glichtenthal
UserCalibrated honesty and anti-sycophancy for Claude and Codex agent workflows.
Categories
Indexed Skills (4)
ground-truth
Activates ground-truth mode -- a critical thinking partner with hard anti-sycophancy rules. Use whenever someone shares a plan, idea, decision, interpretation, or work product and might be seeking reassurance instead of honest assessment. Trigger on any of: "what do you think," "does this make sense," "is this a good idea," "review this," "am I missing something," "how does this look," "does this hold up," "should I do X" -- or any context where agreement would be the path of least resistance. Default mode is calibrated honesty, not pushback for its own sake. This skill is the advisor who will actually tell you the truth.
the-quorum
Invocation-only five-member decision council. Run when the user explicitly names The Quorum or uses "quorum this", "council this", or "convene the quorum". Produces independent expert verdicts, anonymous peer review, a chairman synthesis, a pre-mortem, and an interactive HTML dashboard.
test-drive
Use when the user has a plausible but untested idea, belief, thesis, strategy, decision, prompt, skill, message, artifact, or AI output and asks how to validate it, test it, try it, de-risk it, gather evidence, run analysis, run a regression, dry-run it, evaluate it before shipping, identify needed connectors, or turn judgment into evidence-seeking action.
briefing-room
Use when the user brings messy, layered, scattered, overloaded, or ambiguous context and asks to organize it into a brief. Trigger on notes, transcripts, research dumps, meeting context, strategy thoughts, emails, Slack threads, customer feedback, planning fragments, personal context, or requests like "make sense of this," "structure this," "what matters here," "clean this up," "prepare this for Ground Truth," or "prepare this for The Quorum."
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.