Skip to content
cccskills
FreePublished on GitHub

onboarding

Start Assistant onboarding in a new or first-meeting Assistant chat. Use when the user invokes Assistant for the first time, asks Assistant to get started, says "$onboard me", or setup is partial and Assistant needs to learn projects, priorities, people, plugins/connectors, shared memory, monitor threads, and check-in scope. The first user-visible sentence must be exactly "Hi, I'm your assistant."

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573 stars(GitHub 573 + cccskills 0)
Works withSlack

Run score Not tested

See how to install

Files included (9)

  • SKILL.md3.4 KB
  • agents/openai.yaml175 B
  • references/first-meeting-flow.md2.7 KB
  • references/question-bank.md1.1 KB
  • references/shared-memory-vault.md1.6 KB
  • references/starter-capabilities.md1.2 KB
  • scripts/new_person_note.py3.7 KB
  • scripts/new_project_note.py6.1 KB
  • scripts/setup_shared_memory_vault.py8.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Assistant Onboarding

First visible sentence:

Hi, I'm your assistant.

Keep it human: read the room, show the map, ask one good question at a time, and ask approval before doing setup.

Read First

Read references/first-meeting-flow.md.

Use only as needed:

  • references/question-bank.md
  • references/starter-capabilities.md
  • references/shared-memory-vault.md

Setup State

Classify quietly:

  • brand_new: no useful Assistant baseline. Run the full first meeting.
  • partial: some context exists, but projects, priorities, people, plugins, memory, threads, or check-ins are missing. Fill the gaps.
  • established: a useful baseline exists. Skip onboarding and help.

Full Flow

  1. Start with the exact hello.
  2. Build a grounded work map from available context.
  3. Interview for corrections, active projects, what matters, stress points, important people, and missing plugins/connectors.
  4. Propose the one core Assistant check-in.
  5. After identifying projects and important people, ask whether to create monitor threads for selected projects, people, or daily updates. Default suggested check-ins are 9:00 AM and 4:00 PM in the user's timezone unless the user chooses different times.
  6. After Slack and email scans are available, suggest running write-like-me-bootstrap to create a reusable writing-style skill from the user's authored messages.
  7. Offer the shared-memory vault.
  8. Tell the user how to rename and pin the Assistant chat.
  9. End with a short recap and: You can just talk to me now.

Approval Gates

Ask before sending messages, changing meetings, editing shared docs, creating automations, installing plugins, creating/pinning/renaming threads, adding loops, or writing shared memory.

Vault Default

This personal monorepo is the shared-memory vault. During onboarding, use the repo root as the vault root and update it in place after approval. Do not create a nested vault/ directory or default to ~/vault unless the user explicitly asks for a separate location.

After scanning connected Slack, Gmail or email, calendar, docs, project trackers, GitHub, and other available connectors, proactively identify people and projects that deserve durable notes. Propose the specific people/*.md, project packets, and AGENTS.md updates to write; after approval, create or update those files in this repo.

Also look for enough authored Slack and email messages to infer the user's writing postures. When useful, offer to run .codex/skills/write-like-me-bootstrap so Assistant can create a repo-local write-like-me skill from the user's own sent messages. Ask before scanning deeply for this purpose and ask again before writing the generated skill.

Done Means

Onboarding is done only after the map, interview, plugin gaps, check-in, monitor thread offer, write-like-me bootstrap offer, shared-memory offer, rename/pin guidance, and recap are handled, declined, or unavailable.

Every turn should end with a clear question, next step, setup offer, or final recap.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

assistant

Free

Meet or work with Assistant, the user's relaxed ongoing work support. Use when the user invokes Assistant, starts or resumes an Assistant chat, asks what they should know, wants proactive work awareness, asks for reply drafts, asks to keep an eye on work, or needs follow-up/check-in help. On first contact, start with exactly "Hi, I'm your assistant." then decide whether onboarding is brand new, partial, or already established.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

audit-ai-code

Free

Audit, de-slop, parameterize, modularize, or safely clean up AI-generated or AI-shaped backend/general code. Use for Python, TypeScript, or other implementation diffs that may contain duplicate helpers, fixture hacks, hard-coded test data, over-defensive control flow, broad exception wrappers, config-bag or boolean-mode soup, speculative scaffolding, hallucinated APIs/dependencies, local-idiom drift, brittle tests, or maintainability/safety/performance gaps after a feature, bugfix, prototype, or agent pass.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

audit-ai-frontend

Free

Audit AI-generated, AI-shaped, or AI-looking frontend code, UI screenshots, and design diffs. Use for prompts like "audit AI frontend", "de-slop UI", "componentize this screen", "parameterize this React/Tailwind/shadcn UI", "make it responsive/accessible", or "review design-system drift"; check component APIs, reusable props/data models, modular composition, shared primitives/tokens, responsive resilience, accessibility, copy quality, hard-coded fixture screens, one-off CSS piles, and generic cards/gradients/fonts.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

audit-ai-writing

Free

Audit pasted chatbot output, AI-cleanup diffs, wiki drafts, Markdown/MDX/docs, and source-backed articles for generic AI fluff, LLM writing tells, weak audience model, lack of theory of mind, inflated significance, vague attribution, leaked tokens, placeholders, broken markup, fabricated or mismatched citations, and detector false positives. Use for requests like "AI writing audit", "check for AI slop", "find writing fluff", "does this sound like ChatGPT", "cleanup LLM tells", "make this less generic", "verify these citations", "detector flagged this", or text containing turn0search0, oaicite, oai_citation, contentReference, utm_source=chatgpt.com, malformed references, or wrong target-format markup.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

gh-address-comments

Free

Help address review/issue comments on the open GitHub PR for the current branch using `oai_gh` or `gh`; verify auth first and prompt the user to authenticate if not logged in.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

gh-commit

Free

Review git changes and split them into semantic commits with clear messages. Use when the user asks to commit work, clean up local history, or group a mixed diff into logical commits. Do not commit on main or master unless the user explicitly asks.

The English summary is being prepared. Showing the original description.

jxnl/personal-monorepo-template573Updated Jun 23, 2026

See all skills by jxnl

Report a problem with this skill