Content & Media Creation · alirezarezvani/claude-skills

ceo-advisor

Name: ceo-advisor
Author: alirezarezvani/claude-skills

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, fundraising, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.

L4 High-Privilege · Graded auth & full auditV1 Commit-PinnedExecute CommandWrite FileDual-pass Audit

Author alirezarezvaniGitHub alirezarezvani/claude-skills ↗Stars 25977License MIT（SKILL.md frontmatter `license: MIT`；仓库根 LICENSE：'MIT License / Copyright (c) 2025 Alireza Rezvani'；GitHub API spdx_id=MIT）Commit 19392f7a08

Control levels describe skill capabilities and suggested control measures; they do not represent quality or safety certifications, nor do they dictate usability. Usage decisions rest entirely with users and administrators. Different agent hosts apply varying constraints; do not assume hosts provide automatic protection. Third-party skill copyrights belong to their original authors. Use at your own risk.

1How It Works & Mechanism

The core prompt asset is structured around 'CEO Responsibility Framework + Quantitative Dashboard + Red Flag Checklist': five core responsibility pillars (Vision & Strategy / Capital & Allocation / People & Culture / Stakeholder Management / Board & Governance) each point to an in-depth reference document.

c-level-advisor/skills/ceo-advisor/SKILL.md

### 1. Vision & Strategy Set the direction. Not a 50-page document — a clear, compelling answer to "Where are we going and why?"

What is happening here: The role of 'serving as a CEO advisor' is decomposed into referenceable responsibility blocks. Each block concludes with a reference path (e.g., 'See `references/executive_decision_framework.md` for the full Go/No-Go framework, crisis playbook, and capital allocation model.'), establishing a layered architecture where SKILL.md remains concise while references are comprehensive—preventing excessive main file length and facilitating on-demand loading.

Includes two Python tools built using only the standard library, positioned as 'runnable scoring models' rather than CLI analyzers: scripts import only json, typing, datetime, and math, feature no argument parsing, and involve no file or network I/O; `__main__` executes built-in sample company data and prints a report.

c-level-advisor/skills/ceo-advisor/scripts/strategy_analyzer.py

if __name__ == "__main__": # Example usage example_company = { 'name': 'TechCorp Inc.', 'market_position': { 'market_share': 35,

The five strategic pillars and weights defined in the same file (market_position 0.25 / financial_health 0.25 / operational_excellence 0.20 / organizational_capability 0.20 / growth_potential 0.10) establish the scoring baseline. To derive actionable insights, the model must construct its own company_data to invoke analyze_strategy() or adapt the sample code as a template. SKILL.md's Quick Start instructs running `python scripts/strategy_analyzer.py` directly; users should understand that this runs sample data.

The second script performs three-scenario (base/bull/bear) financial modeling, likewise driven by hardcoded sample data in `__main__`, exposing analyze_financial_scenarios(base_case, scenarios) for external invocation.

c-level-advisor/skills/ceo-advisor/scripts/financial_scenario_analyzer.py

print(analyze_financial_scenarios(example_base_case, example_scenarios))

The sample scenario includes fields such as probability, growth_model (exponential|linear), growth_rate, cogs_ratio, opex_growth, capex_ratio, discount_rate, etc.—computing probability-weighted scenario expectations as a textbook DCF variant. SKILL.md describes this as 'Model financial scenarios (base/bull/bear)'.

Outputs adhere to strict formatting and confidence governance: Bottom Line → What (with confidence level) → Why → How to Act → Your Decision. Every finding is labeled as 🟢 verified / 🟡 medium / 🔴 assumed, and results must pass the repository's unified Internal Quality Loop (Self-Check / Cross-Functional Check / Executive Mentor Review).

c-level-advisor/skills/ceo-advisor/SKILL.md

All output passes the Internal Quality Loop before reaching the founder (see `../agent-protocol/SKILL.md`). - Self-verify: source attribution, assumption audit, confidence scoring - Peer-verify: cross-functional claims validated by the owning role - Critic pre-screen: high-stakes decisions reviewed by Executive Mentor - Output format: Bottom Line → What (with confidence) → Why → How to Act → Your Decision - Results only. Every finding tagged: 🟢 verified, 🟡 medium, 🔴 assumed.

What is happening here: Advisory output is transformed into an auditable deliverable featuring confidence stratification and explicit reservation of decision rights for the user (standardizing the final section as 'Your Decision'). Verification confirmed the existence of the ../agent-protocol/ directory (c-level-advisor/skills/agent-protocol).

Reasoning technique is tied to Tree of Thought, requiring at least three distinct paths evaluated across upside/downside/reversibility/second-order effects, with planning horizons adjusted by company stage.

c-level-advisor/skills/ceo-advisor/SKILL.md

## Reasoning Technique: Tree of Thought Explore multiple futures. For every strategic decision, generate at least 3 paths. Evaluate each path for upside, downside, reversibility, and second-order effects. Pick the path with the best risk-adjusted outcome.

