Updated 3w ago
by chacosoldier
compabob
A customizable Claude Code setup for knowledge workers: agents, safety hooks, skills, memory, and an Obsidian knowledge base. Clone, run setup, make it yours.
34 GitHub stars (34)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 19 skills (19 skills found in its SKILL.md files)
- 6 forks (6 forks)
- 3w ago last update (Last updated 3w ago)
Install
Skills CLI
npx skills add chacosoldier/compabob
Asks which skills and agents to install. Just one: npx skills add chacosoldier/compabob --skill add-agent — add -g for every project.
Claude Code
git clone https://github.com/chacosoldier/compabobcp -r "compabob/.claude/skills/add-agent" ~/.claude/skills/
Copies the add-agent skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add chacosoldier/compabob
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
add-agent
Scaffold a new specialized agent for this assistant. Use for "/add-agent", "create a new agent", or "I want an agent that does X".
.claude/skills/add-agent/SKILL.md on GitHub (opens in a new tab) -
build-list
Build a ranked, CRM-deduped outbound prospect list from an ICP description. Use for "/build-list", "find me leads matching X", "build a prospect list for Y", or when the user wants a scored outbound list. Orchestrates discovery + the lead-pipeline module + enrichment.
.claude/skills/build-list/SKILL.md on GitHub (opens in a new tab) -
chart-tufte
Post-build grader for a rendered quantitative chart, grounded in Edward Tufte's The Visual Display of Quantitative Information: strips chartjunk, checks the lie factor, picks the right genre, and names failures from the VDQI catalogue. Not a chart builder. Runs as the last step of /visual-explainer when the page has a chart, or on demand ("grade this chart", "is this chart honest").
.claude/skills/chart-tufte/SKILL.md on GitHub (opens in a new tab) -
council
Advisor panel plus a mandatory dissenter for a high-stakes decision. Runs strategy-advisor and first-principles in parallel with a third advisor assigned to argue against the leaning option, then writes a recommendation that must answer each dissent point. Use on 'should I X' or 'deciding between Y and Z' when the call is hard to reverse (a job, a hire, a big spend, a strategy bet) and the user w…
.claude/skills/council/SKILL.md on GitHub (opens in a new tab) -
document-export
Create a PDF, Excel (.xlsx), or Word (.docx) file from content. Use for "/document-export", "make a PDF", "export to Excel", "put this in a spreadsheet", "save this as a Word doc", or when the user needs a shareable office document rather than a note or a raw HTML page.
.claude/skills/document-export/SKILL.md on GitHub (opens in a new tab) -
handover
Write a handover note before ending a working session so the next session picks up where this one stopped. Use for /handover, "wrap up", or "write a handover before I stop". It saves state; extracting lessons learned is /reflect.
.claude/skills/handover/SKILL.md on GitHub (opens in a new tab) -
index-memory
Build or refresh the local memory-search index over memory/ and vault/, so retrieval finds notes by relevance. Use for "/index-memory", "reindex my memory", "rebuild the search index".
.claude/skills/index-memory/SKILL.md on GitHub (opens in a new tab) -
log-decision
Record a strategic decision with its reasoning, the alternatives considered, and a date to review the outcome. Use for "/log-decision", "log this decision", or after a significant choice is made.
.claude/skills/log-decision/SKILL.md on GitHub (opens in a new tab) -
mcp-debug
MCP server health check, tool tracing, and audit. Use when an MCP tool fails silently or errors, to check server status, or to audit the configured servers: /mcp-debug [status|trace|audit]. MCP servers only; the health of the whole setup is /system-audit.
.claude/skills/mcp-debug/SKILL.md on GitHub (opens in a new tab) -
meeting-prep
Prepare for an upcoming meeting: who is attending, the history, open items, and the decision the meeting needs to reach. Use for /meeting-prep, "prep me for my meeting with X", or "what do I need to know before the call with Y". To capture what happened after the meeting, use /post-call.
.claude/skills/meeting-prep/SKILL.md on GitHub (opens in a new tab) -
memory-debt
Review and apply memory updates that /reflect proposed but nobody wrote yet (the unchecked items under Suggested Memory Updates in vault/Daily/). Use /memory-debt to see what is pending, /memory-debt apply to resolve it item by item. It does not do the reflecting; that is /reflect.
.claude/skills/memory-debt/SKILL.md on GitHub (opens in a new tab) -
merge-contacts
Merge the user's contact exports (Google Takeout, LinkedIn export, vault People notes) into one local CRM. Use for "/merge-contacts", "build my CRM", "dedup my contacts", or when another workflow needs a clean contacts source of truth.
.claude/skills/merge-contacts/SKILL.md on GitHub (opens in a new tab) -
morning-brief
Start-of-day briefing: priorities, what is due, what is owed, today's meetings, and anything overdue. Use for /morning-brief, "brief me", or at the start of the first session of the day. For the full list of open tasks, use /tasks.
.claude/skills/morning-brief/SKILL.md on GitHub (opens in a new tab) -
post-call
Capture a debrief right after a meeting or call: what was decided, what was committed, and what changed. Use for "/post-call", "debrief the call with X", or "I just got off a call with Y".
.claude/skills/post-call/SKILL.md on GitHub (opens in a new tab) -
reflect
End-of-session reflection: what was learned, what should change, and proposed memory updates, recorded as unchecked items in today's daily note. Use for /reflect, "what did we learn", or at the close of a substantial work session. It proposes; /memory-debt applies what is still open later. To save where the work stands for next time, use /handover.
.claude/skills/reflect/SKILL.md on GitHub (opens in a new tab) -
system-audit
Health check of the assistant's own setup: agents, hooks, skills, settings, memory, and vault structure. Use for /system-audit, "is everything wired up", or after changing the configuration. It reports MCP servers only as connected or failing; to debug one, use /mcp-debug.
.claude/skills/system-audit/SKILL.md on GitHub (opens in a new tab) -
tasks
One aggregated view of open tasks from across the vault and the brief queue. Use for /tasks, "what's on my plate", "what are my open tasks", "what's overdue", or "/tasks done [id]" to complete one. For the start-of-day briefing with meetings and priorities, use /morning-brief.
.claude/skills/tasks/SKILL.md on GitHub (opens in a new tab) -
visual-explainer
Generate a single self-contained HTML page that visually explains a system, a plan, a comparison, or a set of data. Use for "/visual-explainer", "make a diagram of", "show this visually", or when a complex table or architecture would land better as a styled page.
.claude/skills/visual-explainer/SKILL.md on GitHub (opens in a new tab) -
weekly-review
End-of-week review: what got done, what slipped, decisions made, and next week's top 3 priorities. Use for "/weekly-review", "end-of-week review", "what happened this week", or on the last working day of the week.
.claude/skills/weekly-review/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.