SamyakJhaveri
UserCopier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.
Categories
Indexed Skills (49)
council
Multi-agent deliberation council for complex tasks. Spawns 4 specialist agents with distinct thinking styles who independently analyze the problem, then 2 cross-examination agents who argue and synthesize. Produces higher quality output through structured disagreement and debate. Use when user says "council", "deliberate", "multi-agent", "debate this", "think deeply about", "I want multiple perspectives on", or when a task clearly benefits from adversarial analysis.
auto-paper-improvement-loop
Autonomously improve a generated paper via REVIEWER_MODEL (default o3) xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
process-optimizer
Analyzes existing workflows and processes to find inefficiencies, bottlenecks, and optimization opportunities. Goes beyond automation to improve the process itself. Use when user says "optimize my process", "find bottlenecks", "why is this slow", "improve this workflow", "process audit", or "efficiency review".
sop-writer
Takes a process description and generates a complete Standard Operating Procedure document with numbered steps, decision points, checklists, and troubleshooting guidance. Use when user says "write an SOP", "create SOP", "standard operating procedure", "document this process", "write a procedure for", or asks to formalize any business process.
weekly-review
Interactive weekly review assistant that helps business owners reflect on their week, measure progress against stated goals, and plan the next week with clarity. Use when user says "weekly review", "review my week", "what did I accomplish", "plan next week", "week in review", "how did my week go", or asks to reflect on recent work.
workflow-mapper
Maps business processes from natural language descriptions into structured workflows, identifies automation opportunities using the GREEN/YELLOW/RED framework, and generates visual workflow diagrams. Use when user says "map my workflow", "describe my process", "where should I automate", "workflow audit", or describes any business process.
align-prompt
Use when you have a free-form draft prompt and want it rewritten into Claude Opus 4.6 or 4.8 conventions before pasting it into a new planning or execution session. Trigger phrases — "align prompt", "rewrite for opus", "tune prompt for claude". NOT for planning itself, code implementation, or validation. Pre-planning / pre-execution only.
decision-matrix
Structured decision-making tool that helps users evaluate options systematically using weighted scoring, criteria analysis, and practical recommendations. Use when user says "decision matrix", "help me decide", "compare options", "which should I choose", "evaluate options", "pros and cons", or "decision framework".
grill-research
Adversarial research interrogation before launching an eval or making a published claim. Use before /overnight-eval, before adding a claim to the paper, or when a reviewer-style stress test is needed. 4 waves — basics, clarifications, deep probes, assessment. Stops you from running expensive batches on shaky premises. NOT for implementation plan review (use plan-reviewer agent) or general topic research (use /researcher).
model-route
Advisor for selecting optimal Claude model tier (Opus/Sonnet/Haiku) for a specific task. Use before launching an agent team, before a multi-file refactor, or when deciding whether to switch from Opus to Haiku for transactional work (commits, formatting). Analyzes reasoning depth, blast radius, domain expertise, output length, correctness cost.
self-healing
Continuously improve Claude's effectiveness by recognizing patterns, saving memory, creating skills, and refining project knowledge. Use when Claude notices repeated workflows, encounters a problem it solved before, wants to save something for future sessions, needs to create a reusable skill, or when the user asks Claude to improve itself, learn, remember, or get smarter over time.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (DOMAIN.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in DOMAIN.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
prototype
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
to-prd
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
triage
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
codex-plan-review
Second-opinion adversarial review of a PLAN file via the Codex CLI, read-only. Use when a plan needs an independent cross-model review before execution. Manual only. NOT a replacement for /plan-review-invoke or /plan-review-fanout; Codex never edits — findings are advisory and Claude folds them into the plan.
codex-review
Second-opinion review of the current diff via the Codex CLI, read-only. Use when you want an independent adversarial review of a diff from a different model before merging. Manual only. NOT a replacement for /multi-review or /validate; Codex never edits — findings are advisory and Claude applies any fixes.
create-skill
Create high-quality Claude Code custom skills and slash commands. Use when the user wants to create a new skill, build a custom command, make a slash command, or add a reusable workflow.
agent-team
Creates and launches coordinated agent teams using TeamCreate for multi-teammate tasks requiring cross-talk, shared task lists, and lifecycle management. Use when 2+ workers need to communicate findings to each other, not just report to parent. NOT for independent parallel tasks (use dispatching-parallel-agents instead).
session-critique
Use when a session's implementation work is complete and needs adversarial critique and code quality review before committing. Triggers — after multi-file changes, after feature implementation, before final commit on significant work, when independent review of own work is needed. NOT for single-file trivial edits (use /validate directly) or standard code review without fixes (use /multi-review).
cite-check
Paper citation and claims verifier. Use before submitting a paper, after major eval runs that change numbers, or when reviewing a paper draft. Traces every numeric claim in the paper to a result JSON on disk; flags UNTRACED, MISMATCH, STALE_REF, MISSING_CITE, PHANTOM categories.
cuda-omp-translator
CUDA↔OpenMP translation pattern guide for evaluating and reviewing LLM-generated parallel code translations. Use when reviewing eval results that involve CUDA-to-OpenMP or OpenMP-to-CUDA translation pairs, when writing paper sections about translation patterns, when diagnosing why a specific translation failed to build or verify, or when creating new specs for CUDA/OpenMP kernel pairs. Covers memory model mapping, kernel launch → parallel region patterns, shared memory → threadprivate, atomic operations, and common pitfalls that cause BUILD_FAIL or VERIFY_FAIL.
