Skip to content

stevesolun/ctx / docs

skill-router

Flagged

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

FileKindSize
SKILL.mdskill md9.3 KB
assets/javascripts/catalog.jsscript2.5 KB
assets/javascripts/repo-stats-refresh.jsscript3.2 KB
backup-hook-install.mdmarkdown9.2 KB
catalog.mdmarkdown10.3 KB
ctx-fit/ARCHITECTURE_CANDIDATES.mdmarkdown12.9 KB
ctx-fit/ARCHITECTURE_GAP_ANALYSIS.mdmarkdown10.7 KB
ctx-fit/CTX_AUDIT.mdmarkdown11.6 KB
ctx-fit/CURRENT_STATE.mdmarkdown16.3 KB
ctx-fit/DECISIONS.mdmarkdown15.7 KB
ctx-fit/GOOD_FIRST_ISSUES.mdmarkdown20.6 KB
ctx-fit/IMPLEMENTATION_TRACKER.mdmarkdown697 B
ctx-fit/MAP.mdmarkdown7.8 KB
ctx-fit/PRD.mdmarkdown9.7 KB
ctx-fit/STATE.mdmarkdown60.9 KB
ctx-fit/milestones/M1_SPIKE_FRICTION_LOG.mdmarkdown5.5 KB
ctx-fit/milestones/MILESTONE_00_AUDIT.mdmarkdown5.1 KB
ctx-fit/planned_tasks.mdmarkdown17.7 KB
dashboard.mdmarkdown24.7 KB
enterprise-readiness-review.mdmarkdown8.7 KB
entity-onboarding.mdmarkdown18.0 KB
harness/attaching-to-hosts.mdmarkdown16.2 KB
harness/clean-host-contract.mdmarkdown4.5 KB
harness/loopflow-adapter-demo.mdmarkdown11.1 KB
huggingface-publish.mdmarkdown3.3 KB
index.mdmarkdown22.4 KB
knowledge-graph.mdmarkdown22.7 KB
marketplace-registry.mdmarkdown4.0 KB
memory-anchor.mdmarkdown2.7 KB
plans/ctx-agent-reviewer-workbench.mdmarkdown12.4 KB
plans/unified-capability-engine.mdmarkdown59.0 KB
qa/dashboard-user-story-status.csvother26.0 KB
qa/feature-user-story-status.csvother92.5 KB
research/context-engineering-guidance-audit.mdmarkdown10.4 KB
services/macos/com.claude.backup.watchdog.plistother1.7 KB
services/systemd/claude-backup-watchdog.serviceother1.3 KB
skill-lifecycle-and-dashboard.mdmarkdown6.2 KB
skill-quality-install.mdmarkdown6.2 KB
skill-router/index.mdmarkdown2.5 KB
skill-stack-matrix.mdmarkdown5.5 KB
skills-health.mdmarkdown3.5 KB
stack-signatures.mdmarkdown6.2 KB
telemetry.mdmarkdown24.7 KB
threat-model.mdmarkdown15.0 KB
toolbox/behavior-miner.mdmarkdown2.6 KB
toolbox/configuration.mdmarkdown4.0 KB
toolbox/council-runner.mdmarkdown2.4 KB
toolbox/hooks.mdmarkdown2.6 KB
toolbox/index.mdmarkdown3.0 KB
toolbox/intent-interview.mdmarkdown3.0 KB
toolbox/starters.mdmarkdown3.0 KB
toolbox/templates/docs-review.jsonconfig599 B
toolbox/templates/fresh-repo-init.jsonconfig533 B
toolbox/templates/refactor-safety.jsonconfig634 B
toolbox/templates/security-sweep.jsonconfig636 B
toolbox/templates/ship-it.jsonconfig676 B
toolbox/verdicts.mdmarkdown4.0 KB

skill-stack-matrix.md

View on GitHub
# Skill-Stack Matrix

> Maps stack identifiers to the skills that serve them.
> Used as resolver evidence; final ranking still goes through the shared
> recommendation engine and graph/wiki scores.

## Table of Contents
1. [Matrix Format](#matrix-format)
2. [The Matrix](#the-matrix)
3. [Companion Rules](#companion-rules)
4. [Conflict Rules](#conflict-rules)

---

## Matrix Format

Each entry:
- **Stack IDs**: which detected stacks trigger this skill
- **Skill**: skill/entity slug in the graph/wiki catalog
- **Priority Base**: starting priority before signal boosts
- **Required**: must-load if stack detected, vs nice-to-have
- **Companions**: skills that should co-load
- **Conflicts**: skills that should not co-load

## The Matrix

### Document Creation Skills

| Skill | Stack IDs | Priority | Required | Path Pattern |
|-------|-----------|----------|----------|--------------|
| docx | (any -- triggered by user request) | 2 | no | graph/wiki or local skill path |
| pdf | (any -- triggered by user request) | 2 | no | graph/wiki or local skill path |
| pptx | (any -- triggered by user request) | 2 | no | graph/wiki or local skill path |
| xlsx | (any -- triggered by user request) | 2 | no | graph/wiki or local skill path |

> Note: document skills are demand-loaded, not stack-loaded. They activate on user
> request ("make a presentation") not on repo content. The router keeps them in a
> "standby" pool -- not loaded into context, but available for instant load.