Stage-dependent planning horizons: Seed 3m/6m/12m; Series A 6m/1y/2y; Series B+ 1y/3y/5y (consistently defined across two sections in SKILL.md: Strategic planning cycle and Reasoning Technique).

Context injection relies on standard file conventions: It 'ALWAYS' reads company-context.md (if present) before every response and allows the agent to initiate [INVOKE:role|question] requests to peer roles, establishing lateral cross-consultation within the C-suite advisory council.

c-level-advisor/skills/ceo-advisor/SKILL.md

- **Always** read `company-context.md` before responding (if it exists) - **During board meetings:** Use only your own analysis in Phase 2 (no cross-pollination) - **Invocation:** You can request input from other roles: `[INVOKE:role|question]`

c-level-advisor/CLAUDE.md notes that this file is generated by /cs:setup (Founder Interview): '/cs:setup (Founder Interview) → company-context.md'. This constitutes the skill's sole external input channel as well as its injection surface (see security).

The quantitative section establishes standard evaluation baselines via the CEO Metrics Dashboard table (ARR growth, runway > 12 months, burn multiple < 2x, NPS > 40, regrettable attrition < 10%, strategic work allocation > 40%, etc.), enabling advice to be challenged with concrete metrics.

c-level-advisor/skills/ceo-advisor/SKILL.md

| **Capital** | Months of runway | > 12 months | Monthly | | **Capital** | Burn multiple | < 2x | Monthly |

The same table details annual Strategy goal completion > 70%, Revenue ARR growth (stage-dependent), Product NPS/PMF > 40, People engagement > 7/10, positive Board NPS, and Personal time allocated to strategic work > 40%.

A lateral collaboration matrix links the CEO to other C-suite roles by scenario (COO for OKR translation, CFO for fundraising modeling, CHRO for culture assessment, CISO for risk posture, etc.), formalized in c-level-advisor/CLAUDE.md's architectural view: 'Chief of Staff routing → 10 roles → Executive Mentor critique → Decision Logger memory'.

c-level-advisor/skills/ceo-advisor/SKILL.md

| Setting direction | COO | Translate vision into OKRs and execution plan | | Fundraising | CFO | Model scenarios, prep financials, negotiate terms | | Board meetings | All C-suite | Each role contributes their section |

The plugin manifest c-level-advisor/.claude-plugin/plugin.json (name 'c-level-skills', version 2.9.0, description '33 C-level advisory skills…') declares skills: ["./skills"], meaning this skill is distributed as part of the overall plugin suite.

2Core Capabilities

01Weighted scoring model for strategic options (five pillars × multi-factor evaluation, runnable via script)

02Three-scenario financial modeling (base/bull/bear with probability weighting and configurable growth models)

03CEO Metrics Dashboard and threshold benchmarks (runway, burn multiple, NPS, attrition, strategic time allocation, etc.)

04Red Flag self-audit checklist (7 signals, including > 3 decisions blocked weekly, calendar 80% consumed by meetings, passive fundraising with runway < 6 months)

05Proactive Triggers: runway < 12 months without a fundraising plan, strategy unreviewed for 2 quarters, approaching board meetings without preparation, etc.

06Structured decision delivery format with confidence stratification (Bottom Line → What → Why → How to Act → Your Decision; 🟢/🟡/🔴)

07Board of Directors and investor communications support (board narrative framing + anticipated Q&A + data gap analysis; investor communication cadence; managing difficult board members)

08Organizational culture and leadership framework (including CEO learning agendas, succession planning, and crisis management)

4Recommended Governance & Evidence

Suggested Controls for Safe Operation

For Agent Runtime

Graded/per-use authorization, sandbox recommended

For Administrators

Approval workflow, rollback support, full audit

Evidence & Triggers (File Paths & Excerpts)

scripts/: Local script or command execution: python scripts/strategy_analyzer.py (explicitly stated in SKILL.md Quick Start; actually executes module `__main__`)
本地工作目录: File I/O and artifact output: Indirect: other skills within the c-level-advisor pod (decision-logger, company-os) handle memory persistence and decision logging, outside of this skill

Audit Notes: Both scripts rely solely on Python standard libraries for pure computation and printing: no network access (zero URL/urllib/requests/socket hits across the codebase), no credential extraction (zero os.environ hits), and no file writing; SKILL.md contains no standalone shell commands. Fundamentally, it represents an executive management framework prompt asset coupled with two parameterized scoring models. Users should be aware that contents in company-context.md are treated as ground-truth context (local file, human-reviewable), and that script sample data does not represent their actual company—executing scripts out of the box will produce demonstration results for TechCorp.

