workspace-setup
/workspace-setup
Konfiguruje projekt Claude.ai lub folder Claude Code dla jednej pracy: zbiera istniejące materiały, pyta raz i pokazuje szkice przed zapisem.
- Autor
- alex20-create ↗
- Repozytorium
- workspace-setup-skill ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 07.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 33
- Skrypty
- 2
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 07.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 2 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: evals/asks-once-before-drafting/place-files.sh, evals/existing-claude-md-kept/place-files.sh
Co robi i kiedy
Konfiguruje projekt Claude.ai lub folder Claude Code dla jednej pracy: zbiera istniejące materiały, pyta raz i pokazuje szkice przed zapisem.
Oryginalny opis (EN)
Sets up a workspace where Claude can work well on one piece of work: a claude.ai Project (custom instructions plus context documents), a Claude Code project folder (CLAUDE.md and whatever else the folder needs), or both. It gathers what already exists about the work before asking anything, asks every decision question in one round, shows the drafts before writing, links to the sources instead of copying them, and marks anything without a source as PENDING. Use it whenever the user wants to prepare a place for Claude to work on something, even if they only say they are starting something new: "
Jak działa
- The rule underneath everything
- Local map first
- 1. Detect the target
- 2. Gather what already exists
- 3. Ask every decision question in one round
- 4. Draft and show
- 5. Offer a test
- 6. Deliver
- What this skill does not do
Podgląd SKILL.md
---
name: workspace-setup
description: 'Sets up a workspace where Claude can work well on one piece of work: a claude.ai Project (custom instructions plus context documents), a Claude Code project folder (CLAUDE.md and whatever else the folder needs), or both. It gathers what already exists about the work before asking anything, asks every decision question in one round, shows the drafts before writing, links to the sources instead of copying them, and marks anything without a source as PENDING. Use it whenever the user wants to prepare a place for Claude to work on something, even if they only say they are starting something new: "set up a workspace", "create a project", "prepare the project folder", "nuevo proyecto en claude.ai", "monta la carpeta del proyecto", "prepara el espacio de trabajo". Not for picking a CLAUDE.md template on its own, improving an existing CLAUDE.md, or installing plugins and connectors.'
---
# Workspace Setup
Builds the place where Claude will work on one piece of work, so that every new
conversation starts already knowing what the work is, where its facts live and
what Claude may do on its own. There are two kinds of workspace:
- **A claude.ai Project**: custom instructions plus context documents uploaded
to the Project.
- **A Claude Code project folder**: a `CLAUDE.md` and whatever else the folder
needs for Claude to work well in it.
Some work needs both. The skill gathers, asks once, drafts, tests if the user
wants and delivers. It does not replace the tools that already own part of the
job: a CLAUDE.md template picker writes the CLAUDE.md, a note-sync skill keeps a
notes vault, an automation recommender proposes hooks and integrations. Where
those exist, this skill calls them as steps instead of redoing their work.
## The rule underneath everything
Every fact lives in one place. A workspace points to its sources (a project
manager, a notes vault, a repository, a design system); it does not copy them.
A copy goes stale the day its source changes, and from then on Claude acts on
the wrong version without knowing it. When a copy cannot be avoided (the
Project cannot reach the source, for instance), it is marked as generated, with
its source and date, and nobody edits it by hand: it is regenerated from the
source.
Two more rules follow from the same idea:
- **Nothing invented.** A fact with no source goes into the draft as
`PENDING: <what is missing>` (or the same word in the drafts' language), never
as a plausible guess. A wrong fact in standing instructions misleads every
future conversation, and nobody rereads instructions looking for it.
- **Nothing persisted without asking.** No file, page, note or repository
change before the user has seen the draft and said yes. Reading is free;
writing waits.
Reply in the language the user writes in. The drafts are written in the
language the user chooses in step 3, which can differ per target (a repository's
rules may require English while the Project instructions do not).
