Skip to content
Back to search

clawchief

Turn your OpenClaw into a Chief of Staff

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/snarktank--clawchief/badge.svg)](/listings/snarktank--clawchief)

HTML

<a href="/listings/snarktank--clawchief"><img src="/api/listings/snarktank--clawchief/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

- `INSTALL-WITH-OPENCLAW.md` - `SETUP-GOG.md` - `INSTALL-CHECKLIST.md` - `CHANNELS.md` - `cron/jobs.template.json`

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 127 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # clawchief
  2. `clawchief` is a public OpenClaw starter kit for turning OpenClaw into a founder / chief-of-staff operating system.
  3. It is opinionated about the *architecture* of the workflow, but meant to be customized for your own people, programs, calendars, inboxes, trackers, and recurring routines.
  4. ## Launch post
  5. If you want the original public context for `clawchief`, here's the launch post from Ryan Carson's real-world rollout of the idea:
  6. - <https://x.com/ryancarson/status/2039786704731541903>
  7. ## What this repo gives you
  8. A portable operating model with:
  9. - a source-of-truth `clawchief/` layer for priorities, task state, meeting-note policy, and action policy
  10. - an orchestrator heartbeat
  11. - a canonical markdown task system with a separate completed-task archive
  12. - executive-assistant and business-development skills
  13. - cron templates with short DRY prompts
  14. - install docs and workspace templates
  15. ## Repo layout
  16. ### Source-of-truth files
  17. - `clawchief/priority-map.md`
  18. - `clawchief/auto-resolver.md`
  19. - `clawchief/meeting-notes.md`
  20. - `clawchief/tasks.md`
  21. - `clawchief/tasks-completed.md`
  22. ### Skills
  23. - `skills/executive-assistant`
  24. - `skills/business-development`
  25. - `skills/daily-task-manager`
  26. - `skills/daily-task-prep`
  27. ### Workspace templates
  28. - `workspace/HEARTBEAT.md`
  29. - `workspace/TOOLS.md`
  30. - `workspace/memory/meeting-notes-state.json`
  31. - `workspace/tasks/current.md` (deprecated pointer for older installs)
  32. ### Setup docs
  33. - `INSTALL-WITH-OPENCLAW.md`
  34. - `SETUP-GOG.md`
  35. - `INSTALL-CHECKLIST.md`
  36. - `CHANNELS.md`
  37. - `cron/jobs.template.json`
  38. ## Credit / inspiration
  39. A lot of the evolution of this setup was influenced by Pedro Franceschi's OpenClaw setup, which he explained during his conversation with Ashlee Vance on the Core Memory podcast:
  40. - Pedro Franceschi: <https://github.com/pedrofranceschi>
  41. - Podcast segment: <https://www.youtube.com/watch?v=9ZbbxSgrjhw&t=3847s>
  42. [![Watch the Core Memory segment with Pedro Franceschi](https://img.youtube.com/vi/9ZbbxSgrjhw/hqdefault.jpg)](https://www.youtube.com/watch?v=9ZbbxSgrjhw&t=3847s)
  43. In particular, his setup helped inspire the direction of:
  44. - the priority map
  45. - the auto-resolver layer
  46. - the ingestion pipeline mindset for turning passive context into active operational state
  47. ## The design pattern
  48. The system works best when you separate:
  49. 1. *prioritization* -> `clawchief/priority-map.md`
  50. 2. *resolution policy* -> `clawchief/auto-resolver.md`
  51. 3. *meeting-note ingestion policy* -> `clawchief/meeting-notes.md`
  52. 4. *live task state* -> `clawchief/tasks.md`
  53. 5. *archive state* -> `clawchief/tasks-completed.md`
  54. 6. *local environment details* -> `workspace/TOOLS.md`
  55. 7. *recurring orchestration* -> `workspace/HEARTBEAT.md` + cron jobs
  56. That separation is the main thing this repo is trying to teach.
  57. ## Install order
  58. 1. Read `INSTALL-WITH-OPENCLAW.md`
  59. 2. Complete `SETUP-GOG.md`
  60. 3. Copy the skills into `~/.openclaw/skills/`
  61. 4. Copy `clawchief/` and `workspace/` templates into `~/.openclaw/workspace/`
  62. 5. Replace placeholders and customize `workspace/TOOLS.md`
  63. 6. Create cron jobs from `cron/jobs.template.json`
  64. 7. Run `INSTALL-CHECKLIST.md`
  65. ## Good customization targets
  66. Customize these first:
  67. - `workspace/TOOLS.md`
  68. - `clawchief/priority-map.md`
  69. - `clawchief/tasks.md`
  70. - `skills/business-development/resources/partners.md`
  71. - `cron/jobs.template.json`
  72. ## Core operating lessons baked into this repo
  73. - use Gmail *message-level* search, not thread-only search
  74. - check *all relevant calendars* before booking
  75. - keep one canonical live task file
  76. - archive prior-day completions into a separate file
  77. - update the real source of truth in the same turn when you act
  78. - keep cron prompts short and let skills hold workflow logic
  79. - use a policy layer for prioritization and a separate policy layer for auto-resolution
  80. - treat meeting notes as a live signal source, not passive documents
  81. ## Private local files you probably still want
  82. You may still want your own private workspace files such as:
  83. - `AGENTS.md`
  84. - `SOUL.md`
  85. - `USER.md`
  86. - `IDENTITY.md`
  87. - `MEMORY.md`
  88. - `memory/`
  89. Those are intentionally not part of this public repo.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.