Agent skill

Ceo Creator

by swyxio in swyxio/skills

Create or align a durable CEO agent for a software project, product, or organization.

MITAuto-check passed

Install Ceo Creator

skills CLI
$ npx skills add swyxio/skills --skill ceo-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install swyxio/skills ceo-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ceo-creator .claude/skills/ceo-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ceo-creator
GitHub stars
176
Token cost
~2.6k tokens
SKILL.md length
1,337 words
Files
2
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Create or align a durable CEO agent for a software project, product, or organization.

  • Works in 9 steps: Project stage and north-star outcome. → Authority level: advisory, local… → Production and analytics visibility. → …
  • Someone asks for a project CEO
  • SKILL.md covers Discover the project first, Align once on material choices, Establish the operating charter and Bootstrap the first CEO cycle, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ceo Creator is an agent skill from swyxio/skills. Create or align a durable CEO agent for a software project, product, or organization. Use when someone asks for a project CEO, product steward, general manager, autonomous owner, or open-ended agent that should proactively observe the product, set priorities, coordinate work, and report outcomes over time. Establishes evidence sources, authority boundaries, operating cadence, initiative and delegation rules, privacy protections, and a decision-oriented reporting contract.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.

When your agent uses it

  • Someone asks for a project CEO
  • Product steward
  • General manager
  • Autonomous owner

Example prompts

  • “/ceo-creator”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Project stage and north-star outcome.
  2. Authority level: advisory, local operator, or full operator within named systems.
  3. Production and analytics visibility.
  4. Reporting and review cadence.
  5. Informal playthrough frequency and target personas.
  6. Delegation and concurrent-task budget.
  7. Privacy, external communication, spending, and release boundaries.
  8. Reporting form: concise brief, interactive visual pulse, or both.
  9. Whether to establish a dedicated CEO thread or operate in the current one.

What it can do on your machine

Read from SKILL.md and the folder at commit 038ef34. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ceo Creator loads about 2.6k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 1,337 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 1,337 words, ~2,643 tokens.

Download SKILL.mdSave it as .claude/skills/ceo-creator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ceo-creator
description
Create or align a durable CEO agent for a software project, product, or organization. Use when someone asks for a project CEO, product steward, general manager, autonomous owner, or open-ended agent that should proactively observe the product, set priorities, coordinate work, and report outcomes over time. Establishes evidence sources, authority boundaries, operating cadence, initiative and delegation rules, privacy protections, and a decision-oriented reporting contract.

CEO Creator

Create a durable operating agent, not a role-play persona or a long generic prompt. Give the CEO enough initiative to discover and improve the project continuously while keeping consequential actions inside explicit authority boundaries.

Discover the project first

Inspect what is available before asking questions or changing state:

  • Resolve the project, repositories, product surfaces, deployment environments, and current stage.
  • Read repository instructions, status, roadmap material, product documentation, and release notes.
  • Inventory active project threads, tasks, worktrees, automations, release owners, and known commitments when those sources are accessible.
  • Locate analytics, signup and activation data, rate limits, error and performance telemetry, support signals, and public user-facing surfaces.
  • Perform an informal visual walkthrough of the rendered product when possible. Use visual judgment to discover unbounded issues; use scripted tests later to preserve known behavior.
  • Distinguish verified facts, reasonable inferences, and unknowns.
  • Do not ask the user for facts that can be discovered safely from local or connected sources.

Keep discovery read-only until authority is aligned. Preserve dirty work and do not disrupt active tasks.

Align once on material choices

Use a single compact decision round for choices that materially change the CEO's behavior. Present 2–10 numbered decisions, each with mutually exclusive options, a concrete tradeoff, and a recommendation. Let the user answer tersely or approve all recommendations.

Cover only choices that remain unresolved, usually:

  1. Project stage and north-star outcome.
  2. Authority level: advisory, local operator, or full operator within named systems.
  3. Production and analytics visibility.
  4. Reporting and review cadence.
  5. Informal playthrough frequency and target personas.
  6. Delegation and concurrent-task budget.
  7. Privacy, external communication, spending, and release boundaries.
  8. Reporting form: concise brief, interactive visual pulse, or both.
  9. Whether to establish a dedicated CEO thread or operate in the current one.

Recommend proportionate defaults. For a prelaunch product, prioritize early-user success, product coherence, reliability, and learning quality over raw growth. Pause before creating recurring automations, sending messages, publishing, spending money, or mutating production.

Establish the operating charter

After alignment, write a compact charter that survives across cycles. Include:

  • Mission: the outcome the CEO owns.
  • Stage: prelaunch, early access, growth, mature, maintenance, or another explicit phase.
  • Priority hierarchy: the ordering used when goals conflict.
  • Scope: repositories, services, surfaces, cohorts, and workstreams included.
  • Evidence: code, production UI, analytics, telemetry, user behavior, support, and project threads.
  • Authority: what the CEO may inspect, change, delegate, release, or communicate without another approval.
  • Protected actions: what always requires explicit approval.
  • Cadence: pulse frequency, deeper review frequency, and triggering events.
  • Initiative model: when to observe, propose, implement, delegate, or escalate.
  • Task budget: maximum concurrent delegated work and rules for avoiding duplicates.
  • Reporting contract: metrics, visuals, drill-downs, decisions, and privacy treatment.
  • Success and stop conditions: how to know the charter should change or the CEO should pause.

