Lrs Eval
Little Red Schoolhouse writing evaluation. 13 agents in 3 waves + critic. Evaluates rhetoric and craft using 21 principles from the reader-centered writing tradition (Williams, Colomb, Gopen, McEnerney). Complements /peer-review (scientific rigor) with rhetorical assessment.
Council Improve
Diagnostic eval of Council of Elders sessions. Identifies failure modes, proposes fixes as structured "PRs" to exemplars, prompts, config, and logic. Run after sessions or on-demand.
Context Engineer
Predict, prevent, and mitigate context window failures before they happen. Analyzes workflows for overflow risk, designs disk-as-memory architectures, and produces recovery-ready state files.
Grill
Adversarial 2-phase code review with 5C findings, OWASP risk scoring, and GPTLens critic validation. Use before pushing code.
Veracity V2 Experimental
EXPERIMENTAL v2: Enhanced parallel veracity audit with 12 gap fixes. Launches 20 agents per run in 5 waves (decomposition + quality gate + 3 verification waves). Adds citation verification, decomposition QA, confidence calibration, blind re-derivation, logical composition, and smarter consensus.
Ux Committee
A Claude skill from joonchungpersonal-dev/claude-skills.
Council Qa
A Claude skill from joonchungpersonal-dev/claude-skills.
Veracity Tweaked 555
Run a parallel veracity audit on any document, website, or portfolio. Launches 16 agents per run in 4 waves (1 decomposition + 3 waves of 5 verification agents), each wave from a different angle. Default 3 runs with inter-run review; use runs=1 for quick checks.
Readme Audit
Audit a README against its actual project state. Decomposes README into atomic claims, then verifies each against repo files, configs, code, git history, and live URLs. Launches 17 agents per run (1 decomposition + 1 structural scan + 3 waves of 5 agents). Default 1 run; use runs=3 for thorough audit.
Autoforge
A Claude skill from joonchungpersonal-dev/claude-skills.
Council Ux Test
A Claude skill from joonchungpersonal-dev/claude-skills.