Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From improve
Map the topology of a process — discover which files, agents, skills, hooks, crons, and configurations constitute it. Produces a topology map that other improve skills use to know where to make changes. Use when first engaging with a process, when asked to "attach to" or "map" a process, or when you need to understand what a process consists of. Do NOT use for making changes — use improve:fix for that.
npx claudepluginhub cosmicdreams/claude-plugins --plugin improveHow this skill is triggered — by the user, by Claude, or both
Slash command
/improve:attachThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before you can improve a process, you need to know what it's made of. This skill discovers and maps the constituent parts of any process in the plugin ecosystem.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Explores codebases via GitNexus: discover repos, query execution flows, trace processes, inspect symbol callers/callees, and review architecture.
Share bugs, ideas, or general feedback.
Before you can improve a process, you need to know what it's made of. This skill discovers and maps the constituent parts of any process in the plugin ecosystem.
A "process" is anything that runs over time to achieve a purpose:
Where does the process start? A skill invocation, a cron, a hook, an agent spawn? Find it.
From the entry point, trace what gets invoked:
| Component type | Where to look | What to record |
|---|---|---|
| Agents | <plugin>/agents/*.md | Name, model, tools, purpose |
| Skills | <plugin>/skills/*/SKILL.md | Name, triggers, what it does |
| Hooks | <plugin>/hooks/hooks.json | Event, script path, what it does |
| Crons | Active cron loops | Schedule, what it invokes |
| Config files | .claude/, .local.md, vault | What parameters are tunable |
| Board/state | .beads/, state files | What state the process reads/writes |
| External deps | CLIs, APIs, DDEV | What external tools are required |
If a domain :improve skill exists (e.g. sprint:improve, drover:improve), invoke it — it knows the topology better than generic discovery.
Every process exists to achieve something. State it explicitly:
The purpose statement is what all improvement is measured against.
Write a structured summary. Format:
## Process: <name>
**Purpose:** <one sentence>
**Entry point:** <how it starts>
**Components:**
- Agent: <name> (<plugin>/agents/<file>) — <purpose>
- Skill: <name> (<plugin>/skills/<dir>/SKILL.md) — <purpose>
- Hook: <event> (<plugin>/hooks/scripts/<file>) — <purpose>
- Config: <path> — <what it controls>
- State: <path> — <what it tracks>
**Tunable parameters:** <list of things that can be changed>
**Known constraints:** <DDEV slots, API limits, model costs, etc.>
This map is what improve:fix uses to know where to make changes and what improve:lint uses to know what to check.