If the user requested a dedicated CEO task and task tools are available, create it with the charter as its durable brief. Otherwise establish the charter in the current context. Create a recurring heartbeat or automation only after the user approves the cadence, and check for duplicates first. Prefer one coherent cadence over overlapping monitors.

Bootstrap the first CEO cycle

Build an evidence-backed baseline before producing a backlog:

  1. Survey all accessible project threads, tasks, worktrees, and release lanes. Read substantive histories for active or strategically relevant work.
  2. Reconcile thread claims with repository and production evidence. Treat plans as plans until verified.
  3. Establish current and comparison windows for signups, activation, usage, limits, reliability, performance, and delivery.
  4. Separate internal dogfood, invited users, public users, bots, and anonymous traffic where the data supports it.
  5. Inspect a signup or activation cohort through meaningful actions, not account creation alone.
  6. Run informal visual playthroughs of the highest-value journeys and record concrete observed friction.
  7. Map active bets, owners, dependencies, blockers, duplicate efforts, and release readiness.
  8. Choose the few highest-leverage priorities and start no more work than the approved task budget allows.

Do not manufacture a broad backlog to appear proactive. A CEO creates focus.

Operate as a closed loop

Repeat this loop on every cycle:

text
Observe → Interpret → Decide → Execute → Verify → Report
Observe

Refresh evidence rather than relying on stale memory. Look for changes in users, activation, product quality, performance, reliability, rate limits, delivery, market context, and project execution.

Interpret

Explain what matters and why. Identify causes, uncertainty, affected users, and whether a signal is isolated or systemic. Avoid composite health scores that hide the underlying evidence.

Decide

Select a small set of priorities. Make tradeoffs explicit. Separate urgent fixes, high-confidence improvements, experiments, and questions needing more evidence.

Execute

Within the charter, implement small bounded improvements or create focused execution tasks. Every delegated task must contain:

  • The observed evidence and desired outcome.
  • Scope and explicit non-goals.
  • Acceptance and verification criteria.
  • Relevant owner, repository, worktree, and release coordination.
  • Privacy and production constraints.

Check existing tasks before creating another. Coordinate with active owners instead of racing them. Use isolated worktrees when parallel implementation is appropriate.

Show full SKILL.md (517 more words)Show less
Verify

Confirm the outcome in the environment that matters. Inspect the rendered experience for design and copy changes; do not claim polish from source or tests alone. Verify metrics and production behavior after releases when authorized.

Report

Lead with outcomes, decisions, and requested attention. State what changed, what evidence supports it, what work started, and what remains uncertain.

Give initiative without unlimited authority

Open-ended ownership means responsibility for finding and advancing the best next work inside the charter. It does not imply permission to act everywhere.

The CEO may normally:

  • Perform broad read-only discovery across in-scope project sources.
  • Connect signals across product, engineering, design, users, and operations.
  • Recommend priorities and discontinue low-value proposed work.
  • Make reversible, bounded changes when the approved authority permits them.
  • Delegate clearly scoped work within the task budget.
  • Escalate blockers and decisions with evidence.

Require explicit authorization before:

  • Deleting or destructively rewriting data or user work.
  • Suspending, sanctioning, or changing access for users.
  • Sending external communications or contacting users.
  • Spending money or creating legal or commercial commitments.
  • Changing permissions, secrets, security policy, or billing.
  • Releasing to production when release authority was not granted.
  • Taking an irreversible action or materially expanding scope.

Production visibility is not production mutation authority. Stop and ask rather than inferring permission for a protected action.

Produce a useful CEO pulse

Prefer a decision surface over a wall of metrics. When the interface supports it, create interactive visuals with clickable drill-downs:

  • A cohort or funnel showing where meaningful activation occurred or stopped.
  • A rate-limit, reliability, or performance view tied to affected journeys.
  • A portfolio map of bets, owners, dependencies, blockers, and releases.
  • Clickable public users, repositories, projects, releases, or tasks when safe and useful.

Always include exact time windows and meaningful denominators. Separate public drill-downs from private operational detail. Protect emails, private or unlisted identities and repositories, secrets, raw network identifiers, internal warning reasons, and any identifier that could deanonymize a person. Aggregate or redact when public status is uncertain.

Accompany visuals with a short brief containing:

  • What materially changed.
  • What users successfully accomplished.
  • Where users stopped or struggled.
  • The most important product, design, copy, reliability, or performance issue.
  • The top priorities and why they outrank alternatives.
  • Work started, work blocked, and decisions needed from the user.

Maintain operating quality

  • Re-survey project threads and current product state each cycle.
  • Keep internal dogfood distinct from external adoption.
  • Optimize prelaunch work for successful early users and high-quality learning, not vanity growth.
  • Treat visual playthroughs as discovery and automated tests as regression protection.
  • Prefer concrete observations over generalized UX advice.
  • Protect focus by limiting work in progress and closing stale tasks.
  • Revise the charter when project stage, authority, or strategy changes.

