curiositech/windags-skills

190+ agent skills for Claude Code, Codex, Gemini CLI, Cursor, and 40+ other agents. Apache-2.0.

10

stars

62

commits

Python

primary language

Jul 18, 2026

updated

README

/next-move prediction in Claude Code

/next-move execution results

windags-skills

463+ agent skills for Claude Code, Codex, Gemini CLI, Cursor, and 40+ other coding agents.
Built by WinDAGs — DAG orchestration for multi-agent workflows.

next-move · skill search · all skills · install · windags.ai


/next-move

The flagship skill. Tell it what you're working on (or don't — it reads your git state), and it produces a predicted DAG of the highest-impact agents to run next.

/next-move                           # auto-detect from git + conversation
/next-move fix the flaky auth tests  # tell it what you care about
/next-move prediction output

What you get:

  • Problem classification — well-structured, ill-structured, or wicked
  • 3-8 subtasks decomposed into parallel waves
  • Each subtask matched to the best skill from 463+ via BM25 retrieval
  • Risk analysis with mitigations (PreMortem agent)
  • Time and cost estimates per node
  • Accept / Modify / Reject feedback loop

How it works: A 5-agent meta-DAG runs inside your Claude Code session:

Wave 0: Sensemaker    — classify the problem, halt gate if uncertain
Wave 1: Decomposer    — break into subtasks with dependencies
Wave 2: Skill Selector — BM25 search → match skills to subtasks  (parallel)
Wave 2: PreMortem      — scan for failure patterns                (parallel)
Wave 3: Synthesizer    — assemble the predicted DAG + present to user

No extra API keys. No external services. Runs entirely in your Claude session.


BM25 ranked retrieval across the full catalog. Porter stemming, real stopword removal, document-length normalization. Zero API keys — runs locally.

BM25 skill search

Queries like "drone computer vision" find computer-vision-pipeline and drone-cv-expert. "Wedding photo 3d gaussian" finds wedding-immortalist at 35.9. Stemming handles morphological variants — "deploy" matches "deployment" and "deployed".


DAG Execution

Skills don't just get recommended — they get executed in parallel waves. The WinDAGs engine spawns real agents (claude -p) with skill-injected prompts, running independent nodes concurrently.

DAG execution

Install

Claude Code (plugin):

claude plugin add /path/to/windags-skills

Manual (any agent):

git clone https://github.com/curiositech/windags-skills.git

# Use /next-move:
cp -r windags-skills/skills/next-move ~/.claude/commands/

# Or symlink the whole catalog:
ln -s $(pwd)/windags-skills/skills ~/.claude/skills

Single skill:

cp -r windags-skills/skills/api-architect ~/.claude/commands/

All Skills (463)

CategoryCountHighlights
Agent & Orchestration78dag-orchestrator, next-move, skill-architect, task-decomposer
Research & Academic61raft-consensus, bdi-agents, chain-of-thought, tree-of-thoughts
Design & Creative46design-system-creator, pixel-art, typography, vibe-matcher
Backend & Infrastructure35api-architect, microservices, caching, websocket
Cognitive Science29naturalistic-decision-making, sensemaking, expertise-elicitation
AI & Machine Learning27ai-engineer, RAG, computer-vision, embeddings
DevOps & Infrastructure26github-actions, kubernetes, terraform, docker
Frontend & UI24nextjs, react-performance, animation, framer-motion
Data & Analytics17data-pipeline, dbt, data-viz, dimensional-modeling
Mobile Development17ios, react-native, flutter, swiftui
Code Quality & Testing16vitest, playwright, code-review, refactoring
Productivity & Meta16prompt-engineer, documentation, skill-creator
Recovery & Wellness16sobriety, crisis-intervention, speech-pathology
Lifestyle & Personal14ADHD, grief, finance, interior-design
Content & Marketing14SEO, copywriting, product-launches
Career & Interview9interview-prep, resume, hiring-manager
Legal & Compliance7expungement, HIPAA, legal-tech
Video & Audio6video-production, TTS, sound-design
Security5auth, vulnerability-scanning, zero-trust

How Skills Work

Each skill is a markdown file (SKILL.md) with YAML frontmatter:

---
name: api-architect
description: "Expert API designer for REST, GraphQL, gRPC architectures"
category: Backend & Infrastructure
tags: [api, rest, graphql, grpc]
---

The body contains activation triggers, core capabilities, anti-patterns, and reference files. When an agent loads a skill, it gains bespoke expertise — not just instructions, but deep domain knowledge with working examples.

Skills follow the Agent Skills open standard and work with Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor, VS Code Copilot, and 30+ other agents.


Install

Claude Code (one command)

claude plugin marketplace add curiositech/windags-skills
claude plugin install windags-skills

This installs all 463+ skills + the 5 /next-move subagents (sensemaker, decomposer, skill-selector, premortem, synthesizer).

