Results for “grade-evidence-grading”

Grades individual test methods and produces a compact markdown table with a letter grade, score band, and one-line note for each test.

Design grading plans. TRIGGERS - Use when user needs help with grading-plan related tasks.

Design grading plans. TRIGGERS - Use when user needs help with grading-plan related tasks.

Design and implement evaluation harnesses for models, agents, and code. Use when creating benchmarks, designing eval metrics, or comparing system outputs.

Multi-dimensional lead qualification scoring. Evaluates leads against BANT criteria, firmographic fit, behavioral signals, and intent indicators. Outputs qualified/disqualified verdict with detailed reasoning.

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".

Cross-validation only estimates generalization if the split mimics the gap between

Check post-launch adoption for a published ORD package and recommend iterate, graduate, or archive

Mines a codebase for evidence-backed improvement opportunities, forcing two escalation gates to surface breakthrough ideas, and outputs a ranked portfolio with a plan seed without implementing.

Curriculum Learning

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.

Score Analyzer

Readability Review

Use this skill to evaluate which DataQ challenges have winning evidence and which don't. Covers documented vs anecdotal evidence and the 8 high-success patterns.

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

SVIT: Scaling up Visual Instruction Tuning

Validate whether an OSS tool is worth building through staged namespace, existing-solution, and feasibility review

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Require fresh evidence before claiming an implementation, fix, build, or test is complete.