Skip to content

stevesolun/ctx / skills/skill-router

skill-router

Verified

Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.

FileKindSize
SKILL.mdskill md1.2 KB
references/01-scope.mdmarkdown1.0 KB
references/02-plan.mdmarkdown1.0 KB
references/03-build.mdmarkdown1.7 KB
references/04-check.mdmarkdown1.0 KB
references/05-deliver.mdmarkdown1.3 KB

references/01-scope.md

View on GitHub
# Stage 1: Scope — Is a Scan Needed?

Determine which action to take before spending tokens on a full scan.

## Check Order

1. **Read** `~/.claude/pending-skills.json`
   - If exists and `generated_at` is < 2 hours old → action = `apply_pending`
   - Delete the file after reading (it is one-shot)

2. **Read** `~/.claude/skill-manifest.json`
   - Extract `repo_path` and `generated_at`
   - If `repo_path` ≠ current working directory → action = `full_scan`
   - If `generated_at` > 1 hour ago → action = `full_scan`
   - Otherwise → action = `use_cached`

3. **If no manifest exists** → action = `full_scan`

## Output

Emit one of:
```
ACTION: full_scan      — proceed to Stage 2
ACTION: apply_pending  — skip to Stage 3 (use pending-skills.json as manifest delta)
ACTION: use_cached     — skip to Stage 5 (just display current manifest)
```

## Fast Path

If `use_cached`: read current manifest load list and jump to Stage 5 directly.
If `apply_pending`: merge pending into current manifest, jump to Stage 4.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall