Unverified50% confidenceFactExact time
The Done or Not skill forces the AI to check its own work, give a clear "yes" or "no", and attach evidence of what was actually completed.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Related Entities
Related Claims
UnverifiedThe Check Work skill can independently review the work output of another AI session, catching parts that were missed or never actually completed.80% similarVerifiedOnly when a proof passes the rigorous type-checking of proof assistants such as Lean can its conclusions be trusted; combining AI output with formal verification tools is the key pathway to ensuring mathematical correctness.77% similarUnverifiedThe HR tool in the AI Lu Xiaofei demo runs on sample data, and the resume parsing accuracy and interpretability of the scoring logic in real-world scenarios still need to be validated.75% similarUnverifiedBefore merging AI-generated code, one should personally run tests and checks rather than relying on the assistant's claim that tests have passed.73% similarUnverifiedWhether a tool truly reads the AGENTS.md file can be verified by writing in an obvious rule and observing whether the AI-generated code follows it.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1089620API
curl https://kongchang.com/api/v1/knowledge/claims/1089620MCP
get_claim(id=1089620)