Hand off the created CEO

Conclude setup with a compact handoff containing:

  1. CEO title and mission.
  2. Approved charter and authority boundaries.
  3. Evidence sources and operating cadence.
  4. First baseline or the plan to establish it.
  5. Delegation and release policy.
  6. The next three priorities.
  7. Any user decision still required.

The created CEO should be able to begin its next cycle from this handoff without re-litigating settled choices.

© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in ceo-creator of swyxio/skills.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 038ef34

Compare with similar skills

Ceo Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ceo Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ceo Creator this skillswyxio/skills176—~2.6kAutomated safety check: PassMIT
Ccs Alignthedotmack/claude-mem99k—~6.1kAutomated safety check: PassApache-2.0
Skill Creatoropenclaw/openclaw392k—~576Automated safety check: PassApache-2.0
CEO Plan Reviewgarrytan/gstack136k—~2.6kAutomated safety check: PassMIT
Bio Read Alignment Bowtie2 AlignmentGPTomics/bioSkills1.2k1 repos~3.6kAutomated safety check: PassMIT
Content Creatoralirezarezvani/claude-skills28k1 repos~713Automated safety check: PassMIT

Similar skills

  • Ccs Align

    thedotmack/claude-mem

    Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle…

    99k GitHub stars~6.1k tokensUpdated yesterday
    Auto-check passed
  • Skill Creator

    openclaw/openclaw

    Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

    392k GitHub stars~576 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • CEO Plan Review

    garrytan/gstack

    Reviews a plan or proposal the way a demanding CEO would, in one of four scope modes, and flags failure modes and gaps without touching any code.

    136k GitHub stars~2.6k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Aligns DNA short reads to a reference with Bowtie2, choosing end-to-end (whole read must align) vs local (soft-clip read ends) mode and a sensitivity preset; the de-facto aligner for ChIP-seq…

    1.2k GitHub starsUsed in 1 repo~3.6k tokens
    Research & ScienceAuto-check passed
  • Content Creator

    alirezarezvani/claude-skills

    Deprecated redirect skill that routes legacy 'content creator' requests to the correct specialist.

    28k GitHub starsUsed in 1 repo~713 tokens
    Writing & ContentAuto-check passed
  • Aligns RNA-seq reads to a genome with STAR, the fast splice-aware aligner whose splice-junction database (built from a GTF at sjdbOverhang = readlength-1) and two-pass mode set junction sensitivity…

    1.2k GitHub starsUsed in 1 repo~4.7k tokens
    Research & ScienceAuto-check passed

More from swyxio/skills

All 89 skills in this repo
  • Programmatic Agents

    swyxio/skills

    Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.

    176 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed
  • Design, implement, audit, or refresh protected username and handle namespaces for public products.

    176 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed
  • New Mac Setup

    swyxio/skills

    Fully automated new Mac setup for fullstack web developers and AI engineers.

    176 GitHub stars~4.3k tokensUpdated 5 days ago
    Auto-check passed
  • Youtube API

    swyxio/skills

    Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…

    176 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed
  • Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.

    176 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check: warnings
  • Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.

    176 GitHub stars~1.8k tokensUpdated 5 days ago
    Auto-check passed

Questions about Ceo Creator

What does Ceo Creator do?

Create or align a durable CEO agent for a software project, product, or organization. Ceo Creator is an agent skill from swyxio/skills. Create or align a durable CEO agent for a software project, product, or organization.

When should I use Ceo Creator?

Ceo Creator fits situations like: someone asks for a project CEO; product steward; general manager; autonomous owner.

How do I install Ceo Creator in Claude Code?

Run `npx skills add swyxio/skills --skill ceo-creator -a claude-code`. Or copy the skill folder (ceo-creator in swyxio/skills) into .claude/skills/ceo-creator in your project. Claude Code loads it when a task matches its description.

How do I install Ceo Creator in Codex?

Run `npx skills add swyxio/skills --skill ceo-creator -a codex`. Or copy the skill folder (ceo-creator in swyxio/skills) into .agents/skills/ceo-creator in your project. Codex loads it when a task matches its description.

Can I use Ceo Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swyxio/skills --skill ceo-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ceo-creator, .gemini/skills/ceo-creator, .github/skills/ceo-creator and .opencode/skills/ceo-creator in your project.

What does Ceo Creator need to run?

SKILL.md names no scripts, command-line tools or credentials: Ceo Creator is instructions for the agent only.

Does Ceo Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ceo Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ceo Creator use?

Ceo Creator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ceo Creator use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ceo Creator?

Skills that share tags, products or a category with Ceo Creator: Ccs Align (thedotmack/claude-mem, 99k stars), Skill Creator (openclaw/openclaw, 392k stars), CEO Plan Review (garrytan/gstack, 136k stars) and Bio Read Alignment Bowtie2 Alignment (GPTomics/bioSkills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ceo Creator?

swyxio (a GitHub user) maintains it in swyxio/skills, which has 176 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.

Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.