### Frontend Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| frontend-design | react, vue, angular, svelte, nextjs, nuxt, html, css | 8 | yes |
| react | react, nextjs | 7 | yes |
| vue | vue, nuxt | 7 | yes |
| angular | angular | 7 | yes |
| svelte | svelte | 7 | yes |
| tailwind | tailwindcss | 5 | no |
| css-modules | css-modules | 4 | no |

### Backend Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| fastapi | fastapi | 8 | yes |
| django | django | 8 | yes |
| flask | flask | 7 | yes |
| express | express | 8 | yes |
| nestjs | nestjs | 8 | yes |
| rails | rails | 8 | yes |
| gin | gin | 7 | yes |
| actix | actix | 7 | yes |

### Data Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| sqlalchemy | sqlalchemy, alembic | 6 | yes |
| prisma | prisma | 6 | yes |
| typeorm | typeorm | 6 | yes |
| drizzle | drizzle | 6 | yes |
| redis | redis | 4 | no |
| kafka | kafka | 5 | no |
| dbt | dbt | 6 | yes |

### Infrastructure Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| docker | docker, docker-compose | 6 | yes |
| kubernetes | kubernetes, helm, kustomize | 6 | yes |
| terraform | terraform | 7 | yes |
| github-actions | github-actions | 5 | yes |
| gitlab-ci | gitlab-ci | 5 | yes |
| aws | aws-cdk, aws-sam | 7 | yes |
| vercel | vercel | 4 | no |

### AI/Agent Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| langchain | langchain | 7 | yes |
| llamaindex | llamaindex | 7 | yes |
| mcp-dev | mcp | 7 | yes |
| pytorch | pytorch | 6 | yes |
| huggingface | huggingface | 6 | yes |
| openai-sdk | openai-sdk | 5 | no |
| anthropic-sdk | anthropic-sdk | 5 | no |

### Quality Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| pytest | pytest | 5 | yes |
| jest | jest, vitest | 5 | yes |
| cypress | cypress | 4 | no |
| playwright | playwright | 4 | no |
| eslint | eslint | 3 | no |
| ruff | ruff | 3 | no |

### Documentation Skills

| Skill | Stack IDs | Priority | Required |
|-------|-----------|----------|----------|
| openapi | openapi | 5 | yes |
| graphql | graphql | 5 | yes |
| mkdocs | mkdocs | 4 | no |
| docusaurus | docusaurus | 4 | no |

### Meta Skills (always available, never unloaded)

| Skill | Stack IDs | Priority | Required | Notes |
|-------|-----------|----------|----------|-------|
| skill-router | * | 99 | yes | This skill -- always loaded |
| file-reading | * | 50 | yes | Core capability |
| skill-creator | * | 10 | no | Standby pool |
| product-self-knowledge | * | 10 | no | Standby pool |

---

## Companion Rules

When skill A is loaded, also load skill B if its stack is detected:

| Primary Skill | Companion | Condition |
|---------------|-----------|-----------|
| fastapi | sqlalchemy | DB migrations detected |
| fastapi | openapi | OpenAPI spec file exists |
| django | django-orm | (always with django) |
| react | tailwind | tailwind.config.* exists |
| docker | docker-compose | docker-compose.yml exists |
| kubernetes | helm | Chart.yaml exists |
| terraform | aws | provider "aws" in *.tf |
| langchain | openai-sdk | openai in deps |
| pytest | coverage | .coveragerc or coverage config exists |

## Conflict Rules

These skills should not be co-loaded (pick the one with higher confidence/priority):

| Skill A | Skill B | Resolution |
|---------|---------|------------|
| flask | fastapi | Higher confidence wins |
| flask | django | Higher confidence wins |
| jest | vitest | Higher confidence wins |
| webpack | vite | Higher confidence wins |
| npm | yarn | Check lock file |
| npm | pnpm | Check lock file |
| yarn | pnpm | Check lock file |
| react | vue | Both can coexist in monorepo |
| sqlalchemy | prisma | Both can coexist if different services |

> Conflict resolution: check if the repo is a monorepo. In monorepos, "conflicting"
> skills may serve different packages and should both load. In single-package repos,
> pick the one with higher confidence.
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: 471kUpdated 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