stevesolun/ctx / skills/skill-router
skill-router
VerifiedAlive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.2 KB |
| references/01-scope.md | markdown | 1.0 KB |
| references/02-plan.md | markdown | 1.0 KB |
| references/03-build.md | markdown | 1.7 KB |
| references/04-check.md | markdown | 1.0 KB |
| references/05-deliver.md | markdown | 1.3 KB |
SKILL.md
View on GitHub---
name: skill-router
description: Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
type: meta
priority: 99
always_load: true
---
# skill-router
Reads `~/.claude/skill-manifest.json` and `~/.claude/pending-skills.json`.
Executes the 5-stage pipeline. **No skipping stages.**
## Pipeline
```
01-scope → 02-plan → 03-build → 04-check → 05-deliver
```
## Invoke When
- Session starts (automatic via using-superpowers pattern)
- User switches projects or opens a new repo
- `pending-skills.json` exists (mid-session signals detected)
- User asks "what skills are loaded?" or "update my skills"
## Stage Files
All stage files are in `references/`. Read and follow each in order.
1. **[01-scope](references/01-scope.md)** — Is a scan needed?
2. **[02-plan](references/02-plan.md)** — Run the scanner
3. **[03-build](references/03-build.md)** — Resolve the manifest
4. **[04-check](references/04-check.md)** — Validate before loading
5. **[05-deliver](references/05-deliver.md)** — Present to user
See [check-gates.md](check-gates.md) for validation questions.
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 |