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/02-plan.md

View on GitHub
# Stage 2: Plan — Run the Scanner

Only reached if Stage 1 determined `full_scan`.

## Steps

1. **Identify current repo root**
   - Use current working directory from the session
   - Confirm it looks like a project (has package.json, pyproject.toml, Cargo.toml, go.mod, etc.)
   - If it's the home dir or system dir → warn and use limited scan

2. **Run the scanner**

```bash
python3 ~/.claude/ctx/scan_repo.py \
  --repo <cwd> \
  --output /tmp/skill-stack-profile.json
```

(Replace `~/.claude/ctx` with the actual ctx_dir from `~/.claude/skill-registry.json`)

3. **Read the output** (`/tmp/skill-stack-profile.json`)
   - Report top 5 detected stacks with confidence scores
   - Note any monorepo packages detected

## Expected Duration

< 10 seconds for repos up to 10K files. If it takes longer, something is wrong.

## On Failure

If scanner exits non-zero or output file is missing:
- Fallback: use `use_cached` action if manifest exists
- Otherwise: proceed to Stage 3 with an empty profile (will load only meta-skills)
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