setup-config

Generates and re-syncs per-repo workflow configuration files and plugin declarations for Claude Code.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/Sassy-Dog/sassydog-skills --skill setup-config-sassy-dog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup-config
Source: https://github.com/Sassy-Dog/sassydog-skills/tree/main/skills/setup-config
Command: npx skills add https://github.com/Sassy-Dog/sassydog-skills --skill setup-config-sassy-dog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Repositories using the sassy-dog workflow skills need per-repo configuration (.claude/sassy-dog/*.md plus .claude/settings.json plugin declarations), and hand-writing or migrating that config from older generated skills is error-prone: facts drift, merge policies go stale, and legacy skill directories must be removed safely without losing project-specific prose. ## Core Features & Use Cases - Four operating modes: migrate (extract facts and prose from legacy generated skills, re-verify against live state, then delete old directories), update (re-verify every configured fact against live GitHub state while carrying user prose verbatim), adopt (fold hand-written skills into config), and create (render fresh config from templates). - Capability detection and interview: runs scripts/detect-capabilities.sh to probe merge queues, boards, CI workflows, migrations, codegen, Sentry, and secret managers, then confirms policy decisions through a structured interview. - Safe writes: prints every file in full and writes only after user approval, never deletes directories lacking a generated-by: marker, and verifies settings.json declares both the marketplace and the plugin. - Use Case: A repo still carrying old .claude/skills/plate-it/ generated skills is migrated to .claude/sassy-dog/survey-work.md config, with its merge-queue setting re-verified via GraphQL before the legacy directory is deleted. ## Quick Start Ask the agent to set up this repo's sassy-dog workflow config by running the setup-config skill from inside the target repository.

Frequently Asked Questions about setup-config

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up sassy-dog workflow config for my repo?

Run the setup-config skill from inside the target repository. It probes the repo with gh and a detection script, interviews you for policy decisions like merge strategy, previews every file in full, and writes `.claude/sassy-dog/*.md` plus settings.json only after approval.

How do I migrate from old generated skills like plate-it to config-based skills?

Setup-config's migrate mode extracts facts and PROJECT-SPECIFIC prose fences from legacy `.claude/skills/` directories carrying a `generated-by:` marker, re-verifies every fact against live GitHub state, writes the new config files, and deletes old directories only after you approve.

Does setup-config work with GitHub merge queues?

Yes. It detects merge queue state via the GraphQL `mergeQueue(branch:)` field because `gh repo view` cannot report it, and always confirms merge policy against live state rather than trusting a previously rendered value.

Why does settings.json need both extraKnownMarketplaces and enabledPlugins?

The enabledPlugins entry alone cannot resolve the marketplace in cloud sessions or scheduled routines, since marketplace registration normally lives in user-level state. Declaring extraKnownMarketplaces lets cloud sessions install the plugin, otherwise scheduled skills silently fail.

Will a config refresh overwrite my custom prose sections?

No. Update mode regenerates only YAML frontmatter facts and carries `##` prose sections across verbatim, since prose is user-owned. Facts are re-verified against live state, but disagreements like a visibility mismatch are surfaced for your decision rather than silently rewritten.