## Local map first
The skill is generic; the user's setup is not. Before step 1, look for a local
map that names the concrete tools and places. It can be a section titled
`workspace-setup local map` in the user's own instructions (a `CLAUDE.md` in
Claude Code, read from disk), a section titled `Local map for this install` in
this file (added when the skill was packaged for one person's claude.ai
account), or the custom instructions of the claude.ai Project being built or
revised, if they name these things. Where several exist, the most specific wins line by line;
`references/local-map.md` gives the order. The instructions of the Project this
session runs in govern how you behave here; they are not the content of the
workspace you are building, unless that workspace is the same Project.
Names in a map are hints, not exact strings: a session may list a skill with a
plugin prefix (`anthropic-skills:skill-improver` for `skill-improver`). Match by
the last part of the name, or by the description when the name differs.
A map does not replace checking: confirm that what it names can be reached in
this session, and say in the step 2 inventory what could not.
A map can name: the CLAUDE.md template picker and where its template collection
lives; the notes vault and where project notes go; the project manager where
work is tracked (a Notion database, for example); the automation recommender and
the skill used to dry-run instructions; the house order of sections in a
CLAUDE.md; language and style rules for drafts; and existing workspaces that
show what works. Whatever the map says overrides the defaults in this skill.
With no map, discover: list the connectors, skills and file access this session
has (where no tool lists connectors, infer them from the names of the tools the
session offers), and note which of the roles above each one could fill. Use what you find,
say what you assumed, and at the end (step 6) offer to write a map so the next
run does not have to discover again. `references/local-map.md` has the format
and the discovery checklist.
## 1. Detect the target
Decide whether the user wants a claude.ai Project, a Claude Code folder, or
both, from what they said and from where you are running:
- "Project in claude.ai", "project instructions", "knowledge" point to a
Project; "folder", "repo", "CLAUDE.md" point to Claude Code.
- In claude.ai with no file access, a Claude Code folder can still be the
target, but it is delivered as text for the user to save.
- In Claude Code, both targets can be delivered; the Project still has to be
created by hand.
If it is still unclear, do not stop to ask: gather for both, and make the target
the first question of the batch in step 3.
## 2. Gather what already exists
Before asking anything, read what already exists about this work, so that the
questions in step 3 arrive with proposed answers instead of blank fields. Look
in every source the map or discovery turned up:
- the project manager: the item or page for this work, its status, its links;
- the notes vault: a project note, decisions, open questions;
- the repository or folder: README, any existing `CLAUDE.md` or `AGENTS.md`,
manifest files (`package.json`, `pyproject.toml` and the like), the layout;
- claude.ai: artifacts, an existing Project's instructions (where the session
can reach them), a design system;
- handoff, memory or session-log files the setup keeps, checked against the
live state (they go stale);
- this conversation: what the user has already said;
- drafts that already exist (in this conversation, in files, or the
instructions of an existing Project the user pastes). They are the starting
point: the questions in step 3 cover only what they leave open, and the drafts
in step 4 are revisions of them, not new text.
Only read. Then write a short inventory and show it with the questions: each
source, what kind of data it holds (tasks, decisions, specs, design tokens,
code), and any contradiction (two places, or two files within one source,
claiming different things about the same fact). The inventory is what step 3
asks about and what the drafts link to. If a source the map names or discovery found cannot be reached in this session (an
existing claude.ai Project's instructions, often), say so in the inventory; do
not fill the gap from memory. Say also what would give access (linking the chat
to the computer, connecting a folder, attaching the file, adding the
repository) and ask for it in the step 3 batch; do not request access on your
own.
## 3. Ask every decision question in one round
Ask once, with everything, because a drip of questions costs the user more than
one well-prepared batch. `references/decision-questions.md` has the template.
The batch covers:
1. **Target**, only if step 1 left it open.
2. **Purpose**: what this workspace is for, and what it is not for. For a
claude.ai Project, also its name and one-line description. Also whether a
workspace for this work already exists: claude.ai Projects cannot be listed
from a session, so ask, and if one exists, ask the user to paste its
instructions.
