Skip to content
Back to skills

Skill

ASecurity

Drive a slimspec change end to end (explore, plan, apply, verify, refine, ground, init), resuming from `.slimspec/changes/`. Use when the user says `slimspec <phase|mode> <args>`, asks to build a change with slimspec, or asks to resume or list slimspec changes.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agents

Works with

  • cli

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add yushman/slimspec --skill skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yushman-skill/badge)](https://www.skillsdirectory.com/skills/yushman-skill)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: slimspec
description: "Drive a slimspec change end to end (explore, plan, apply, verify, refine, ground, init), resuming from `.slimspec/changes/`. Use when the user says `slimspec <phase|mode> <args>`, asks to build a change with slimspec, or asks to resume or list slimspec changes."
---

# slimspec

The slimspec install root is `<root>`. It is the plugin root: wherever the slimspec files say `${CLAUDE_PLUGIN_ROOT}`, use `<root>`.

1. Identify your host by the tools you have. OpenCode has the `question` and `task` tools. Codex has subagent spawn tools and no `question` tool. ZCode has the `Task` subagent tool and no `question` tool. Qwen Code has the `agent` and `ask_user_question` tools. Antigravity CLI has the `invoke_subagent` tool. If unsure, pick the closest match by tools.
2. Read that host's mapping and follow it for the whole session: `<root>/hosts/opencode.md`, `<root>/hosts/codex.md`, `<root>/hosts/zcode.md`, `<root>/hosts/qwen.md` or `<root>/hosts/antigravity.md`.
3. Look at the first argument after `slimspec`. If it names a phase or mode (`explore`, `plan`, `apply`, `verify`, `refine`, `ground`, `init`, `fast`, `medium`, `full`), read `<root>/skills/<it>/SKILL.md` and follow it with the rest of the arguments as its `$ARGUMENTS`. Otherwise (an idea, a change slug, or nothing) read `<root>/skills/slimspec/SKILL.md` and follow it with all the arguments as its `$ARGUMENTS`.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.