Tooluck logoTooluck
SKILL.md

agent-protocol

Agent skill fromalirezarezvani/claude-skills

Use when C-suite advisor agents need to call each other or run a multi-role meeting. Defines invocation syntax, loop prevention, isolation and response formats.

How to install agent-protocol

install agent-protocol
# install the claude-skills pack with the skills CLI
npx skills add alirezarezvani/claude-skills

# or add only this skill to Claude Code: copy the folder

c-level-advisor/skills/agent-protocol/

# into

~/.claude/skills/agent-protocol/ (all projects)

.claude/skills/agent-protocol/ (one project)

c-level-advisor/skills/agent-protocol/SKILL.md

MITFull file
1# Inter-Agent Protocol
2
3How C-suite agents talk to each other. Rules that prevent chaos, loops, and circular reasoning.
4
5## Keywords
6agent protocol, inter-agent communication, agent invocation, agent orchestration, multi-agent, c-suite coordination, agent chain, loop prevention, agent isolation, board meeting protocol
7
8## Invocation Syntax
9
10Any agent can query another using:
11
12```
13[INVOKE:role|question]
14```
15
16**Examples:**
17```
18[INVOKE:cfo|What's the burn rate impact of hiring 5 engineers in Q3?]
19[INVOKE:cto|Can we realistically ship this feature by end of quarter?]
20[INVOKE:chro|What's our typical time-to-hire for senior engineers?]
21[INVOKE:cro|What does our pipeline look like for the next 90 days?]
22```
23
24**Valid roles:** `ceo`, `cfo`, `cro`, `cmo`, `cpo`, `cto`, `chro`, `coo`, `ciso`, `gc`, `cdo`, `caio`, `cco`, `vpe`
25
26| Role token | Advisor skill |
27|---|---|
28| `gc` | general-counsel-advisor (legal, contracts, term sheets) |
29| `cdo` | chief-data-officer-advisor (data strategy, training-data rights) |
30| `caio` | chief-ai-officer-advisor (AI strategy, evals, AI risk) |
31| `cco` | chief-customer-officer-advisor (retention, customer success) |
32| `vpe` | vpe-advisor (engineering delivery, DORA, eng hiring) |
33
34## Response Format
35
36Invoked agents respond using this structure:
37
38```
39[RESPONSE:role]
40Key finding: [one line — the actual answer]
41Supporting data:
42 - [data point 1]
43 - [data point 2]
44 - [data point 3 — optional]
45Confidence: [high | medium | low]
46…

Excerpt shown under the repository's MIT license.

More skills in claude-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates