Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 56401–56430 of 57830 skills

diagnosing-bugshenrygoldsmith07-wq/Claude-CodeDiagnosis loop for hard bugs and performance regressions. Use for "diagnose", "debug this", or a reported crash/hang/slowdown.Stars: 0Updated Claude CodeCodexUnverifiedInstall
domain-modelinghenrygoldsmith07-wq/Claude-CodeBuild and sharpen a project's domain model, ubiquitous language, and architectural decision records.Stars: 0Updated Claude CodeCodexUnverifiedInstall
grillinghenrygoldsmith07-wq/Claude-CodeInterview the user relentlessly to stress-test a plan or design before building. Use on any "grill" phrasing.Stars: 0Updated Claude CodeCodexUnverifiedInstall
impeccablehenrygoldsmith07-wq/Claude-CodeFinal quality pass before shipping: verify it works, remove loose ends, confirm it matches the ask. Use for "make it impeccable", "polish this", "final pass", "ship-ready".Stars: 0Updated Claude CodeCodexUnverifiedInstall
improve-codebase-architecturehenrygoldsmith07-wq/Claude-CodeAssess and improve overall codebase architecture — layering, coupling, module boundaries.Stars: 0Updated Claude CodeCodexUnverifiedInstall
improve-prompthenrygoldsmith07-wq/Claude-CodeSingle-pass rewrite of an LLM prompt — paste a prompt or point at a file (system prompt, prompt template, agent definition, SKILL.md) and get an improved version with a rationale for each change. Use when the user wants a prompt improved, optimized, tightened, or reviewed against prompt-engineering best practices.Stars: 0Updated Claude CodeCodexUnverifiedInstall
improve-systemhenrygoldsmith07-wq/Claude-CodeThe self-improvement loop — parse freshly synced /raw data, auto-apply low-risk fixes, write high-stakes proposals to output/review_[date].md for sign-off. Use for the scheduled routine or "improve the system".Stars: 0Updated Claude CodeCodexUnverifiedInstall
karpathy-guidelineshenrygoldsmith07-wq/Claude-CodeBehavioral guidelines that reduce common LLM coding mistakes — surgical changes, surfaced assumptions, verifiable success criteria.Stars: 0Updated Claude CodeCodexUnverifiedInstall
re-freshhenrygoldsmith07-wq/Claude-CodeStart a clean session carrying only the context the next task needs, instead of /compact. Use for "re-fresh", "refresh context", "fresh start", "hand off this session", or when output is drifting. Levels: lite | full | ultra.Stars: 0Updated Claude CodeCodexUnverifiedInstall
researchhenrygoldsmith07-wq/Claude-CodeInvestigate a question against high-trust primary sources and capture findings as Markdown in the repo. Use to research a topic or gather docs/API facts.Stars: 0Updated Claude CodeCodexUnverifiedInstall
routineshenrygoldsmith07-wq/Claude-CodeCreate, fire, and manage Claude Code cloud routines (scheduled/API/GitHub-triggered remote agents). Use for "routine", "schedule a remote agent", "webhook to Claude", "daily/weekly Claude job", "cron routine".Stars: 0Updated Claude CodeCodexUnverifiedInstall
sync-claude-sessionshenrygoldsmith07-wq/Claude-CodeDigest recent local Claude Code CLI history into /raw/sessions and index recurring mistakes in /wiki. Use when syncing session data or as part of /data-ingestion.Stars: 0Updated Claude CodeCodexUnverifiedInstall
sync-curated-contenthenrygoldsmith07-wq/Claude-CodeRead the +newsletter Gmail alias, extract claims and techniques into /raw/curated, update wiki entries. Use when syncing newsletters or as part of /data-ingestion.Stars: 0Updated Claude CodeCodexUnverifiedInstall
sync-ecosystem-datahenrygoldsmith07-wq/Claude-CodePull meeting transcripts, email threads, and calendar activity into /raw/ecosystem and index in /wiki. Use when syncing ecosystem data or as part of /data-ingestion.Stars: 0Updated Claude CodeCodexUnverifiedInstall
tddhenrygoldsmith07-wq/Claude-CodeTest-driven development: red-green-refactor, integration tests. Use to build features or fix bugs test-first.Stars: 0Updated Claude CodeCodexUnverifiedInstall
solana-devYT4l0/Superteam-Brasil-x-NearXUnified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, solana-game, trailofbits, cloudflare, qedgen, colosseum) and local skills. Progressive disclosure — read only what you need.Stars: 0Updated Claude CodeCodexUnverifiedInstall
ck-create-noteOxyd22/ContextKitRecord knowledge, decisions, and tickets in the knowledge base (the model can read and write it). Creates or updates a schema-valid entry and rebuilds the index. Run: /ck-create-note <what to record> — or /ck-create-note <TICKET-ID>.Stars: 0Updated Claude CodeCodexUnverifiedInstall
ck-doctorOxyd22/ContextKitKnowledge-base hygiene: setup doctor, schema lint, rebuild the index, freshness stamp. Run: /ck-doctorStars: 0Updated Claude CodeCodexUnverifiedInstall
ck-migrateOxyd22/ContextKitUpdate an existing ContextKit project to this hub's version. Scripts, skills, and VERSION are refreshed; config, the index cache, and unrelated files stay. Run from the hub: /ck-migrateStars: 0Updated Claude CodeCodexUnverifiedInstall
ck-read-noteOxyd22/ContextKitLook up project knowledge (notes, decisions, tickets) through the generated INDEX instead of reading every entry. Use it so earlier decisions are considered before a new one. Run: /ck-read-note <topic/question>Stars: 0Updated Claude CodeCodexUnverifiedInstall
ck-refs-lookupOxyd22/ContextKitLook up reference repos (read-only) through the condensed contract index instead of reading the whole repo. Run: /ck-refs-lookup <topic/type/endpoint>Stars: 0Updated Claude CodeCodexUnverifiedInstall
ck-refs-syncOxyd22/ContextKitUpdate reference repos (git pull) and rebuild the condensed contract index. Run: /ck-refs-syncStars: 0Updated Claude CodeCodexUnverifiedInstall
ck-setupOxyd22/ContextKitConversational ContextKit setup assistant. In the hub: install (merge-safe) into a project and configure it. In an installed project: reconfigure only. Run: /ck-setupStars: 0Updated Claude CodeCodexUnverifiedInstall
agent-architecture-auditsakamoto-family-smile/agent_monorepoFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.Stars: 0Updated Claude CodeCodexUnverifiedInstall
agent-harness-constructionsakamoto-family-smile/agent_monorepoDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.Stars: 0Updated Claude CodeCodexUnverifiedInstall
agent-introspection-debuggingsakamoto-family-smile/agent_monorepoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.Stars: 0Updated Claude CodeCodexUnverifiedInstall
agent-sortsakamoto-family-smile/agent_monorepoBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.Stars: 0Updated Claude CodeCodexUnverifiedInstall
agentic-engineeringsakamoto-family-smile/agent_monorepoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.Stars: 0Updated Claude CodeCodexUnverifiedInstall
agentic-ossakamoto-family-smile/agent_monorepoBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.Stars: 0Updated Claude CodeCodexUnverifiedInstall
ai-first-engineeringsakamoto-family-smile/agent_monorepoEngineering operating model for teams where AI agents generate a large share of implementation output.Stars: 0Updated Claude CodeCodexUnverifiedInstall