
## Purpose
Create focused, portable Skills that encode repeatable workflows without duplicating permanent repository instructions.
## Workflow
1. Confirm that the workflow is repeatable and belongs in a Skill rather than repository instructions.
2. Choose a concise `pelagornis-` name and trigger-specific description.
3. Write a focused `SKILL.md` with purpose, context, workflow, verification, output, and safety boundaries.
4. Put detailed material in `references/`, deterministic operations in `scripts/`, and reusable files in `assets/` only when needed.
5. Validate frontmatter, directory structure, links, uniqueness, and triggering prompts using [the evaluation set](references/trigger-evals.md).
6. Check the Skill with each supported agent before claiming cross-agent compatibility.
## Output
Report the Skill's trigger conditions, structure, validation, and agent-specific limitations.
## Boundaries
Do not add unsupported agent-specific frontmatter to a portable shared Skill. Do not create a Skill solely to restate permanent repository instructions.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |