All authors
Claude Skills by naman10parikh
github.com/naman10parikh32 skills0 installs0 views
- Agent RuntimeBuild the Energy agent runtime adapter wrapping Claude Agent SDK. This is the core of Phase 1.Votes: 0GitHub stars: 9
- ArchitectUse when making architectural decisions for the Energy/NRG platform. Loads architecture from VISION.md and debates trade-offs using Socratic thinking.Votes: 0GitHub stars: 9
- Deep ThinkActivate multi-modal thinking for complex decisions. Combines Socratic thinking, self-critique, second/third-order effects, and adversarial debate.Votes: 0GitHub stars: 9
- Design SystemsV3 design harness — discovery brief gate, DFS pipeline, 12-dimension binary audit, OKLCH colors, jakub.kr micro-details. Produces world-class designs for any vertical.Votes: 0GitHub stars: 9
- Ecosystem ReferenceQuick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.Votes: 0GitHub stars: 9
- Fractal DelegationEvery task with 2+ independent workstreams, or any task that would take >15 minutes as solo work. Also triggered by maintainer voice dumps with multiple requirements.Votes: 0GitHub stars: 9
- Harness ReviewReview an agent's harness (scaffold) for quality, token efficiency, and correctness. Based on harness engineering research.Votes: 0GitHub stars: 9
- HeartbeatImplement the HEARTBEAT.md pattern for proactive agent behavior. Agents check for updates, run scheduled tasks, and act without user prompting.Votes: 0GitHub stars: 9
- Integrate ResourcesProcess new resources dropped into resources/unread/. Extracts Claude Code tips, tools, patterns and updates the setup guide, skills, hooks, and knowledge catalog.Votes: 0GitHub stars: 9
- Llm Council CritiqueRun a 6-hat brutal LLM Council self-critique on any deliverable, session output, or status update. Surfaces what's actually missing, where the work is shallow, and what was tabled-for-later. Use BEFORE re-attacking a problem the maintainer has flagged twice. Encodes the Karpathy LLM Council pattern from CP82 ralph loop iterations 2 and 3 — applying the council BEFORE the next attack saves three iterations.Votes: 0GitHub stars: 9
- Loop CreateScaffold a new agent with the full file structure. Use when creating any new agent for the Energy platform. NOTE — ".loop" is a working name for the agent file format. When building, use a configurable extension constant.Votes: 0GitHub stars: 9
- Mcp SetupSelf-install MCP servers to expand Claude's capabilities. Read the catalog, install the server, wire it into .mcp.json, and test.Votes: 0GitHub stars: 9
- Memory CompressionProduction memory management for Energy agents. Prevents context loss, enables compound memory.Votes: 0GitHub stars: 9
- MemorySearch, store, compress, and recall memories across the Energy platform. Semantic search over LEARNINGS.md, daily logs, vault notes, and rules.Votes: 0GitHub stars: 9
- Model RoutingAdaptive budget-aware model routing. Manages 4-tier system to maximize $200/mo Max plan usage across full weekly cycle. Run when starting sessions, hitting usage warnings, or optimizing sub-agent costs.Votes: 0GitHub stars: 9
- Oss Project ScaffoldScaffold a new OSS CLI project with package.json, tsconfig, README template, Vitest, CI, and LICENSE. The standardized starting point for all Energy OSS tools.Votes: 0GitHub stars: 9
- Playwright CliAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.Votes: 0GitHub stars: 9
- Repo ScoutScout popular GitHub repos for patterns, frameworks, and harnesses relevant to Energy. Ingest learnings automatically.Votes: 0GitHub stars: 9
- Self ImproveAnalyze past session logs to find repeated patterns, forgotten rules, and backtracking moments. Auto-update CLAUDE.md, skills, and rules to address gaps. "Correct once, never again."Votes: 0GitHub stars: 9
- Skill CreatorAuto-generate new skills from learnings, approved patterns, and repeated user preferences. The meta-skill that makes the harness self-improving. Core to AutoLab.Votes: 0GitHub stars: 9
- Skill RoutingClaude Code's architecture already solves the "50,000 skills" problem:Votes: 0GitHub stars: 9
- SprintPlan a focused development sprint. Breaks large goals into 2-hour chunks with dependencies and parallelization opportunities.Votes: 0GitHub stars: 9
- Test VisualBrowser-based visual testing of UI changes. Requires Chrome integration (--chrome flag or /chrome command).Votes: 0GitHub stars: 9
- TroubleshootMulti-layer error recovery. Uses docs, web search, context7, learnings, and browser to unblock errors instead of failing repeatedly.Votes: 0GitHub stars: 9
- Ux AuditSystematic UX audit for Spark and Energy platform. Checks component consistency, accessibility, duplicate elements, responsive layout, and interaction patterns. Run before any demo or commit.Votes: 0GitHub stars: 9
- Agentgrid OrchestrateHand out and track work across a running agentgrid. Send a prompt to one pane, inject a long mission file, broadcast to every pane, read a pane's output and watch live status. Use after a grid is running, when the user says "send this to pane 3", "broadcast", "inject the mission", "what is pane 2 doing" or "monitor the grid".Votes: 0GitHub stars: 9
- Agentgrid SessionsSave, restore and replay agentgrid layouts. Save a working grid (layout, pane names, agent commands, conversation ids), restore it after a crash or a reboot, and launch the built-in team presets. Use when the user says "save this grid", "restore my session", "launch a preset" or "set up the same team again".Votes: 0GitHub stars: 9
- AgentgridSpawn a visible grid of AI coding agents (Claude Code, Codex, Gemini CLI, Aider and others) in one command, one agent per tmux pane. Use when the user wants several agent sessions running in parallel, a multi-agent terminal layout, or a team of agents working side by side.Votes: 0GitHub stars: 9
- Fractal DelegationEvery task with 2+ independent workstreams, or any task that would take >15 minutes as solo work. Also triggered by maintainer voice dumps with multiple requirements.Votes: 0GitHub stars: 7
- Wikimem Ingest PipelineTurn raw sources (files, folders, URLs, 13 formats) into linted, wikilinked WikiMem pages, and keep a changing folder in sync incrementally. Use WHEN the user says "add/save/import this to my wiki", drops a PDF/DOCX/MD/audio/video, points at a folder that changes daily, or asks to re-ingest only what's new. This is the ingestion + pipeline job (Automations 1+2): detect raw → extract → dedup → lint → save as page. Do NOT use for one-off scratch notes or for querying existing knowledge (use the...Votes: 0GitHub stars: 7
- Wikimem ObserverRun WikiMem's self-improvement Observer — score every wiki page on quality, surface the weakest/orphan/most-referenced pages and knowledge gaps, then optionally auto-improve a budget-capped set and commit one reviewable change. Use WHEN the user says "improve / clean up / lint / tidy my wiki", "what's weak in my notes", "score my vault", "fill the gaps", or wants the nightly self-evolution loop (Automation 3). This is the open-endedness moat — the wiki gets better while you sleep. Do NOT use ...Votes: 0GitHub stars: 7
- WikimemSelf-improving LLM knowledge base. Use WHEN you need to ingest a file/URL/folder into a wiki, query your own knowledge with LLM-powered search, sync a connector (Slack/GitHub/Gmail/Discord/Notion/Linear/Jira + 30 more), run the Observer to score + improve your wiki nightly, or expose the wiki to Claude as a Custom Connector via MCP OAuth. Do NOT use for ephemeral notes, scratch work, or single-session context — WikiMem is for persistent, compounding knowledge. The harness IS the product.Votes: 0GitHub stars: 7