Cross-tool install (Codex, Gemini CLI, Cursor, Aider, …)

Clone the plugin and run the installer. It detects which tools you have under $HOME and links skills + subagents into the right place. No hardcoded paths — uses $HOME and the plugin checkout dir.

git clone https://github.com/curiositech/windags-skills.git ~/coding/windags-skills
~/coding/windags-skills/scripts/install.sh

What it does (idempotent — safe to re-run after git pull):

ToolWhat gets installed
Claude Code~/.claude/skills/{next-move, windags-*} + ~/.claude/agents/{5 subagents}.md
Codex~/.codex/skills/{next-move, windags-*} + ~/.codex/AGENTS.md
Cursor / Cline / Aider~/AGENTS.md (auto-discovered by AGENTS.md-aware tools)
Gemini CLIMarked block appended to ~/.gemini/GEMINI.md

Override the install location with WINDAGS_HOME=/path ./install.sh. Preview without changes with --dry-run.

The MCP server lives at <plugin>/mcp-server/index.js — wire it into any MCP-aware client. It exposes 10 tools and 1 prompt:

ToolPurpose
windags_skill_searchCascade-ranked skill search (BM25 + MiniLM + RRF + cross-encoder + per-user attribution k-NN)
windags_skill_graftFull SKILL.md bodies for top primaries + adjacencies + asset manifest
windags_skill_referenceLoad one reference file from a skill's references/
windags_historyRecent /next-move predictions for a project
windags_skill_search_batchN searches in one round-trip (capped at 20)
windags_skill_graft_batchN grafts in one round-trip (capped at 20)
windags_node_requirementsPer-skill allowed-tools, pairs-with, suggested model_tier, and provider-native model IDs
windags_validate_dagSchema-check a candidate DAG before saving
windags_estimate_costPer-node + total cost estimate during planning
windags_run_pipelineRun the full 5-stage /next-move pipeline server-side. Provider-agnostic — auto-detects from env (Anthropic / OpenAI / Google / Groq / OpenRouter / Together / DeepSeek / Fireworks / Cerebras / xAI). Pin one with WINDAGS_PROVIDER=<id>. ~$0.02–$0.15 per run. Returns a halt response or a validated PredictedDAG.
PromptPurpose
next_moveTemplated /next-move runner. Drives the 5-stage pipeline (sensemaker → decomposer → skill-selector + premortem → synthesizer) for non-Claude clients that don't have Claude Code's slash commands. Args: task (focus hint), fresh ("true" to ignore conversation history).

License

BUSL-1.1 (Business Source License). Free for non-commercial and personal use. Converts to Apache 2.0 on 2030-03-03.

Commercial licensing: licensing@curiositech.ai


Built by Curiositech · windags.ai

Contributors

erichowens

62 commits

curiositech/windags-skills

190+ agent skills for Claude Code, Codex, Gemini CLI, Cursor, and 40+ other agents. Apache-2.0.

10

stars

62

commits

Python

primary language

Jul 18, 2026

updated

README

/next-move prediction in Claude Code

/next-move execution results

windags-skills

463+ agent skills for Claude Code, Codex, Gemini CLI, Cursor, and 40+ other coding agents.
Built by WinDAGs — DAG orchestration for multi-agent workflows.

next-move · skill search · all skills · install · windags.ai


/next-move

The flagship skill. Tell it what you're working on (or don't — it reads your git state), and it produces a predicted DAG of the highest-impact agents to run next.

/next-move                           # auto-detect from git + conversation
/next-move fix the flaky auth tests  # tell it what you care about
/next-move prediction output

What you get:

  • Problem classification — well-structured, ill-structured, or wicked
  • 3-8 subtasks decomposed into parallel waves
  • Each subtask matched to the best skill from 463+ via BM25 retrieval
  • Risk analysis with mitigations (PreMortem agent)
  • Time and cost estimates per node
  • Accept / Modify / Reject feedback loop

How it works: A 5-agent meta-DAG runs inside your Claude Code session:

Wave 0: Sensemaker    — classify the problem, halt gate if uncertain
Wave 1: Decomposer    — break into subtasks with dependencies
Wave 2: Skill Selector — BM25 search → match skills to subtasks  (parallel)
Wave 2: PreMortem      — scan for failure patterns                (parallel)
Wave 3: Synthesizer    — assemble the predicted DAG + present to user

No extra API keys. No external services. Runs entirely in your Claude session.


BM25 ranked retrieval across the full catalog. Porter stemming, real stopword removal, document-length normalization. Zero API keys — runs locally.

BM25 skill search

Queries like "drone computer vision" find computer-vision-pipeline and drone-cv-expert. "Wedding photo 3d gaussian" finds wedding-immortalist at 35.9. Stemming handles morphological variants — "deploy" matches "deployment" and "deployed".


DAG Execution

Skills don't just get recommended — they get executed in parallel waves. The WinDAGs engine spawns real agents (claude -p) with skill-injected prompts, running independent nodes concurrently.

