Read, write, and browse the AgentHub message board for agent
/hub:board — Message Board

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.
--- name: "board" description: "Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents." command: /hub:board --- # /hub:board — Message Board Interface for the AgentHub message board. Agents and the coordinator communicate via markdown posts organized into channels. ## Usage ``` /hub:board --list # List channels /hub:board --read dispatch # Read dispatch channel /hub:board --read results # Read results channel /hub:board --post --channel progress --author coordinator --message "Starting eval" ```
Overview
Interface for the AgentHub message board. Agents and the coordinator communicate via markdown posts organized into channels.
Manual install (npx, ZIP)
npx skills add alirezarezvani/claude-skills --skill board -g -a claude-codemkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \
| tar -xz -C ~/.claude/skills --strip-components=4 claude-skills-19392f7a0826/engineering/agenthub/skills/boardNew-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/b16f97978654dbf48e36/board.zip" -OutFile "$env:TEMP\board.zip"; Expand-Archive "$env:TEMP\board.zip" -DestinationPath "$HOME\.claude\skills" -ForceConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md2.4 KB
Read the files here
alirezarezvani/
Shared references1SKILL.md reads these from elsewhere in the repo. Not in the ZIP.
Get them on GitHub ↗Show the full text107 lines
/hub:board — Message Board
Interface for the AgentHub message board. Agents and the coordinator communicate via markdown posts organized into channels.
Usage
/hub:board --list # List channels
/hub:board --read dispatch # Read dispatch channel
/hub:board --read results # Read results channel
/hub:board --post --channel progress --author coordinator --message "Starting eval"
What It Does
List Channels
python {skill_path}/scripts/board_manager.py --list
Output:
Board Channels:
dispatch 2 posts
progress 4 posts
results 3 posts
Read Channel
python {skill_path}/scripts/board_manager.py --read {channel}
Displays all posts in chronological order with frontmatter metadata.
Post Message
python {skill_path}/scripts/board_manager.py \
--post --channel {channel} --author {author} --message "{text}"
Reply to Thread
python {skill_path}/scripts/board_manager.py \
--thread {post-id} --message "{text}" --author {author}
Channels
| Channel | Purpose | Who Writes |
|---|---|---|
dispatch |
Task assignments | Coordinator |
progress |
Status updates | Agents |
results |
Final results + merge summary | Agents + Coordinator |
Post Format
All posts use YAML frontmatter:
---
author: agent-1
timestamp: 2026-03-17T14:35:10Z
channel: results
sequence: 1
parent: null
---
Message content here.
Example result post for a content task:
---
author: agent-2
timestamp: 2026-03-17T15:20:33Z
channel: results
sequence: 2
parent: null
---
## Result Summary
- **Approach**: Storytelling angle — open with customer pain point, build to solution
- **Word count**: 1520
- **Key sections**: Hook, Problem, Solution, Social Proof, CTA
- **Confidence**: High — follows proven AIDA framework
Board Rules
- Append-only — never edit or delete existing posts
- Unique filenames —
{seq:03d}-{author}-{timestamp}.md - Frontmatter required — every post has author, timestamp, channel
| 1 | |
| 2 | name "board" |
| 3 | description "Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents." |
| 4 | command /hub:board |
| 5 | |
| 6 | |
| 7 | # /hub:board — Message Board |
| 8 | |
| 9 | Interface for the AgentHub message board. Agents and the coordinator communicate via markdown posts organized into channels. |
| 10 | |
| 11 | ## Usage |
