// Verify factual claims before adding them to agent memory blocks. Use this skill when proposing FAQ entries, documentation updates, or any factual statements about Letta features, APIs, or behavior. Prevents confident-but-wrong assertions.
| name | verify-claims |
| description | Verify factual claims before adding them to agent memory blocks. Use this skill when proposing FAQ entries, documentation updates, or any factual statements about Letta features, APIs, or behavior. Prevents confident-but-wrong assertions. |
Test assumptions against code, docs, and live APIs before committing them to memory.
Search relevant repos for implementation evidence:
./scripts/check-code.sh "lettabot supports skills" ~/lettabot
Search docs.letta.com for official statements:
./scripts/check-docs.sh "archival memory vector database"
Run actual API calls to verify behavior:
./scripts/check-api.sh "agents list pagination"
./scripts/verify.sh "claim to verify" [optional: repo_path]
Each script outputs:
CLAIM: <the claim being tested>
METHOD: <code|docs|api>
STATUS: VERIFIED | NOT_VERIFIED | PARTIAL | NEEDS_MANUAL
EVIDENCE: <what was found>
CONFIDENCE: <high|medium|low>
~/lettabot - LettaBot implementation~/letta/letta-sdk-api-docs - SDK documentation~/letta/skills - Shared skills repo# Verify before adding FAQ entry
./scripts/verify.sh "lettabot supports skills"
# Output:
# CLAIM: lettabot supports skills
# STATUS: VERIFIED
# EVIDENCE:
# - CODE: installSkillsToAgent in bot.ts
# - CODE: skills memory block in system-prompt.ts
# CONFIDENCE: high
Then add to FAQ with citation: "Lettabot supports skills (verified: installSkillsToAgent in bot.ts)"