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/04-check.md

View on GitHub
# Stage 4: Check — Validate Before Loading

Binary YES/NO gates. Any NO = stop and report before proceeding.

## Gates

- [ ] **G1** Load list has ≥ 1 skill?
- [ ] **G2** Load list has ≤ 15 skills?
- [ ] **G3** No skill appears in both load AND unload?
- [ ] **G4** All loaded skills have a valid path that exists on disk?
- [ ] **G5** No two conflicting skills in load list? (e.g., flask + fastapi, jest + vitest)
- [ ] **G6** Manifest `generated_at` is within the last 24 hours?

## Failure Handling

| Gate | Failure action |
|------|---------------|
| G1 | Load only meta-skills (skill-router), warn user |
| G2 | Trim to top 15 by priority, warn about excluded skills |
| G3 | Remove the skill from unload (keep loaded version) |
| G4 | Remove missing-path skills from load, add to suggestions |
| G5 | Keep highest-priority conflicting skill, warn about the other |
| G6 | Warn that manifest may be stale, offer to re-scan |

## Pass Condition

All gates YES (or failures handled per table above).
Proceed to Stage 5 only after resolving all failures.
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