193 skills · sorted by relevance
Identify software protections that hinder inspection, such as debugger detection and obfuscation that makes code harder to understand. Support authorized binary analysis and CTF security challenges with protection findings, bypass strategies, reports, and analysis scripts.
Compose compact, structured prompts for coding, debugging, review, and research with Codex or GPT-5.4. This internal skill defines task scope, completion criteria, output format, verification steps, and evidence requirements using consistent XML tags.
Guides PyTorch model training and fine-tuning, from choosing architectures to configuring optimizers and learning rates. Provides troubleshooting steps for unstable loss and memory shortages, plus methods for improving GPU throughput and comparing experiments.
Use the Obsidian command-line interface to read, create, and search notes, manage tasks and properties, and work with specific vaults. It also supports plugin and theme debugging through error checks, screenshots, and interface inspection.
Search Echo for previous Marin work and cite the original evidence during debugging or research. Reuse relevant findings throughout an investigation, and create or update concise wiki notes that guide future decisions and troubleshooting.
Write and debug nvMolKit Python code for processing large molecule batches on GPUs. Covers molecular fingerprints, compact representations of molecular features, plus similarity calculations, 3D conformer generation, optimization, clustering, and molecular searches using RDKit objects.
Use when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. Isolates it in a debugger subagent with persistent .planning/debug state, unlike skills/systematic-debugging.
The English summary is being prepared. Showing the original description.
資料や観点を比較して根拠付きの結論・仮説をまとめる。一次資料まで引用・参照を追跡し、検証対象の主張ごとの出典で完了判定する deep research にも使う。実装や不具合調査は pir2/debug。
The English summary is being prepared. Showing the original description.
The PRIMARY development workflow for the Archon project (remote-coding-agent). Use this skill instead of any PRP skills when working on Archon code. Routes to 10 specialized cookbooks based on what the user is trying to do: RESEARCH — "how does the orchestrator work?", "where is session state defined?", "trace the workflow execution flow", "what is IWorkflowStore?" INVESTIGATE — "should we use Drizzle or Prisma?", "what's the best way to add WebSockets?", "can we migrate to Turso?", "how do other projects handle rate limiting?" PRD — "write a PRD for dark mode", "spec out the notification feature", "product requirements for webhook retry" PLAN — "plan the auth refactor", "design the caching layer", "create an implementation plan for #42" IMPLEMENT — "implement the plan", "execute .claude/archon/plans/auth.plan.md", "build the feature from the plan", "code this up" REVIEW — "review PR #123", "review my changes", "code review the diff" DEBUG — "debug the failing test", "why is streaming broken?", "root cause analysis on the timeout issue" COMMIT — "commit these changes", "commit the auth refactor" PR — "create a PR", "open a pull request for this branch" ISSUE — "report this to gh", "create a gh issue", "log it in github", "file a bug for this", "create a feature request" This skill triggers on ANY development task: researching, investigating, planning, building, reviewing, debugging, committing, or shipping code. NOT for: Running Archon CLI workflows in worktrees (use /archon instead).
The English summary is being prepared. Showing the original description.
Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.
Keep project decisions, debugging notes, and session discoveries in a lasting Markdown wiki. Organize pages with tags and categories, connect related notes with links, and retrieve information through keyword searches.
Define custom entities and relationships in cognee, a memory system for AI applications. This skill guides model design, identity matching, searchable fields, and troubleshooting when entities are duplicated or relationships are missing.
Operate Screenpipe from the terminal to set up continuous recording, check capture health, and search local history. Manage Pipes, scheduled AI automations, and configure and test connections to external services.
Helps AI agents recover from repeated failures by reviewing previous attempts, checking original sources, testing different hypotheses, and verifying results. It combines structured troubleshooting with performance review rhetoric modeled on large technology companies.
Find, add, and combine shadcn/ui components to build forms, dashboards, and other interfaces. Use project settings and component documentation to guide styling, debugging, preset changes, and updates that preserve local modifications.
Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.
Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
Connect AI agents to Jira and Confluence through MCP, a protocol for accessing external tools. This skill guides issue searches and updates, page management, sprint workflows, authentication setup, and troubleshooting of Atlassian integrations.
Split debugging, audits, searches, and code questions into read-only tasks for sub-agents. Combine their structured reports into an evidence-based answer, requesting follow-up investigations when findings conflict or leave important gaps.
Develop and check research code in MATLAB/Octave or Python for signal processing, image analysis, statistics, and simulations. This skill supports reproducible workflows, checks units and assumptions, and prepares figures for papers and presentations.
Write, debug, and understand Stata code for data cleaning, statistical analysis, causal inference, and charts. The reference covers command syntax, common pitfalls, Mata programming, and community packages for estimation and reporting.
Organize work so an expensive AI model handles planning, judgment, and final review while cheaper helper agents perform bounded research, coding, and testing. Define ownership and verification requirements, then inspect the evidence and integrate their results centrally.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
The English summary is being prepared. Showing the original description.