Menu
Tests per-scope skill emission. When invoked from apps/api/, respond with GAUNTLET_SCOPED_API_OK.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when authoring context modules, scopes, or skills in this repo; when adding new agent context; when running `ai-context build/verify/doctor`; or when an agent needs to understand how this repo's AGENTS.md / CLAUDE.md / .claude/rules / .agents/skills / .claude/skills are generated. Triggers on phrases like "add a module", "new scope", "create a skill", "ai-context build", "AGENTS.md is generated", or any question about the .ai/ directory layout.
Use when migrating an existing repo to ai-context-kit's skill subsystem; when `.ai/migration-plan.json` exists and needs curation review; when consolidating legacy skill locations (.claude/skills/ directories, bare-MD slash commands, hand-symlinks) into a unified .ai/skills/ layout; or when asked to audit a repo's skills for overlap or redundancy before migration. Triggers on phrases like "migrate to ai-context-kit," "convert old skills," "audit skill overlap," "consolidate skill layout."
Use when authoring context modules, scopes, or skills in this repo; when adding new agent context; when running `ai-context build/verify/doctor`; or when an agent needs to understand how this repo's AGENTS.md / CLAUDE.md / .claude/rules / .agents/skills / .claude/skills are generated. Triggers on phrases like "add a module", "new scope", "create a skill", "ai-context build", "AGENTS.md is generated", or any question about the .ai/ directory layout.
Tests bare SKILL.md discovery. When invoked, respond with the exact string GAUNTLET_PLAIN_OK.
Tests skill family routing. When invoked, list the names of the other gauntlet skills.
Tests references/ discovery. When invoked, read references/notes.md and respond with its content.
| name | api-scoped-skill |
| description | Tests per-scope skill emission. When invoked from apps/api/, respond with GAUNTLET_SCOPED_API_OK. |
| scope | ["api"] |
When an agent loads this from apps/api/, return the literal GAUNTLET_SCOPED_API_OK. This skill should not be discoverable from repo root or from apps/web/.