3. **Source of truth per kind of data**: for each kind found in the inventory,
which source wins. The "where each thing lives" part of the drafts is built
from this answer. For a claude.ai Project, also how the Project reaches each
source: a connector or synced integration (stays current), a link it can
open, the user's computer when the chat is linked to it (only in chats that
have the link), or a generated copy uploaded to it.
4. **Permissions, in three tiers**: what Claude does without asking, what it
does after a yes, and what it does only when asked. For a Claude Code
folder, also whether to enforce part of them in the folder's permission
settings, and whether the `CLAUDE.md` is committed or kept local.
5. **Routines**: phrases that start a fixed routine ("open the session", "close
the day") and what each one runs.
6. **Language and style**: language of the drafts and of the replies, tone,
formats to use or avoid.
For each question, propose an answer drawn from the inventory or the map and
say where it came from; the user confirms or corrects. Where nothing supports a
proposal, leave the answer open instead of guessing. If the user or the local map already
answered something in their request, show it as settled rather than asking
again. A structured question tool may be used if it fits the whole batch in one
round; if it limits the number of questions, ask in a single message instead.
## 4. Draft and show
Write every deliverable in full and show it before writing anything anywhere:
- **claude.ai Project**: follow `references/claude-ai-project.md`. The
instructions, plus the context documents (usually one: a map of links to the
sources).
- **Claude Code folder**: follow `references/claude-code-folder.md`. The
`CLAUDE.md` comes from the template picker the map names or discovery
found: hand it the target
folder and the answers from step 3, and let it choose and fill the template;
template choice is its job, not this skill's. Without a template picker, write
the CLAUDE.md directly, in the house order of sections from the map or the
user's own instructions, or in the
plain order the reference gives if there is no map.
Mark every gap `PENDING` and every unavoidable copy with its generated header.
List the PENDING items under the drafts, so the user sees at a glance what still
needs a source. Revise until the user is satisfied, showing each revision again
in full or as a clear diff.
## 5. Offer a test
Offer to dry-run the drafts with a fresh agent that has no conversation
context: it gets only the drafts and a realistic first request ("pick up where
we left off", "add the export feature"), and reports every doubt, contradiction
or missing fact it runs into. The author cannot see these gaps, because the
author already knows the context the drafts forgot to state.
Use the instruction-testing skill the map names (a skill improver with a
clean-subagent dry run, for example). If that skill accepts only skills as
targets, follow its protocol directly: launch one subagent with the drafts and
the request, no other context, and ask for its doubts. Before launching, state
the estimated cost, taking the reference figure from the instruction-testing
skill if it gives one and saying whose figure it is, and launch only on a yes.
Whether a clean test is possible depends on the session having a subagent tool,
not on where it runs: where there is none, say so and offer the test for a
session that has one. If the drafts were already tested with a fresh agent in
this conversation, say so and offer a re-test only for what changed since.
Fix what the test finds that is real, show the changes, and move on.
## 6. Deliver
**claude.ai Project.** This skill cannot create a Project; say so plainly.
Deliver:
- the instructions as one block, ready to paste;
- each context document as a file to upload (or a block to save as one);
- the steps from `references/claude-ai-project.md` to create the Project, paste
the instructions and upload the documents.
**Claude Code folder.** Write the files only after an explicit yes to the shown
drafts, list every path written, and do not commit unless asked.
Then offer, one at a time and only where the map or discovery found the tool:
- the note-sync skill, to create or update this work's note in the vault, if
the vault's conventions give this kind of work a note (the map may say which
kinds do);
- the automation recommender, when the folder is a code repository;
- writing a local map, if this run had to discover its tools.
## What this skill does not do
- Create a claude.ai Project or upload files to one.
- Choose or adapt CLAUDE.md templates: the template picker does.
- Install plugins, connectors, hooks or MCP servers: the automation recommender
proposes those, and the user decides.