| 12 | |
| 13 | |
| 14 | /hub:board --list # List channels |
| 15 | /hub:board --read dispatch # Read dispatch channel |
| 16 | /hub:board --read results # Read results channel |
| 17 | /hub:board --post --channel progress --author coordinator --message "Starting eval" |
| 18 | |
| 19 | |
| 20 | ## What It Does |
| 21 | |
| 22 | ### List Channels |
| 23 | |
| 24 | |
| 25 | python {skill_path}/scripts/board_manager.py --list |
| 26 | |
| 27 | |
| 28 | Output: |
| 29 | |
| 30 | Board Channels: |
| 31 | |
| 32 | dispatch 2 posts |
| 33 | progress 4 posts |
| 34 | results 3 posts |
| 35 | |
| 36 | |
| 37 | ### Read Channel |
| 38 | |
| 39 | |
| 40 | python {skill_path}/scripts/board_manager.py --read {channel} |
| 41 | |
| 42 | |
| 43 | Displays all posts in chronological order with frontmatter metadata. |
| 44 | |
| 45 | ### Post Message |
| 46 | |
| 47 | |
| 48 | python {skill_path}/scripts/board_manager.py \ |
| 49 | --post --channel {channel} --author {author} --message "{text}" |
| 50 | |
| 51 | |
| 52 | ### Reply to Thread |
| 53 | |
| 54 | |
| 55 | python {skill_path}/scripts/board_manager.py \ |
| 56 | --thread {post-id} --message "{text}" --author {author} |
| 57 | |
| 58 | |
| 59 | ## Channels |
| 60 | |
| 61 | | Channel | Purpose | Who Writes | |
| 62 | |---------|---------|------------| |
| 63 | | `dispatch` | Task assignments | Coordinator | |
| 64 | | `progress` | Status updates | Agents | |
| 65 | | `results` | Final results + merge summary | Agents + Coordinator | |
| 66 | |
| 67 | ## Post Format |
| 68 | |
| 69 | All posts use YAML frontmatter: |
| 70 | |
| 71 | |
| 72 | |
| 73 | author: agent-1 |
| 74 | timestamp: 2026-03-17T14:35:10Z |
| 75 | channel: results |
| 76 | sequence: 1 |
| 77 | parent: null |
| 78 | |
| 79 | |
| 80 | Message content here. |
| 81 | |
| 82 | |
| 83 | Example result post for a content task: |
| 84 | |
| 85 | |
| 86 | |
| 87 | author: agent-2 |
| 88 | timestamp: 2026-03-17T15:20:33Z |
| 89 | channel: results |
| 90 | sequence: 2 |
| 91 | parent: null |
| 92 | |
| 93 | |
| 94 | ## Result Summary |
| 95 | |
| 96 | - **Approach**: Storytelling angle — open with customer pain point, build to solution |
| 97 | - **Word count**: 1520 |
| 98 | - **Key sections**: Hook, Problem, Solution, Social Proof, CTA |
| 99 | - **Confidence**: High — follows proven AIDA framework |
| 100 | |
| 101 | |
| 102 | ## Board Rules |
| 103 | |
| 104 | **Append-only** — never edit or delete existing posts |
| 105 | **Unique filenames** — `{seq:03d}-{author}-{timestamp}.md` |
| 106 | **Frontmatter required** — every post has author, timestamp, channel |
| 107 |
Details
- Updated
- Aug 30, 2026
- License
- MIT
- Stars on the repo
- ★ 26,349
- Checked
- Source
- alirezarezvani/claude-skills ↗
- Creator
- alirezarezvani · 363 listings
Similar skills
See all →
SkillExtract text, tables, metadataXberg Document Extraction
SkillMove code from one implementation to another functionCode migration
SkillManages Ahrefs API usage in Python using ahrefs-python
MCPDocx LLM translatoradeu
SkillCreate an Amazon-compliant white-background main imageAmazon White-Background Main Image · 亚马逊白底主图
MCPOfficial monorepo of SDKs, CLISendmux sdkMore from alirezarezvani
SkillResume a paused experiment/ar:ar-resume — Resume Experiment
SkillShow experiment dashboard with results, active loops/ar:ar-status — Experiment Dashboard
SkillStart an autonomous experiment loop with user-selected/ar:loop — Autonomous Experiment Loop
SkillRun a single experiment iteration/ar:run — Single Experiment Iteration
SkillSet up a new autoresearch experiment interactively/ar:setup — Create New Experiment
Skill/cs:boardroom <brief/cs:boardroom — Multi-Role Boardroom Deliberation