DAG execution

Install

Claude Code (plugin):

claude plugin add /path/to/windags-skills

Manual (any agent):

git clone https://github.com/curiositech/windags-skills.git

# Use /next-move:
cp -r windags-skills/skills/next-move ~/.claude/commands/

# Or symlink the whole catalog:
ln -s $(pwd)/windags-skills/skills ~/.claude/skills

Single skill:

cp -r windags-skills/skills/api-architect ~/.claude/commands/

All Skills (463)

CategoryCountHighlights
Agent & Orchestration78dag-orchestrator, next-move, skill-architect, task-decomposer
Research & Academic61raft-consensus, bdi-agents, chain-of-thought, tree-of-thoughts
Design & Creative46design-system-creator, pixel-art, typography, vibe-matcher
Backend & Infrastructure35api-architect, microservices, caching, websocket
Cognitive Science29naturalistic-decision-making, sensemaking, expertise-elicitation
AI & Machine Learning27ai-engineer, RAG, computer-vision, embeddings
DevOps & Infrastructure26github-actions, kubernetes, terraform, docker
Frontend & UI24nextjs, react-performance, animation, framer-motion
Data & Analytics17data-pipeline, dbt, data-viz, dimensional-modeling
Mobile Development17ios, react-native, flutter, swiftui
Code Quality & Testing16vitest, playwright, code-review, refactoring
Productivity & Meta16prompt-engineer, documentation, skill-creator
Recovery & Wellness16sobriety, crisis-intervention, speech-pathology
Lifestyle & Personal14ADHD, grief, finance, interior-design
Content & Marketing14SEO, copywriting, product-launches
Career & Interview9interview-prep, resume, hiring-manager
Legal & Compliance7expungement, HIPAA, legal-tech
Video & Audio6video-production, TTS, sound-design
Security5auth, vulnerability-scanning, zero-trust

How Skills Work

Each skill is a markdown file (SKILL.md) with YAML frontmatter:

---
name: api-architect
description: "Expert API designer for REST, GraphQL, gRPC architectures"
category: Backend & Infrastructure
tags: [api, rest, graphql, grpc]
---

The body contains activation triggers, core capabilities, anti-patterns, and reference files. When an agent loads a skill, it gains bespoke expertise — not just instructions, but deep domain knowledge with working examples.

Skills follow the Agent Skills open standard and work with Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor, VS Code Copilot, and 30+ other agents.


Install

Claude Code (one command)

claude plugin marketplace add curiositech/windags-skills
claude plugin install windags-skills

This installs all 463+ skills + the 5 /next-move subagents (sensemaker, decomposer, skill-selector, premortem, synthesizer).

Cross-tool install (Codex, Gemini CLI, Cursor, Aider, …)

Clone the plugin and run the installer. It detects which tools you have under $HOME and links skills + subagents into the right place. No hardcoded paths — uses $HOME and the plugin checkout dir.

git clone https://github.com/curiositech/windags-skills.git ~/coding/windags-skills
~/coding/windags-skills/scripts/install.sh

What it does (idempotent — safe to re-run after git pull):

ToolWhat gets installed
Claude Code~/.claude/skills/{next-move, windags-*} + ~/.claude/agents/{5 subagents}.md
Codex~/.codex/skills/{next-move, windags-*} + ~/.codex/AGENTS.md
Cursor / Cline / Aider~/AGENTS.md (auto-discovered by AGENTS.md-aware tools)
Gemini CLIMarked block appended to ~/.gemini/GEMINI.md

Override the install location with WINDAGS_HOME=/path ./install.sh. Preview without changes with --dry-run.

The MCP server lives at <plugin>/mcp-server/index.js — wire it into any MCP-aware client. It exposes 10 tools and 1 prompt:

ToolPurpose
windags_skill_searchCascade-ranked skill search (BM25 + MiniLM + RRF + cross-encoder + per-user attribution k-NN)
windags_skill_graftFull SKILL.md bodies for top primaries + adjacencies + asset manifest
windags_skill_referenceLoad one reference file from a skill's references/
windags_historyRecent /next-move predictions for a project
windags_skill_search_batchN searches in one round-trip (capped at 20)
windags_skill_graft_batchN grafts in one round-trip (capped at 20)
windags_node_requirementsPer-skill allowed-tools, pairs-with, suggested model_tier, and provider-native model IDs
windags_validate_dagSchema-check a candidate DAG before saving
windags_estimate_costPer-node + total cost estimate during planning
windags_run_pipelineRun the full 5-stage /next-move pipeline server-side. Provider-agnostic — auto-detects from env (Anthropic / OpenAI / Google / Groq / OpenRouter / Together / DeepSeek / Fireworks / Cerebras / xAI). Pin one with WINDAGS_PROVIDER=<id>. ~$0.02–$0.15 per run. Returns a halt response or a validated PredictedDAG.
PromptPurpose
next_moveTemplated /next-move runner. Drives the 5-stage pipeline (sensemaker → decomposer → skill-selector + premortem → synthesizer) for non-Claude clients that don't have Claude Code's slash commands. Args: task (focus hint), fresh ("true" to ignore conversation history).

License

BUSL-1.1 (Business Source License). Free for non-commercial and personal use. Converts to Apache 2.0 on 2030-03-03.

Commercial licensing: licensing@curiositech.ai


Built by Curiositech · windags.ai

Contributors

erichowens

62 commits

Languages

Python

45.6%

JavaScript

24.4%

TypeScript

14.4%

Shell

8.6%

HTML

6.0%