myicor/mypka/sops

Claude Code and agent skill by myicor/mypka

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install myicor/mypka/sops

SKILL.md

SOP-1012 Convert an external skill into scaffold shape

Users find skills online: Claude Skills (SKILL.md packages), prompt recipes, agent toolkits. None of them enter this scaffold verbatim. Larry routes the request; Nolan rules the conversion. A skill is DECOMPOSED into the scaffold's native shapes:

Skill partBecomesWhere
Procedure ("do X then Y")an SOP, steps marked [JUDGEMENT]/[SCRIPT]SOPs/
Bundled scripts / codescripts, red-tested before any SOP points at themScripts/
Reference tables, rules, style guidesa GuidelineGuidelines/
A role in disguise ("you are a...")agent ruling via [[SOP-1011-import-or-align-an-external-agentSOP-1011]] (hire / merge / extract)Agents/
Invocation trigger (slash command)a THIN runtime shim pointing at the SOP.claude/skills/<name>/SKILL.md

Steps:

  1. [SCRIPT] Scripts/import-inventory.py <skill-folder> produces the

inventory (shape skill-package when a SKILL.md is present, and every SKILL.md and script listed).

  1. [JUDGEMENT] Nolan drafts the decomposition per the table above,

with one line per target file. The user approves before any write.

  1. Write the pieces:
  • SOPs and Guidelines get the next free number ([[GL-1004-naming-rules|GL-1004]] naming) and

frontmatter per [[GL-1002-frontmatter-conventions|GL-1002]]; foreign prose is rewritten to this scaffold's shape, never pasted wholesale.

  • Scripts land in Scripts/, are made ROOT-relative (no absolute

paths from the source machine), and each new guard gets a case in run-red-tests.py and is watched go red ([[GL-1005-code-vs-instructions|GL-1005]] rule 4).

  • If the skill must stay invocable by name, add skill_summary and

skill_triggers (and skill_prerun when step 1 is an argument-free script) to the owning SOP's frontmatter; Scripts/scaffold-init.py plan, then apply, writes the SKILL.md pointer from them into 06 AI Team/AI Team Knowledge/Skills/<name>/ and links it into .claude/skills/ ([[SOP-1007-hire-a-new-agent|SOP-1007]] step 6b). The SOP is canonical; the generated file is a pointer. Never write or edit a SKILL.md by hand.

  1. Conflicts: a skill instruction that collides with AGENTS.md hard

rules or an existing SOP loses, and the conflict is reported to the user, never silently resolved.

  1. The manifest ([[WS-1004-import-and-convert-external-knowledge|WS-1004]] shape) records source, license note if the

skill carries one, and every file created. Update the touched agents' bios if their works-with lists grew.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/myicor/mypka/sops/badge)](https://verified-skill.com/skills/myicor/mypka/sops)

Something wrong with this skill or its page? Tell us.