anson
v1.0.0Bootstrap and personalize an AI assistant with a rich, bespoke identity, user profile, and soul. Use this skill whenever a user wants to set up, personalize,...
⭐ 1· 27·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill declares no binaries, no env vars, and no installs — and its instructions are focused on creating and updating identity/user/soul documents and generating maker skills via an existing 'skill-creator'. Asking for the skill-creator and reading/writing workspace files is coherent with bootstrapping an assistant.
Instruction Scope
Instructions restrict activity to the workspace root (explicitly avoid searching the rest of the machine) — good. The skill reads project files (IDENTITY.md, USER.md, SOUL.md, AGENTS.md/CLAUDE.md, README, package.json), git history (if available), conversation/memory files, and may append internal scaffolds and ANSON_META.md. This is consistent with its purpose but is somewhat invasive of workspace contents and git history; users should expect those reads and produced files.
Install Mechanism
No install spec and no code files — lowest-risk form. The instructions suggest cloning https://github.com/anthropics/skills if 'skill-creator' is absent; that is a standard GitHub source and reasonable for the stated workflow. There are no opaque downloads or archive extraction steps.
Credentials
The skill requires no environment variables, credentials, or special config paths. It does perform a model-detection advisory step (check local config/session info or ask the user) but does not ask for unrelated secrets. The amount of access (workspace files, git history) is proportional to its goal of inferring and writing identity/user/soul documents.
Persistence & Privilege
always is false and the skill does not request system-wide privileges. It will create and update files in the workspace and can generate new skills via 'skill-creator' — behavior consistent with its purpose. These writes are limited to the project workspace rather than global agent settings.
Assessment
This skill is an instruction-only wizard that will read your project workspace (README, package.json, existing IDENTITY.md/USER.md/SOUL.md, git history if available), create ANSON_META.md in the workspace root, and generate maker skills (identity-maker, user-maker, soul-maker, agents-maker) via a required 'skill-creator' helper. Before installing or running it, consider: 1) Back up your workspace or use a disposable project directory — the skill will write files and scaffolds. 2) Review ANSON_META.md and any generated SKILL.md files it creates (especially the generated maker skills) before allowing further automated runs. 3) The skill may ask you to clone https://github.com/anthropics/skills if 'skill-creator' is missing; only allow that if you trust the repository. 4) Expect the skill to read git history and any local conversation/memory files in the project—if those contain sensitive data, remove or move them first. 5) If you do not want the agent to autonomously generate or run new skills, restrict model/agent permissions or avoid installing this skill. Overall the skill is coherent with its stated goal, but you should inspect the files it creates and the 'skill-creator' source it relies on before allowing ongoing automation.Like a lobster shell, security has layers — review code before you run it.
latestvk974mqxjq28y1wz91rtkymfc95841r5z
License
MIT-0
Free to use, modify, and redistribute. No attribution required.