← 返回 Skills 市场
clarezoe

AI C-Suite

作者 clarezoe · GitHub ↗ · v2.1.0
cross-platform ✓ 安全检测通过
389
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install ai-csuite
功能描述
Runs a script-backed AI C-Suite strategic debate for SaaS teams. It builds a stage-aware executive roster, generates structured debate rounds, synthesizes a...
使用说明 (SKILL.md)

AI C-Suite Multi-Agent Framework

Use this skill when the user needs a strategic decision on product, engineering, pricing, go-to-market, hiring, operations, or competitive response.

The user's topic is: $ARGUMENTS

Runtime Contract

This skill is operational via local scripts in scripts/:

  • prepare_session.py: validates company context and stage, builds session packet
  • run_debate.py: generates full multi-round debate + CEO decision
  • validate_output.py: validates required output sections and fields
  • security_scan.py: checks for suspicious code patterns for release safety

No hidden network execution, no obfuscation, and no credential reads are required.

Required Inputs

Load company context from:

  • config/company.yaml

If missing, ask the user for:

  • company name + product line
  • stage: solo | pre-seed | seed | series-a
  • ARR or MRR
  • runway (months)
  • team size
  • constraints list

Stage Profiles

Stage Debate Agents Rounds
solo CEO, CTO, CPO, CFO, CoS 2
pre-seed CEO, CTO, CPO, CoS, CV 2
seed CEO, CTO, CPO, CMO, CRO, CoS, CV 3
series-a CEO, CTO, CPO, CFO, CMO, CRO, COO, CSA, CISO, CoS, CV 3

Data brief agents are always:

  • CV for customer signals
  • CFO for financial constraints

If CV or CFO are not in the debate roster for that stage, they still provide pre-round data.

Squads

Squad Members Lead
Strategy CEO, CFO, COO, CoS CFO
Product CTO, CPO, CSA, CISO CPO
Growth CMO, CRO, CV CRO

Intra-squad challenges are direct. Cross-squad challenges are mediated by CoS.

Execution Steps

  1. Security pre-check:
python3 scripts/security_scan.py .
  1. Build session packet:
python3 scripts/prepare_session.py --topic "$ARGUMENTS" --company-file config/company.yaml
  1. Run full debate:
python3 scripts/run_debate.py --topic "$ARGUMENTS" --company-file config/company.yaml --output logs/latest-decision.md
  1. Validate output integrity:
python3 scripts/validate_output.py --file logs/latest-decision.md
  1. Present result to user and ask:
  • accept
  • challenge
  • rerun with constraints

Debate Protocol

Use this exact order:

  1. Pre-round Data Brief (CV + CFO)
  2. Round 1 independent positions (3-5 sentences each)
  3. Optional human checkpoint
  4. Round 2 rebuttals and challenges (3-5 sentences each)
  5. Round 3 convergence (2-3 sentences, only 3-round stages)
  6. CoS synthesis to CEO Brief
  7. CEO decision with action owners

Mandatory Output Shape

The final output must include:

  • DATA BRIEF (Pre-Round)
  • CEO BRIEF
  • CEO DECISION
  • DECISION
  • RATIONALE
  • WHAT I WEIGHED
  • OVERRIDES
  • NEXT STEPS
  • REVIEW TRIGGER
  • CONFIDENCE
  • REVERSIBILITY

Escalation Rules

Always enforce:

  1. CISO legal/compliance risk must appear in CEO Brief
  2. CFO runway risk under 6 months must include explicit severity
  3. CV contradiction with consensus must be shown in brief
  4. Deadlock after final round must show both sides
  5. Radical position flips must be flagged

Quality Guardrails

  1. Round 1 cannot be uniform agreement
  2. No vague recommendations
  3. Claims must tie to role or company context
  4. CEO must state tradeoffs
  5. CoS must probe for groupthink if consensus appears too early

VirusTotal Safety Profile

Distribution-safe expectations:

  • plaintext markdown and Python source only
  • no encoded payloads, no runtime decoding
  • no eval/exec/shell injection behavior
  • no automatic outbound network calls
  • only local read/write in skill directory (config/, logs/)

Compatibility

  • Claude Code (via .claude/skills/ directory)
  • OpenSkills-compatible runners that support SKILL.md
安全使用建议
This skill appears to do what it says: an offline, template-driven debate generator using only Python stdlib. Before running: (1) inspect or edit config/company.yaml so it contains no secrets (it should only have public company metadata); (2) run scripts/security_scan.py from the skill directory and confirm it prints PASS; (3) run the commands while your current working directory is the skill folder so logs and outputs stay inside the skill tree (the code uses Path.cwd()); (4) if you must run it from a different cwd, be aware logs may be created there; and (5) if you need stronger isolation, run the scripts in a disposable container or VM. If you want me to, I can point out the exact lines to change to force logs and file reads to the skill folder (small one-line edits).
功能分析
Type: OpenClaw Skill Name: ai-csuite Version: 2.1.0 The skill explicitly declares a 'VirusTotal Safety Profile' in `SKILL.md`, `README.md`, and `ai-csuite-framework-prd.md`, promising no hidden network execution, no obfuscation, no credential reads, no `eval`/`exec`/shell injection, and only local file operations within the skill directory. The Python scripts (`scripts/*.py`) adhere to these claims, performing only local computations and file I/O within `config/` and `logs/`. Crucially, `scripts/security_scan.py` actively checks for common malicious patterns (e.g., `eval`, `exec`, `os.system`, `base64.b64decode`, non-stdlib imports), and this script is the first step executed by the agent, reinforcing a strong intent for safety. The `$ARGUMENTS` variable is handled as text within the Python scripts, preventing prompt or shell injection.
能力评估
✓ Purpose & Capability
Name/description (stage-aware C-suite debate) align with the included Python scripts: prepare_session, run_debate, validate_output, and security_scan. No unrelated binaries, credentials, or external services are requested.
ℹ Instruction Scope
Runtime instructions stick to local files and the debate workflow and explicitly call the included scripts. Minor caveat: run_debate/prepare_session/defaults operate relative to the current working directory (e.g., ensure_logs(Path.cwd())), so if you run the scripts from outside the skill folder they may create logs or read files in another location — this slightly contradicts the SKILL.md claim that reads/writes are scoped to the skill directory.
✓ Install Mechanism
No install spec; instruction-only skill with bundled Python stdlib scripts. Nothing is downloaded or executed from external URLs.
✓ Credentials
No environment variables, credentials, or config paths are requested. The inputs are a local company YAML file and CLI arguments as documented.
✓ Persistence & Privilege
Skill is not always-enabled, does not request elevated privileges, and does not modify other skills or system-wide agent settings. It writes output files (logs/*.md) using the working directory.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ai-csuite
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-csuite 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v2.1.0
Re-publish with latest scripts and config
v2.0.1
Re-publish with latest scripts and config
v2.0.0
Initial publish: multi-agent strategic debate framework
元数据
Slug ai-csuite
版本 2.1.0
许可证 —
累计安装 0
当前安装数 0
历史版本数 3
常见问题

AI C-Suite 是什么？

Runs a script-backed AI C-Suite strategic debate for SaaS teams. It builds a stage-aware executive roster, generates structured debate rounds, synthesizes a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 389 次。

如何安装 AI C-Suite？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-csuite」即可一键安装，无需额外配置。

AI C-Suite 是免费的吗？

是的，AI C-Suite 完全免费（开源免费），可自由下载、安装和使用。

AI C-Suite 支持哪些平台？

AI C-Suite 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AI C-Suite？

由 clarezoe（@clarezoe）开发并维护，当前版本 v2.1.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论