RationalDynamics/claude-skills
πͺMarketplaceRationalDynamics/claude-skills
STORM-based research skills (storm-research one-shot, costorm-session interactive) plus an example eval skill, for Claude Code / Cowork.
Add this Marketplace
/plugin marketplace add RationalDynamics/claude-skillsPlugins in this Marketplace
breakpoint
contextInsert /breakpoint context-checkpoint markers that divide a session into logical blocks so /neuralize can later evict irrelevant context. Slash-invoked only (model auto-invocation disabled).
camera-lens-travel-eval
evalsWorked-example eval skill: grades a candidate answer to a camera travel-gear question with a 100-point rubric, gold-fact baseline, line-grounded evidence, and critical-error score caps. A template for rigorous, auditable evals.
costorm-session
researchInteractive, human-in-the-loop Co-STORM research: a steerable, turn-based discourse among LLM experts and a moderator over web sources, growing a shared mind map, then synthesizing a cited report. Resumable.
esoteric-elucidation
developmentExplain unfamiliar code, systems, or domains by orienting in plain English, scoping blast radius, and walking concrete data flows before diving into implementation detail. Repo-agnostic.
grill-me
productivityInterview the user relentlessly about a plan or design, resolving each branch of the decision tree until shared understanding. Use to stress-test a plan.
neuralize
contextSelectively evict irrelevant context blocks and reload only what matters (/neuralize) β the surgical alternative to clearing a whole session. Pairs with breakpoint. Slash-invoked only.
scaffold-agent-team
developmentScaffold a repo-coupled multi-agent team (lead / architect / backend / qa / reviewer / devops) tuned to a target repo's conventions β emits project-local agents, slash commands, and a coordination protocol, then adversarially verifies the generated claims.
session-cost
observabilityReport token usage, wall-clock time, and per-model cost for Claude Code sessions from the on-disk ~/.claude/projects JSONL transcripts β grouped by session or git worktree, with a compare mode. Dedups streamed/re-serialized usage and prices per model so totals reconcile with ccusage. Read-only.
storm-research
researchPerspective-driven, outline-first long-form research (Stanford STORM): multi-perspective research conversations, an evidence-grounded outline, a sectioned cited article, and a deterministic citation audit.
tdd
developmentTest-driven development with a red-green-refactor loop, plus references on deep modules, interface design, mocking, and refactoring.
the-orchestrator
orchestrationDecompose a design doc into a parallelizable DAG of tasks and run them across git worktrees with an interactive visual workflow. Repo-agnostic.