- Edit the sources it links to. If a source is wrong, the skill says so and the
user fixes it there. The one exception: when the user takes a decision during
this run that changes a source, show the exact change and write it only on an
explicit yes.
Pliki w paczce (33)
- SKILL.md 13 KB
- evals/asks-once-before-drafting/case.yaml 1 KB
- evals/asks-once-before-drafting/place-files.sh 1 KB
- evals/asks-once-before-drafting/prompt.md 1 KB
- evals/asks-once-before-drafting/files/README.md 1 KB
- evals/asks-once-before-drafting/files/package.json 1 KB
- evals/asks-once-before-drafting/graders/01-reads-files-before-asking.md 1 KB
- evals/asks-once-before-drafting/graders/02-one-batch-of-questions.md 1 KB
- evals/asks-once-before-drafting/graders/03-batch-covers-the-topics.md 1 KB
- evals/asks-once-before-drafting/graders/04-proposals-cite-the-files.md 1 KB
- evals/asks-once-before-drafting/graders/05-writes-no-file.md 1 KB
- evals/asks-once-before-drafting/graders/06-replies-in-spanish.md 1 KB
- evals/claude-ai-delivery-with-pending/case.yaml 1 KB
- evals/claude-ai-delivery-with-pending/prompt.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/01-no-repeated-questions.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/02-instructions-in-one-block.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/03-context-doc-is-a-map.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/04-release-schedule-pending.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/05-cannot-create-project.md 1 KB
- evals/claude-ai-delivery-with-pending/graders/06-three-permission-tiers.md 1 KB
- evals/existing-claude-md-kept/case.yaml 1 KB
- evals/existing-claude-md-kept/place-files.sh 1 KB
- evals/existing-claude-md-kept/prompt.md 1 KB
- evals/existing-claude-md-kept/files/CLAUDE.md 1 KB
- evals/existing-claude-md-kept/files/README.md 1 KB
- evals/existing-claude-md-kept/graders/01-reads-existing-claude-md.md 1 KB
- evals/existing-claude-md-kept/graders/02-shows-draft-first.md 1 KB
- evals/existing-claude-md-kept/graders/03-existing-file-unchanged.md 1 KB
- evals/existing-claude-md-kept/graders/04-keeps-user-content.md 1 KB
- references/claude-ai-project.md 5 KB
- references/claude-code-folder.md 4 KB
- references/decision-questions.md 5 KB
- references/local-map.md 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · alex20-create/workspace-setup-skill | 100 | MIT |
| mikeleg/skills | 100 | MIT |
| madappgang/magus | 100 | MIT |
| danielrosehill/claude-image-production-plugin | 100 | MIT |
| evolvehq/docflow | 100 | MIT |
| seziCZ/daybook | 100 | Apache-2.0 |
| byenzyme/margins | 96 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki 4ee75bbacaf4 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100setup-workspace
Tworzy folder konfiguracji Claude z szablonów albo porządkuje istniejące foldery planem odwracalnych kroków, każdy za zgodą właściciela. - 100new-project
Zakłada projekt z plikami CLAUDE.md, STATE.md i DECISIONS.md, żeby stan prac i decyzje były zapisane między sesjami. - 100project-start
Zakłada folder projektu w katalogu Projects z plikiem CLAUDE.md, żeby sesje dzieliły wskazówki, decyzje, pamięć i pliki. - 95onboard
Prowadzi przez konfigurację przestrzeni roboczej AI w Cowork z plikami AGENTS.md, CLAUDE.md i folderami pasującymi do pracy. - 100second-brain-project
Zakłada lub aktualizuje projekt w vaulcie: czteroetapowy potok folderów, projektowy CLAUDE.md z jednym celem i linki do stron pojęć, od których projekt zależy. - 90mb-help
Odpowiada na pytania o Main Branch i Claude Code: folder business, CLI, skille, konfigurację, błędy i dalsze kroki pracy.