5Second-Pass Verification

[ok] skill 路径（任务书标『待定位』） — 实际相对路径 c-level-advisor/skills/ceo-advisor；仓库内另有 .gemini/skills/ceo-advisor（生成镜像，逐字相同）、.hermes/.vibe 打包树，以及 c-level-advisor/ceo-advisor.zip（见下条）。
[ok] 『两个 Python 工具』的真实能力 — 两脚本确实存在且可独立运行，但都只含内置示例数据、无 argparse/无输入输出文件参数：strategy_analyzer.py 的 __main__ 构造 example_company（TechCorp Inc.）后 print；financial_scenario_analyzer.py 的 __main__ 构造三个示例情景后 print。如实测能力应为『可复用的评分函数库 + 演示运行』，SKILL.md Quick Start 的三行注释（'Analyze strategic options with weighted scoring' 等）描述的是函数能力而非 CLI 行为，未夸大但易被误读。
[discrepancy] 随包 zip 与目录版本不一致 — c-level-advisor/ceo-advisor.zip 内的 ceo-advisor/SKILL.md 是旧版：505 行、frontmatter 无 license/metadata、description 为 'Comprehensive CEO leadership skill providing strategic planning frameworks, financial scenario modeling, board governance guidance, investor relations strategies, and organizational leadership tools. …'，条目时间 2025-10-18/19；目录内为 169 行、version 2.0.0、updated 2026-03-05 的新版。凡按 zip 安装者拿到的是旧内容（含旧脚本副本）。属分发产物未同步。
[ok] 引用目标（agent-protocol / culture-architect / board-deck-builder） — 三者均存在于 c-level-advisor/skills/ 下；正文 'see `../agent-protocol/SKILL.md`' 路径正确。
[ok] 无网络/无凭证/无写入 — 全目录 token 扫描零命中；两脚本 import 仅标准库；脚本无 open()、无 subprocess、无环境变量读取。company-context.md 为读取路径（SKILL.md 文本指令），非本目录内代码行为。
[ok] 跨宿主镜像一致性 — diff -q .gemini/skills/ceo-advisor/SKILL.md c-level-advisor/skills/ceo-advisor/SKILL.md 无输出（内容相同），确认为 sync-gemini-skills.py 生成产物。
[ok] 输出协议引用的一致性 — SKILL.md 声称输出过 Internal Quality Loop 并引用 ../agent-protocol/SKILL.md；该文件存在，属仓库统一协议，非本 skill 独有机制（已如实标注归属）。
[ok] 元数据（commit/license/stars/last_push） — 本地 git HEAD = 19392f7a08264ed00486a251f5b2098321771f94（= 任务书 pin 19392f7a0826）；SKILL.md frontmatter license MIT、metadata.version 2.0.0、author Alireza Rezvani、category c-level、updated 2026-03-05；LICENSE MIT / Copyright (c) 2025 Alireza Rezvani；gh api → stars 25977、pushed_at 2026-08-30T09:46:16Z。

6Verdict & Scenarios

High framework density and immediate operational utility: Combines responsibility blocks, quantitative dashboards, red flag checklists, and Go/No-Go criteria, allowing CEOs to directly benchmark reality against explicit thresholds.

Auditable decision-making: Prioritizes Bottom Line, provides tiered confidence levels, explicitly reserves final decision authority for the user, and enforces the Internal Quality Loop.

Structured reasoning: Tree of Thought requires evaluating at least three paths based on risk-adjusted upside, preventing single-narrative bias.

Computational rigor over abstract advice: Two standalone scripts turn five-pillar weighted scoring and three-scenario financial modeling into parameterized, executable functions.

Clear positioning within the advisory council (COO/CFO/CHRO/CISO, etc.), facilitating seamless delegation of cross-functional issues rather than force-fitting answers.

Best for: Ideal for founders, CEOs, and executives seeking structured thinking and presentation preparation: formulating strategy, preparing for board meetings, evaluating fundraising timing, assessing culture and organizational health, handling difficult stakeholders, and modeling high-uncertainty decisions across three distinct paths. Also well-suited for startup teams that have established company-context.md and want an agent acting as a rigorous advisor equipped with structured frameworks, metric thresholds, and critical self-evaluation loops. Installed via the c-level-skills plugin (claude /plugin install …).

Not for: Not suitable for scenarios requiring real-time market data, production-grade financial calculations, or certified legal counsel (no internet access, external data feeds, or professional legal certifications); not intended for non-managerial operational inquiries (it functions as an executive management advisor, not a general Q&A assistant); not designed for automated file writing or direct decision log persistence (handled by sibling skills in the pod, such as decision-logger); and not intended for drawing definitive conclusions from script outputs without modifying parameters—the scripts require user-supplied data.

Install Agent-Ready

① Verified Mirror 2026-09-15

Option A · Direct DownloadDownload ceo-advisor.tar.gz

sha256: 4c873d324e29d1c8…

Option B · Copy Guide for Agent

install.json

Agents automatically download and verify mirrors from this JSON guide.

② Upstream GitHub

GitHub Repo ↗

Pinned to commit 19392f7a08.