Agent skill
reasoning/citation-verifier
Verify each generated claim against provided sources, enforce inline citations, and prune unsupported text. Use when outputs must be strictly grounded.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/devops/reasoningcitation-verifier-cloudhabil-agi-server
SKILL.md
Citation Verifier
Capabilities
- extract_claim_atoms: split output into verifiable claim units.
- locate_source_span: find supporting spans in scoped sources.
- generate_inline_citation: attach [Source: file:line] style tags.
- prune_unsupported_claims: drop or flag claims without support.
Dependencies
- constrained-decoding (to force citation format)
- S2 (optional multi-scale selection)
- guardrails-control (optional enforcement)
Inputs
- claims or draft text, plus source chunks with refs (path + lines).
Outputs
- validated_text with inline citations
- unsupported_claims list (if any)
Usage
- Use after context-boundary-manager has produced scoped chunks; enforce that every claim cites a known span or is removed.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?