Skip to content
Skills Library
AI & agents · Tool integration

setup

/setup

Use when the user wants to install, initialise or configure waymark memory for the first time (/waymark:setup), or says waymark is "not set up". Creates the memory layer and optionally replaces Claude's built-in auto-memory.

Repository
waymark ↗
Licence
MIT
Last repository change
29.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 29.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when the user wants to install, initialise or configure waymark memory for the first time (/waymark:setup), or says waymark is "not set up". Creates the memory layer and optionally replaces Claude's built-in auto-memory.

Triggers from the description

not set up
Original author description

Use when the user wants to install, initialise or configure waymark memory for the first time (/waymark:setup), or says waymark is "not set up". Creates the memory layer and optionally replaces Claude's built-in auto-memory.

How it works

  1. 1. Gather
  2. 2. Play back
  3. 3. Init
  4. 4. Auto-memory (only if replace = yes)
  5. 5. Finish
Original SKILL.md headings · 38 lines, 513 words
SKILL.md preview
---
name: setup
description: Use when the user wants to install, initialise or configure waymark memory for the first time (/waymark:setup), or says waymark is "not set up". Creates the memory layer and optionally replaces Claude's built-in auto-memory.
---

# waymark setup

Interactive, one question group at a time. Nothing outside the layer changes without an explicit yes. Never run `git push` or add a git remote.

## 1. Gather
Ask for each; show the default and accept it on a bare Enter.
1. Owner name (default `git config --global user.name`) and email (default `git config --global user.email`).
2. Layer path (default `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/waymark`). It must not be inside a git repo and must be absent or empty.
3. Replace Claude's built-in auto-memory with waymark? yes/no (default no).
4. `repo_roots` (optional): comma-separated parent folders of the owner's repos, used to find stray docs.
5. Only if `git config --global commit.gpgsign` is `true`: sign layer commits? yes/no. Signing needs a key available non-interactively; if unsure, recommend no for the layer.

Warn if the email domain is a public provider (gmail.com outlook.com hotmail.com live.com icloud.com yahoo.com proton.me protonmail.com): the secrets scan only flags other addresses at the owner's own domain, so other private addresses on a public domain will not be caught. Offer `--email-allowlist` for addresses that are fine to store.

## 2. Play back
Show a table: owner name, email, layer path, replace auto-memory, repo_roots, sign layer. Also list what the yes will do: create the layer (git repo of markdown), copy `bin/` into `<layer>/bin/`, install the pre-commit hook, write `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/waymark.conf`, make the first commit. Ask: "Proceed?" Stop on anything but yes.

## 3. Init
On yes run (omit flags the user left empty):

```
"${CLAUDE_PLUGIN_ROOT}/bin/waymark" init --owner-name "<name>" --owner-email "<email>" --root "<layer>" --repo-roots "<a,b>" --replace-auto-memory yes|no --sign-layer yes|no --email-allowlist "<a,b>" --plugin-root "${CLAUDE_PLUGIN_ROOT}"
```

`init` never touches Claude settings. If it fails, show its message and stop; do not retry with `--force`-style workarounds or delete anything. One exception: if it says `waymark.conf` already points to an existing layer, ask the user whether to point waymark at the new layer instead (the old one stays on disk), and rerun with `--force` only on an explicit yes.

## 4. Auto-memory (only if replace = yes)
The setting is `autoMemoryEnabled` (boolean) in the user settings file `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/settings.json` (see `docs/hook-contract.md`, "Auto-memory setting"; env alternative `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1`).
1. Read the file. Prior value = the current `autoMemoryEnabled` (`true`/`false`) or empty if the key is absent (file missing counts as absent).
2. Record it: edit `<layer>/layer.conf`, setting the line `prior_auto_memory=<value>` (and `replace_auto_memory=yes` if init left it `no`). Commit with `"${CLAUDE_PLUGIN_ROOT}/bin/waymark" commit "memory: record prior auto-memory setting"`.
3. Show the exact one-key change: `"autoMemoryEnabled": false` added to or updated in `settings.json`, nothing else. Ask for approval.
4. On yes, apply it with the Edit tool on that one key. Never rewrite the whole file; preserve all other keys and formatting. If the file does not exist, say so and ask before creating it with just that key.
5. List existing files under `~/.claude/projects/*/memory/` (names and sizes). Do not migrate, move or delete them; tell the user they can ask to have items recorded with `/waymark:remember`.

## 5. Finish
Print the verification table `init` produced. Tell the user: start a fresh session (memory is injected at session start), and run `/waymark:uninstall` to undo.

Versions

RepositoryScoreLicence
This page · MohammedOmar3/waymark100MIT
HwangSlater/harness-fit100MIT
nesquikm/dev-process-toolkit100MIT
userKael/rastro100MIT
als-apg/osprey100BSD-3-Clause
dedujeong/gemba100Apache-2.0
eigenwise/eigenwise-toolshed100MIT
awrshift/agent-memory-kit100MIT
lifecycle-innovations-limited/claude-ops100MIT

Database snapshot: 13.11.2026 · package version 19c1c16b49f3 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 86uninstall
    Use when the user wants to remove waymark or undo its setup (/waymark:uninstall). Restores changed settings, removes the pointer file, and deletes the memory layer only on explicit confirmation.
  • 90review
    Use for periodic waymark upkeep (/waymark:review), or when the user asks to review, clean up or prune memory. Distils gotchas into playbook rules, flags expired docs and revisit conditions, checks injection size and stats.
  • 100setup-project
    When setting up agentskel on a new project that does not yet have .memory/ or .agents/. Use when the user says "set up agentskel", "install agentskel", or "add agent memory to this project".
  • 84audit
    Audit the Claude Code instruction/memory layer covering CLAUDE.md, a root AGENTS.md, CLAUDE.local.md, .claude/rules/, and auto-memory against a codified checklist derived from official Claude Code documentation. Use when: 'audit CLAUDE.md', 'audit AGENTS.md', 'memory health',…
  • 100auto-memory
    This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic…
  • 100cc-stack-setup
    Deploy or audit the full 5-layer Claude Code stack (CLAUDE.md + skills + hooks + agents + memory) in a repository. Use this skill whenever the user runs /cc-setup, asks to "set up Claude Code on this repo", "configure a new repo for Claude", "audit my Claude Code setup",…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.