eval-grader
Evaluation result grading and classification workflow. Use when classifying eval results into pass/fail categories, diagnosing failure patterns in batch results, computing pass rates with proper exclusions, or preparing result tables for papers. Handles the grading pipeline: load results, apply exclusions, classify failure modes, compute statistics, generate summary tables.
eval-run
Launch a model evaluation batch. Use when running interactive/foreground eval runs — parameter collection, pre-flight checks, execution, and post-run analysis. NOT for: long-running batches that need tmux isolation (use overnight-eval instead).
experiment
Generic experiment lifecycle orchestrator with reproducibility tracking and evolution support. Use when running any structured experiment. Integrates with /grill-research (pre-flight), /interpret-results (post-analysis), and /hypothesis-tree (evidence tracking). Subcommands — init, plan, run, evolve.
academic-research
4-skill academic pipeline: deep research (13-agent), academic paper (LaTeX), peer review (7-agent), pipeline orchestrator (10-stage). CC BY-NC 4.0 — non-commercial use only.
code-review-graph
GraphRAG-powered code review with blast-radius analysis via Tree-sitter AST. MCP server. Recommended for 500+ file codebases.
gpt-researcher
Autonomous multi-source research agent with MCP server. Planner/executor architecture, 5 MCP tools. Requires 3 API keys (Tavily + Anthropic + embeddings). Research-flavor.
prompt-improver
Use when invoked automatically by the UserPromptSubmit hook after a prompt is flagged as vague. Researches context, then generates 1-6 targeted clarifying questions before executing. Do NOT invoke this manually — it is triggered by the hook in .claude/hooks/improve-prompt.py.
impeccable
Design polish with 27 deterministic anti-pattern rules + 12-rule LLM critique. By Paul Bakaus (jQuery UI creator). Commands: polish, audit, critique, typeset, animate, colorize, layout, delight. Apache-2.0.
nature-skills
9 Nature-journal skills: figures, polishing, writing, citations, data availability, paper reading, reviewer responses, paper-to-PPT, academic search (MCP). MIT license.
planning-with-files
Manus-style persistent markdown planning with task_plan.md, findings.md, progress.md. Hook-based re-injection after /compact.
techdebt
Scan for tech debt: duplicated logic, dead code, magic numbers. Run at end of every session before final commit.
storm-research
Stanford STORM — LLM research pipeline for Wikipedia-quality articles with citations. Multi-perspective research, Co-STORM collaborative mode. Python package, no native Claude Code integration.
ui-ux-pro-max
Design system generator with curated color palettes, font pairings, UI styles, product-type rules, and UX guidelines across multiple tech stacks.
understand-anything
Multi-agent codebase analysis with interactive React knowledge graph dashboard. Best for onboarding and visual architecture exploration.
augment-test
Data augmentation testing workflow. Use when testing a new augmentation transform, diagnosing transform failures on a specific input, or validating transforms against known-good baselines. Runs augmentation pipeline and reports pass/fail per transform.
bootstrap-cc-setup
Write the always-loaded rules layer that a plugin cannot ship into the current repo: a CLAUDE.md skeleton (purpose + gotchas only) and a generic workflow.md rule (model notes only). Optionally vendors the pre-commit gate hooks into .claude/hooks/ for git-tracked, collaborator-visible enforcement. Run once per new repo after installing the sam-cc-setup plugin. NOT for repos rendered by the Loam Copier template (they already have this layer).
mode-routing
Decide how much to constrain the model for the task at hand - open for research, ideation, design and diagnosis; clamped for published numbers, harness code and anything a reviewer will read. Use when starting a task whose kind is unclear, when output feels safe and obvious and you wanted invention, when a session is producing plausible prose instead of checked facts, or when choosing effort level and whether to fan out subagents.
reflect
Structured post-task reflection — surprises, pattern proposals, prompt improvements, gotchas to record. Use at the end of a significant session, after a debugging marathon, or when patterns emerged that should update CLAUDE.md or .claude/rules/.
unknowns
Surface what you do not know before prompting, log deviations during implementation, and verify understanding after. Use before starting in an unfamiliar area, when you cannot describe what you want, when a long-horizon task came back wrong, when a plan needs stress-testing, and before merging a change you have not fully read. Emits HTML artifacts that carry the prompt and the output together.
validate
Post-session validation loop — two-wave checks (Deterministic / Rule-based) before commit. Use before every git commit. Writes .validation_passed sentinel with waves_passed field on success. NOT for: ad-hoc test runs, code review, or implementation work — only the Pipeline Gate between implement and commit.
navigate
Tool recommender — takes freeform intent and returns the best skill/agent/command to use. Use when unsure which tool to invoke next. NOT for: executing tasks directly — only recommending which skill, agent, or command to use next.
sam_handoff
Write or update a handoff document so the next agent with fresh context can continue this work. Use for IN-PROGRESS work only, not end-of-session cleanup. Writes to the project root. Renamed from `handoff` on 2026-08-02 to avoid a name clash with the mattpocock-skills plugin, whose `handoff` compacts the conversation into the OS temp dir instead - a different contract.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.