chief-of-staff
Act as Tobias's chief of staff, the one thread he talks to.
Skill by TobiasBak
Chalk Labs
Need help deploying chief-of-staff?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tobiasbak-chief-of-staff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/chief-of-staff
What's inside
- Skill name
chief-of-staff- Description
- Act as Tobias's chief of staff, the one thread he talks to. It delegates project work to team threads, raises what needs him without blocking, diagnoses team performance as a context problem, and keeps the vault healthy. Invoked only by Tobias.
- License
- unknown
- Instructions
- 113 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- SKILL.md
- openai.yaml · agents/
- board.html · scripts/
- brief.md · scripts/
- cos.py · scripts/
- reload-after-compact.sh · scripts/
- test_cos_main_health.py · scripts/
- test_cos_slow_steps.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from TobiasBak/vault-public
- 0.587score
review-agent-history
TobiasBak
Review Pi or Codex histories for reusable knowledge or recurring patterns where agents needed correction or excess steering.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
theodore-kaczynski-nullifier
TobiasBak
Build self-explanatory, hardened repositories that agents can understand, change safely, verify and recover.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
system-specs
TobiasBak
Write, extend, or check requirement specs that let Tobias understand a system's design without reading code, for systems agents change several times a day.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
potato-approach
TobiasBak
Design, implement, refactor, or review agent-maintained code so the easiest change is the correct one.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
create-verification-skill
TobiasBak
Create a project-local verification skill and case-derived feature map that drive the real app.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
maintain-verification-skill
TobiasBak
Check an existing project verification skill and case-derived feature map against source and live behavior, then fix proven drift.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
disk-cleanup
TobiasBak
Free disk space on Tobias's Omarchy workstation without disrupting concurrent agents.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
review-test-quality
TobiasBak
Review tests for contract value and classify them keep, rewrite, delete, or uncertain.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
retro
TobiasBak
Review coding-agent sessions for concrete improvements to a repository's navigation, checks, tools, and instructions.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
benchmark-checklist
TobiasBak
Vet a performance measurement before reporting or acting on it, covering limiter, tuning, physical limits, errors, repeatability, relevance, and whether the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
audit-knowledge-consistency
TobiasBak
Find and fix duplicated or contradictory knowledge and broken links in this vault.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
hardware-deal-check
TobiasBak
Find and assess new or used development hardware deliverable in Denmark.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/TobiasBak/vault-public
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TobiasBak
- 0.587score
review-agent-history
TobiasBak
Review Pi or Codex histories for reusable knowledge or recurring patterns where agents needed correction or excess steering.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
theodore-kaczynski-nullifier
TobiasBak
Build self-explanatory, hardened repositories that agents can understand, change safely, verify and recover.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
system-specs
TobiasBak
Write, extend, or check requirement specs that let Tobias understand a system's design without reading code, for systems agents change several times a day.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
potato-approach
TobiasBak
Design, implement, refactor, or review agent-maintained code so the easiest change is the correct one.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
benchmark-checklist
TobiasBak
Vet a performance measurement before reporting or acting on it, covering limiter, tuning, physical limits, errors, repeatability, relevance, and whether the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
retro
TobiasBak
Review coding-agent sessions for concrete improvements to a repository's navigation, checks, tools, and instructions.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get chief-of-staff running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
chief-of-staff skill. Agent Mart. https://agentmart.dev/skills/tobiasbak-chief-of-staff (last updated 2026-10-24)