R
Reactive-Skills/reactive-skills
HSM runtime for deterministic AI workflows
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Client config (built from the install command this repo gives)
{
"mcpServers": {
"reactive-skills-reactive-skills": {
"command": "npx",
"args": ["-y", "@reactive-skills/axi"]
}
}
}Parsed from the README we fetched on 2026-11-11; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"reactive-skills-reactive-skills": {
"command": "npx",
"args": ["-y", "@reactive-skills/axi"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio reactive-skills-reactive-skills -- npx -y @reactive-skills/axi
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 1 ★ · Reactive-Skills/reactive-skills · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-12 · last seen 2026-11-14 · seen 3× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
- Install
npx -y @reactive-skills/axi
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx -y @reactive-skills/axi. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
Reactive-Skills/reactive-skills；first catalogued 2026-11-12；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# ⚡ Reactive Skills Architecture (RSA)
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
> Event-Driven Hierarchical State Machine Engine and Immutable Event Store for Agentic Skills
> 🚀 What's New in v0.21.0:
> - Breaking 0.x minor release: MCP emit and human response return a continuation envelope with a delta-v1 view by default, and reactive_state returns the complete compact-v1 view.
> - Delta views send the instructions plus only the context the ledger committed since the last delivered view; the complete recovery view is sent on resume.
> - Large declared text evidence passes by evidence reference automatically, and MCP tool descriptions are shorter.
> - return_view: "none" and output: "legacy" keep the previous outputs for one release.
> Breaking Changes and Migration Notes → · View Changelog
## 🌟 What is Reactive Skills?
Conventional agent skills are static markdown instruction files (SKILL.md). An LLM reads all instructions upfront, enters an unstructured execution loop, and guesses its next steps without state verification or deterministic progress guarantees.
Reactive Skills upgrade passive agent skills into Hierarchical State Machines (HSM) driven by a reactive Event/Signal Bus:
1. Just-In-Time Prompt Slices: Reactive workflows expose the active state's prompt, constraints, and allowed tools as the workflow advances.
Instructions for unvisited branches can remain unread; previously delivered content remains in the host transcript.
2. Signal-Driven Ingress: Transitions are triggered by typed runtime signals (REQUIREMENTS_GATHERED, TESTS_PASSED, USER_APPROVED).
3. Deterministic Guard Gates: Progress requires deterministic programmatic invariants to evaluate true (preventing hallucinated completion).
4. Event Sourcing & Live Deliverables: Every transition is recorded to an append-only ledger (events.jsonl + SQLite events.db). Documentation, PR bodies, and review matrices are live read-model projections rendered from the event stream.
## 📦 Packages
This repository is a monorepo containing:
@reactive-skills/runtime: The core TypeScript statechart engine, SQLite event store driver, guard evaluator, and stdio MCP server.
@reactive-skills/axi: The Agent eXperience Interface (AXI) CLI (reactive-skills-axi) providing human- and agent-ergonomic state inspection and signal dispatch in TOON format.
## 🚀 Quickstart
### 1. Execution Options
You can execute commands on-demand via npx (zero installation required) or install the CLI globally:
bash
# Zero install — works immediately for any agent or shell:
npx -y @reactive-skills/axi state
npx -y @reactive-skills/axi emit
npx -y @reactive-skills/axi capabilities --json
npx -y @reactive-skills/axi preflight --json
# Optional: Install globally for instant local commands (reactive-skills-axi or axi):
npm install -g @reactive-skills/axi
### 2. Inspect a Skill's Current State
bash
npx -y @reactive-skills/axi state --output compact-v1
Outputs the current state, its instructions and recorded context, allowed tools, and applicable signal requirements.
Negotiate state.compact_v1 through capabilities before selecting --output compact-v1; omitting the flag or using --output legacy preserves the existing terminal format shown below:
yaml
state:
skill_id: my-skill
> 🚀 What's New in v0.21.0:
> - Breaking 0.x minor release: MCP emit and human response return a continuation envelope with a delta-v1 view by default, and reactive_state returns the complete compact-v1 view.
> - Delta views send the instructions plus only the context the ledger committed since the last delivered view; the complete recovery view is sent on resume.
> - Large declared text evidence passes by evidence reference automatically, and MCP tool descriptions are shorter.
> - return_view: "none" and output: "legacy" keep the previous outputs for one release.
> Breaking Changes and Migration Notes → · View Changelog
## 🌟 What is Reactive Skills?
Conventional agent skills are static markdown instruction files (SKILL.md). An LLM reads all instructions upfront, enters an unstructured execution loop, and guesses its next steps without state verification or deterministic progress guarantees.
Reactive Skills upgrade passive agent skills into Hierarchical State Machines (HSM) driven by a reactive Event/Signal Bus:
1. Just-In-Time Prompt Slices: Reactive workflows expose the active state's prompt, constraints, and allowed tools as the workflow advances.
Instructions for unvisited branches can remain unread; previously delivered content remains in the host transcript.
2. Signal-Driven Ingress: Transitions are triggered by typed runtime signals (REQUIREMENTS_GATHERED, TESTS_PASSED, USER_APPROVED).
3. Deterministic Guard Gates: Progress requires deterministic programmatic invariants to evaluate true (preventing hallucinated completion).
4. Event Sourcing & Live Deliverables: Every transition is recorded to an append-only ledger (events.jsonl + SQLite events.db). Documentation, PR bodies, and review matrices are live read-model projections rendered from the event stream.
## 📦 Packages
This repository is a monorepo containing:
@reactive-skills/runtime: The core TypeScript statechart engine, SQLite event store driver, guard evaluator, and stdio MCP server.
@reactive-skills/axi: The Agent eXperience Interface (AXI) CLI (reactive-skills-axi) providing human- and agent-ergonomic state inspection and signal dispatch in TOON format.
## 🚀 Quickstart
### 1. Execution Options
You can execute commands on-demand via npx (zero installation required) or install the CLI globally:
bash
# Zero install — works immediately for any agent or shell:
npx -y @reactive-skills/axi state
npx -y @reactive-skills/axi emit
npx -y @reactive-skills/axi capabilities --json
npx -y @reactive-skills/axi preflight --json
# Optional: Install globally for instant local commands (reactive-skills-axi or axi):
npm install -g @reactive-skills/axi
### 2. Inspect a Skill's Current State
bash
npx -y @reactive-skills/axi state --output compact-v1
Outputs the current state, its instructions and recorded context, allowed tools, and applicable signal requirements.
Negotiate state.compact_v1 through capabilities before selecting --output compact-v1; omitting the flag or using --output legacy preserves the existing terminal format shown below:
yaml
state:
skill_id: my-skill
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/reactive-skills-reactive-skills/)
- Source
- github · https://github.com/Reactive-Skills/reactive-skills
- Browse by field
- Open source
- Traction
- 1 ★
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.