skills/config-sync/SKILL.md
Synchronize opencode.jsonc with the latest OpenCode config schema from Context7. Checks schema, detects drift, and updates config to remain compliant.
npx skillsauth add Thomashighbaugh/opencode config-syncInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Enforce that opencode.jsonc stays compliant with the latest OpenCode configuration schema.
OpenCode's config schema evolves. Keys get deprecated (mode → agent, autoshare → share), new keys are added (tool_output, compaction, experimental.policies), and invalid keys that don't exist in the schema can silently cause config load failures.
This skill fetches the latest schema from https://opencode.ai/config.json, compares it against the current config, and reports any compliance issues.
/project auditFetches https://opencode.ai/config.json via web fetch and extracts valid top-level keys, deprecated keys, and new additions.
Reads opencode.jsonc, parses all top-level keys, and checks:
@deprecated → warn if still used.opencode/context/research/opencode-config-schema.md for offline referencescripts/check-schema-compliance.mjs — Standalone compliance checker
node scripts/check-schema-compliance.mjs # Check only
node scripts/check-schema-compliance.mjs --fix # Auto-fix issues
node scripts/check-schema-compliance.mjs --save # Save schema to context
The last-fetched schema is stored at:
.opencode/context/research/opencode-config-schema.md
This serves as the durable reference and diff baseline.
tools
Create valid, type-safe TypeScript tools for OpenCode — generates correct boilerplate, typed interfaces, and handler stubs. Use when building new tools for global config or per-project .opencode/tools/.
testing
Explore multiple solution branches in parallel, evaluate each, and recommend the best path. Use when the user explicitly invokes /ideation tree-of-thoughts or asks for "tree of thought" / "branching exploration".
testing
Run multiple independent reasoning passes and find consensus. Use when the decision is critically important, the stakes are high, or the user explicitly requests "run it multiple times" / "check consistency" / "self-consistency".
testing
Optimization by PROmpting — generate candidate prompt variations, test each against a benchmark, and report the best performer. Use when the user invokes /ideation opro or asks for "prompt optimization" / "OPRO".