tools
This Claude Code skill manages persistent, reusable procedures by creating, updating, or deleting skill files stored in an isolated directory. Use it to codify repeatable workflows like setup sequences, debugging recipes, or project-specific processes that should be available across future sessions while remaining separate from manually authored skills.
git clone --depth 1 https://github.com/can1357/oh-my-pi /tmp/tools && cp -r /tmp/tools/packages/coding-agent/src/prompts/tools/manage- ~/.claude/skills/toolsmanage-skill.md
Create, update, or delete a managed skill — a `SKILL.md` written to an isolated directory (`~/.omp/agent/managed-skills`) and surfaced like a normal skill in future sessions. Managed skills are for repeatable procedures worth codifying: a setup sequence, a debugging recipe, a project-specific workflow. They are kept separate from user-authored skills and this tool NEVER edits those. - `action: "create"` — requires `name`, `description`, and `body`. Fails if the skill already exists. - `action: "update"` — requires `name`, `description`, and `body`. Fails if the skill does not exist. Overwrites the body. - `action: "delete"` — requires `name`. Fails if the skill does not exist. `name` is kebab-case (lowercase letters, digits, hyphens). `description` is a single line stating when to use the skill — it drives discovery, so make it specific. `body` is the SKILL.md content in markdown; do not include frontmatter (it is generated from `name` and `description`).
Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments. Use when compressing text for prompts, reducing token count, preparing context for LLM input, or making documentation more token-efficient. Applies LLM-aware compression rules that delete predictable grammar while preserving semantics.
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.