| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 0 | 1 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − CareerSwarm
- + OpenClaw parallel assistant
Commands
neither file has anySection tags
0 shared · 0 only in A · 1 only in B- + agent-behaviour
Line diff
zganich/careerswarm-honeycomb · .cursorrules
@@ −1 @@
1# CareerSwarm
2
3AI-powered career evidence platform: Master Profile, achievements (STAR), 7-stage agent pipeline (Scout → Qualifier → Profiler → Tailor → Scribe → Assembler → Success Predictor), Resume Roast, application tracker.
4
5**Full rules:** See `.cursor/rules/` for core, architecture, agent-prompts, flywheel, pivot, roast.
6
7**Reference:** [CONTEXT_FOR_NEW_CHAT.md](CONTEXT_FOR_NEW_CHAT.md) for handoff and detailed context.
8
zganich/careerswarm-honeycomb · .cursor/rules/openclaw.mdc
@@ +1 @@
1---
2description: When OpenClaw is used in parallel; sync points and when to use which agent.
3globs: CONTEXT_FOR_NEW_CHAT.md, todo.md, docs/OPENCLAW_INTEGRATION.md, server/agents/gtm/**/*
4---
5
6# OpenClaw parallel assistant
7
8When the user runs OpenClaw alongside Cursor (see [docs/OPENCLAW_INTEGRATION.md](docs/OPENCLAW_INTEGRATION.md)):
9
10- **CONTEXT_FOR_NEW_CHAT.md** and **todo.md** are the shared sync points. OpenClaw reads them to avoid duplicating work and to know current state.
11- On session wrap-up or at 50–60% context: update CONTEXT and todo so OpenClaw (and future Cursor chats) see the latest "what was done" and "what's next."
12- **You (Cursor) have a Business agent.** When the task involves **GTM, strategy, positioning, pricing, or the in-app business/GTM agents** (`server/agents/gtm/`, strategy, content, pipeline), recommend that the user use the OpenClaw **Business** agent for suggestions and "why," or hand off a brief so they can ask Business. See [docs/BUSINESS_AGENT_IMPROVEMENTS.md](docs/BUSINESS_AGENT_IMPROVEMENTS.md). Do not assume you are the only agent; the Business agent exists for this lane.
13- No need to mention OpenClaw in every response; just keep CONTEXT and todo accurate and recommend the right agent (e.g. Business for GTM/strategy work) when relevant.
14
@@ −1 +1 @@
1−# CareerSwarm
1+---
2+description: When OpenClaw is used in parallel; sync points and when to use which agent.
3+globs: CONTEXT_FOR_NEW_CHAT.md, todo.md, docs/OPENCLAW_INTEGRATION.md, server/agents/gtm/**/*
4+---
25
3−AI-powered career evidence platform: Master Profile, achievements (STAR), 7-stage agent pipeline (Scout → Qualifier → Profiler → Tailor → Scribe → Assembler → Success Predictor), Resume Roast, application tracker.
6+# OpenClaw parallel assistant
47
5−**Full rules:** See `.cursor/rules/` for core, architecture, agent-prompts, flywheel, pivot, roast.
8+When the user runs OpenClaw alongside Cursor (see [docs/OPENCLAW_INTEGRATION.md](docs/OPENCLAW_INTEGRATION.md)):
69
7−**Reference:** [CONTEXT_FOR_NEW_CHAT.md](CONTEXT_FOR_NEW_CHAT.md) for handoff and detailed context.
10+- **CONTEXT_FOR_NEW_CHAT.md** and **todo.md** are the shared sync points. OpenClaw reads them to avoid duplicating work and to know current state.
11+- On session wrap-up or at 50–60% context: update CONTEXT and todo so OpenClaw (and future Cursor chats) see the latest "what was done" and "what's next."
12+- **You (Cursor) have a Business agent.** When the task involves **GTM, strategy, positioning, pricing, or the in-app business/GTM agents** (`server/agents/gtm/`, strategy, content, pipeline), recommend that the user use the OpenClaw **Business** agent for suggestions and "why," or hand off a brief so they can ask Business. See [docs/BUSINESS_AGENT_IMPROVEMENTS.md](docs/BUSINESS_AGENT_IMPROVEMENTS.md). Do not assume you are the only agent; the Business agent exists for this lane.
13+- No need to mention OpenClaw in every response; just keep CONTEXT and todo accurate and recommend the right agent (e.g. Business for GTM/strategy work) when relevant.
814
