setup
Skill2 starsChanged 34 days agoMITView on GitHub
First-run setup for a personal portfolio built with this kit. Gathers name, role, contact, and anything already written, then points to the next step. Use for "help me build my portfolio", "set up my portfolio", "start a new portfolio", or the first time using this kit. Not for setting up code projects, repos, or other tools.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- anonymizerSkill
- content-strategistSkill
- find-my-voiceSkill
- portfolio-copywriterSkill
- quality-checkSkill
- refreshSkill
- skill-improverSkill
- story-adapterSkill
- voice-guardianSkill
- web-content-optimizerSkill
- website-expertSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 7 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Create a CLAUDE.md profile in the user's working folder that every other skill reads as its source of truth, then route the user to …
- Distinctive: line 23
If the full kit is installed, also mention: content-strategist helps pick what to add, and quality-check is the final gate before …
- Very specific: line 29
If CLAUDE.md is already a # Portfolio Profile, don't re-gather — say what's done, point to the first missing step (Voice Profile …
- Distinctive: line 31
Ask conversationally (use AskUserQuestion where it helps, but keep it light):
- Distinctive: line 39
Never block on optional fields.
- Distinctive: line 43
Ask: "Do you have anything I can work from?" and accept any of:
- Distinctive: line 50
If they have nothing, that's fine — say so and move on.
- Very specific: line 54
Create CLAUDE.md in the working folder (if it's already a # Portfolio Profile, only fill empty fields — never overwrite Voice Profile, …
- Very specific: line 84
Create or update .gitignore in the working folder so private kit files are never committed:
- Distinctive: line 97
If another skill started setup (e.g.
- Distinctive: line 102
Keep it short. This is config, not content.
- Very specific: line 103
Don't ask about anonymization (that's built into story-adapter and refresh).
- Very specific: line 104
Don't pick a voice from a menu here — find-my-voice does that properly by reading their writing.
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Setup
Get a new user started in under five minutes. Gather the minimum, store it, and hand off. Do NOT try to write content here — other skills do that.
Goal
Create a CLAUDE.md profile in the user's working folder that every other skill reads as its source of truth, then route the user to find-my-voice.
Process
1. Welcome + the map
Greet the user and lay out the whole path so they're never lost:
"Welcome — I'll get you from raw material to a live portfolio, no coding. The path: setup (a few basics, now) → find-my-voice (so it sounds like you) → story-adapter (turn your work into case studies and flag what you may not be able to share) → build and publish the page (just say "build my page") → refresh (keep it current). I'll point you to each next step."
If the full kit is installed, also mention: content-strategist helps pick what to add, and quality-check is the final gate before publishing.
2. Gather identity and contact
The portfolio needs its own folder. If this one already has a CLAUDE.md that isn't a portfolio profile, or looks like a code project, don't write anything here — ask them to open a new empty folder and run setup there, then stop.
If CLAUDE.md is already a # Portfolio Profile, don't re-gather — say what's done, point to the first missing step (Voice Profile placeholder → find-my-voice; no case-studies/ → story-adapter; otherwise "build my page" or refresh), and stop.
Ask conversationally (use AskUserQuestion where it helps, but keep it light):
- Name
- What they do / role
- LinkedIn URL
- GitHub or personal site (optional — skip if they don't have one; do not imply they should)
- What they're looking for next (optional — roles, clients, collaborators)
Never block on optional fields. If they volunteer that something must never be named — or that an employer or client is fine to name — record it under Privacy, not in Role.
3. Ask for raw material
Ask: "Do you have anything I can work from?" and accept any of:
- A résumé (file or paste)
- Things they've written (LinkedIn posts, a newsletter, talks, even emails) — flag these as voice samples for
find-my-voice - Rough notes on projects or wins
Save anything pasted to files so later sessions can use it — a later session can't see this chat: résumé → source/resume.md, writing → source/writing-samples.md, notes → source/notes.md. If they point to an existing file, record its path instead.
If they have nothing, that's fine — say so and move on.
4. Write the profile
Create CLAUDE.md in the working folder (if it's already a # Portfolio Profile, only fill empty fields — never overwrite Voice Profile, Hero, About, or Live site):
# Portfolio Profile
**Owner:** [name]
**Role:** [job title and employer only — no notes; it becomes the page title]
**Looking for:** [what's next, or "not specified"]
**Live site:** not yet
## Contact
- Email: [email]
- LinkedIn: [url or "none"]
- Site/GitHub: [url or "none"]
## Source Material
- Résumé: [file path or "none"]
- Writing samples: [file path or "none"]
- Notes: [file path or "none"]
## Privacy
- Never name: [real names the user asked to keep private — names only, no stand-in wording — or "none"]
- OK to name: [employers or clients the user said are fine to name, or "none"]
## Voice Profile
- (not captured yet — run find-my-voice)4b. Protect private files
Create or update .gitignore in the working folder so private kit files are never committed:
# portfolio-kit private files — never publish
ANONYMIZATION-LEDGER.md
CLAUDE.md
source/The ledger (created later by story-adapter) holds the real, unredacted originals; CLAUDE.md and source/ hold raw material. .gitignore only protects git — the page is built into a separate site/ folder, and only that folder ever goes online.
5. Hand off
If another skill started setup (e.g. find-my-voice), skip this and go straight back to that skill. Otherwise, point to the next step explicitly:
"Setup done. Next: run find-my-voice so everything sounds like you — it hands you on to the next step from there. When you've got 2–3 case studies, say "build my page"."
Rules
- Keep it short. This is config, not content.
- Don't ask about anonymization (that's built into
story-adapterandrefresh). - Don't pick a voice from a menu here —
find-my-voicedoes that properly by reading their writing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

