Address findings from pedagogical review simulating a non-expert user:
- Add CLAUDE.md to project root (was referenced but missing)
- Fix README score from 12/9/1 to 13/8/1 (match feature-map.md)
- Add Expected Output sections to examples 01, 02, 05, 09, 10
- Create pipeline-output/ and briefings/ directories
- Add example ordering guidance in README
- Add plan requirements for examples 11/13 in prerequisites
- Add skill frontmatter explanation in GETTING-STARTED.md
- Explain Cowork/Dispatch with links in cowork-integration
- Expand .gitignore with node_modules and generated output files
- Add model override hints in agent frontmatter comments
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Actual table verdicts: 13 full match (59%), 8 different (36%), 1 gap (5%).
Summary table was wrong since initial commit.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Practical 6-step guide that takes users from "clone and explore"
to "personal AI assistant I text from my phone":
1. Personalize CLAUDE.md (30 min)
2. Set up phone channel - iMessage/Telegram/Discord (10 min)
3. Keep session alive with tmux (5 min)
4. Write first personal skills with 3 real examples (15 min)
5. Connect external tools via MCP (15 min per tool)
6. Let it learn over time (ongoing)
Includes: "what your day looks like after setup" scenarios,
honest expectations, and quick reference table.
README updated with two-path entry: demo mode vs daily driver.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- messaging/channels-setup.md: comprehensive guide covering all 3
channels (Telegram, Discord, iMessage), bun install, plugin setup,
session persistence workarounds, and enterprise admin settings
- messaging/imessage-setup.md: macOS-specific iMessage setup with
Full Disk Access, /imessage access allow, and known quirks
- messaging/README.md: rewritten with 3-way distinction table
(Channels=event-based, Dispatch=message-based, RC=direct control)
- examples/12: expanded from 2 options to 3 with clear trigger model
- feature-map.md: row 9 updated to include iMessage
- README.md: session persistence warning added as top-level section
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Major update based on Anthropic's March 24, 2026 releases:
- feature-map.md: expanded from 20 to 22 capabilities, gaps reduced
from 2 to 1 (only Canvas/A2UI remains)
- examples/11-computer-use: desktop control via screenshots and clicks
- examples/12-remote-control: /rc and Dispatch for phone control
- examples/13-auto-mode: AI safety classifier for autonomous execution
- cowork-integration/: how Code + Cowork + Dispatch together replicate
OpenClaw's full feature set
- security/auto-mode-explained.md: deep-dive on the new permission mode
- Updated README with broader ecosystem table and revised scores
Score: 12 full match (55%), 9 different approach (41%), 1 gap (4%)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
