bootloops-setup
/bootloops-setup
Set up the BootLoops protocol skills for this user. Use when the user asks to set up BootLoops, activate or install its skills, or asks what discipline the toolkit ships with. Presents the roster, asks which skills to activate, and installs only what the user chooses.
- Author
- bootloops-ai ↗
- Repository
- skills ↗
- Licence
- MIT
- Last repository change
- 30.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Set up the BootLoops protocol skills for this user. Use when the user asks to set up BootLoops, activate or install its skills, or asks what discipline the toolkit ships with. Presents the roster, asks which skills to activate, and installs only what the user chooses.
Original author description
Set up the BootLoops protocol skills for this user. Use when the user asks to set up BootLoops, activate or install its skills, or asks what discipline the toolkit ships with. Presents the roster, asks which skills to activate, and installs only what the user chooses.
How it works
- Procedure
SKILL.md preview
--- name: bootloops-setup description: Set up the BootLoops protocol skills for this user. Use when the user asks to set up BootLoops, activate or install its skills, or asks what discipline the toolkit ships with. Presents the roster, asks which skills to activate, and installs only what the user chooses. --- # bootloops-setup BootLoops ships twelve working protocols in `skills/` at the repository root. They are a library, not an installation: nothing in `skills/` is active until the user chooses to activate it. This skill is the installer. Never activate anything without an explicit choice. ## Procedure 1. **Show the roster.** Present the two groups below (one line each). The protocol layer is discipline for any quantitative work; the research skills are heavier machinery for specific tasks. *The protocol layer:* - **acceptance-gate** — what "done" means: never-fit digits against an independent route - **constant-recognition** — integer-relation discipline: declared rings, height bounds, refusal over invention - **planted-truth** — synthetic-truth controls before real data - **independence-bookkeeping** — provenance of reference values; no oracle that fed a fit certifies the result - **timing-discipline** — measure a small run first; a multi-hour projection means restructure - **reading-contract** — sources-only assertion for document-reading instruments - **tool-stewardship** — consult the toolkit first, write code last, document for the next agent *The research skills:* - **prove-protocol** — proving with agents: adversary-first pipelines, skeptic loops - **referee-sim** — pre-circulation audit: the strongest standard objection from every audience - **lit-review** — the literature audit behind a novelty claim: papers actually read, citation chains both directions - **ref-check** — bibliography verification against authoritative sources - **prose-lint** — scientific-prose linter: hype vocabulary, empty structures, agentless prose, honesty and number checks 2. **Ask what to activate.** Offer: all twelve, the protocol layer only, the research skills only, an individual selection, or none. Use the host's question/multi-select interface if it has one (in Claude Code, grouped multi-select questions fit within the four-option limit); otherwise ask in plain text. "None" is a fine answer — the library stays available to read or load ad hoc either way. 3. **Ask the scope.** Project-level (`.claude/skills/` in the user's project — active only there) or user-level (`~/.claude/skills/` — active in every project). Default to project-level if the user has no preference. 4. **Install.** Copy each chosen skill's directory from `skills/<name>/` in this repository into the chosen location, keeping the directory name. Nothing else: no edits to the files, no extra registration step. 5. **Confirm.** List what is now active and where. Note that an activated skill still only engages when its work actually comes up; activation makes it discoverable, not mandatory. To deactivate one later, delete its directory from the install location. Re-run this setup any time to add or change the selection.
Versions
The database has no other skills named bootloops-setup.
Database snapshot: 13.11.2026 · package version e169f9a47fc4 (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
- 90import-skills
Finds outside skills, checks them for security and license problems, and installs the ones the user picks. Use when the user says "find skills I could add", "import a skill", "are there skills for X", "is this skill safe", "vet this skill", or otherwise wants to use a skill written by someone else. - 100skillvm
Version manager for agent skills (Claude Code, Codex). Searches GitHub for skills on a topic, installs skills from GitHub, checks for and applies updates, shows version history, and rolls back or pins skills. Use when the user asks to find, install, update, check for updates,… - 98setup-agent-skills
Set up shared skills on this computer. Use when installing this repository's skills, linking them into Claude Code or Codex, or troubleshooting those links. - 100manage-skills
Install, remove, and inspect skills from a clone of the kapo-skills repo. Use when someone asks to install or add a skill, see which skills they have, remove or uninstall a skill, update their shared skills, or when a skill that should be available isn't showing up. - 96setup-autoontology
Set up and run AutoOntology locally in one go — check prerequisites, install, configure the chat provider (default the user's Claude login, no API key), build the quickstart sample set and show the web UI URL. Use when the user asks to install, set up, bootstrap, start or try AutoOntology. - 90setup
Set a person up on Aitherium from Claude Code - check what local model their machine can run, install the awdk agent toolkit and that model with their approval, and sign them in to their Aitherium account. Use when the user asks to install, set up, try or connect Aitherium,…