Production-oriented template for building AI agent skills as verifiable software components — offline eval harness, source-grounding validators, structured logs/traces/metrics, replay artifacts, and a CI quality gate. Runs fully offline with a deterministic mock model.
HelloThisWorld/agent-skill-verification-template
Skill Claude CodeCodex
Answers questions about a codebase using source-grounded evidence. Every factual claim must cite a specific file and line; ambiguous or unsupported questions return insufficientevidence instead of a guess.
HelloThisWorld/agent-skill-verification-template
Skill Claude CodeCodex
Looks up "glossary " on English Wikipedia and returns a source-grounded definition rendered as a web page. Every claim cites the exact snapshot line carrying the term; unknown terms return insufficientevidence instead of a guess.
HelloThisWorld/agent-skill-verification-template
Skill Claude CodeCodex
Route any query to exactly one documented Open Mind capability (glossary / structure / search) using the deterministic if-else floor — the mode where routing never depends on a model. The decision is grounded by citing the capability's documented registry line. Runs Open Mind's real Python implementation through the…
HelloThisWorld/agent-skill-verification-template
Skill Claude CodeCodex
Answer code-structure questions (definition sites, usage sites) from Open Mind's deterministic structure map — real defs, imports and call sites recovered from the corpus code, never invented nodes or edges. Runs Open Mind's real Python implementation through the skill bridge.
HelloThisWorld/agent-skill-verification-template
Skill Claude CodeCodex
Resolve a term against Open Mind's deterministic, source-traceable glossary — verbatim definitions with file:line provenance, exact-token lookup, honest "not found" for unknown terms. Runs Open Mind's real Python implementation through the skill bridge.