All authors
Claude Skills by IgorGanapolsky
github.com/IgorGanapolsky100 skills0 installs78 views
- Pi Paper FactoryRun the paper SPY put-credit factory from Pi (pi.dev). Status, dry-run, exits, scorecard. No live, no MCP install, no iron-condor entries.Votes: 0GitHub stars: 38
- Alpaca Browseros AuthRecover Alpaca paper API access from the authenticated BrowserOS Neo session, store credentials in macOS Keychain without exposing them, and verify broker truth through the trading repo. Use when Alpaca credentials are reported missing, broker inventory is unverified, system_state is stale, or a paper dry-run fails closed.Votes: 0GitHub stars: 38
- Bogleheads ForumTrading-repo Bogleheads research/ingest via RSS and optional logged-in forum use (Keychain eazyigz @ bogleheads.org). Trigger: Bogleheads, passive forum, three-fund, bogleheads_research. Slash: /bogleheads-forum.Votes: 0GitHub stars: 38
- Explainx TrendingHonest ingest of https://explainx.ai/trending into the trading lab: parse live page-view scores, map onto existing rails, two-ceiling honesty, planner vs executor split. Never auto-install. Never clone ExplainX.Votes: 0GitHub stars: 38
- Google Colab Trading CohortUse existing Google Colab Pro+ (iganapolsky@gmail.com) for put-credit cohort scorecards. Never buy compute units. Pack ledgers via scripts/colab_cohort_pack.py and open notebooks/put_credit_cohort_colab.ipynb. Auto-invoke on Colab signup, Colab Pro, GPU offload, cohort notebook. Slash: /google-colab-trading-cohort.Votes: 0GitHub stars: 38
- GraphifyOfficial Graphify-Labs/graphify for this trading repo. Query graph.json (query/path/explain), never graph.html, never pip install graphify (wrong package). Package is graphifyy. Slash: /graphifyVotes: 0GitHub stars: 38
- Never Ask Igor To DialHARD permanent (CEO 2026-09-16 / LL-638): NEVER tell Igor to dial, call, phone, or "you dial TOP_5". Disability — agents own outreach automation. Auto-invoke before dial sheets, call-now lists, or phone-first close language. Slash: /never-ask-igor-to-dial.Votes: 0GitHub stars: 38
- Package Manager HonestyFail-closed uv.lock doctor. Steal InfoQ pnpm 12 FORMAT (keep lockfile, refuse manager switch, unknown extra lockfiles). Do not migrate trading to pnpm. Slash: /package-manager-honesty.Votes: 0GitHub stars: 38
- Speculative DecodeN-gram draft-then-verify for trading LLM text (NVIDIA FORMAT). Measure AL. Do not vendor TensorRT-LLM or train EAGLE. Slash: /speculative-decode.Votes: 0GitHub stars: 38
- SupermemoryOfficial SuperMemory adapter for the trading lab. Bearer SUPERMEMORY_API_KEY, POST /v3/documents, POST /v4/search, singular containerTag trading-lab. Local ledgers remain edge truth. Use when SuperMemory, console.supermemory.ai, container tags, or memory vs RAG comes up in this repo.Votes: 0GitHub stars: 38
- Trading OpsOperate the Igor trading lab (paper SPY put-credit validation, broker sync, safety gates, RAG). Use when working in the trading repo, checking status, planning trades, or touching risk/execution code. Prefer dry-run and ledger evidence over claims.Votes: 0GitHub stars: 38
- Typesafe Skill Suggest Not CloneSteal TypeSafe skill_suggestion FORMAT (cheap shortlist → Choice/Noul gate → top-3 fits rerank) onto Grok/trading skill rosters. Do NOT clone TypeSafe as a product. Prefer scripts/typesafe_skill_suggest.py. Auto-invoke on TypeSafe skill suggestion, skill roster routing, progressive disclosure skills, context rot from loading all skills. Slash: /typesafe-skill-suggest-not-clone.Votes: 0GitHub stars: 38
- Typesafe System One Not CloneSteal TypeSafe System One FORMAT (Choice/Score/Noul + confidence-gated routing) onto trading evidence honesty. Do NOT clone TypeSafe as a product SKU. Prefer scripts/typesafe_claim_gate.py for edge/profit claim gating. Auto-invoke on TypeSafe, Jev, console.typesafe.ai/hook, System One, confidence routing, false edge claim. Slash: /typesafe-system-one-not-clone.Votes: 0GitHub stars: 38
- Options Vol GexQuantitative options volatility, dealer gamma exposure (GEX), term structure backwardation, and market tide flow analysis engine.Votes: 0GitHub stars: 38
- Pstack ArchitectDesign caller-first, type-safe interfaces and contracts with pre-implementation checkpoints before writing internal code. Use when adding new strategy modules, broker adapters, risk gates, or multi-agent bridges.Votes: 0GitHub stars: 38
- Pstack ArenaRun competing implementation approaches in isolated git worktrees, evaluate them against a shared quantitative rubric, and synthesize the best solution. Use when tackling high-stakes algorithms, complex refactors, performance optimizations, or options sizing formulas.Votes: 0GitHub stars: 38
- Pstack HowConduct read-only runtime tracing and subsystem mental model generation without modifying code. Use when exploring unfamiliar modules, understanding data flow through trading risk rails, mapping order execution pipelines, or preparing for refactoring.Votes: 0GitHub stars: 38
- Pstack InterrogateConduct rigorous multi-perspective diff interrogation and code review. Categorize all findings strictly into 'act on', 'consider', 'noted', and 'dismissed' with explicit technical rationale. Use before opening or merging PRs.Votes: 0GitHub stars: 38
- Pstack WhyConduct deep historical archaeology and architectural rationale investigation using Git blame, PR discussions, and RAG lessons. Use when questioning why an architectural constraint exists, investigating regressions, or evaluating whether a legacy rule can be relaxed.Votes: 0GitHub stars: 38
- Ralph LoopExecute an autonomous, test-driven, hypothesis-validated Ralph Loop until a falsifiable finish condition is strictly met. Use when solving complex bugs, implementing refactors, improving test coverage, or healing CI pipelines without manual handoffs.Votes: 0GitHub stars: 38
- Verify TradingExecute end-to-end operational verification of the Igor trading lab ('Prove It Works'). Validates safety gates, risk kill switches, paper SPY put credit spread dry-run, broker connectivity, ledger integrity, and multi-agent coordination.Votes: 0GitHub stars: 38
- Jules CoordinationCoordinate with Google Jules cloud coding agent via official REST API, MCP server tools, and Chrome Browser Automation Bridge.Votes: 0GitHub stars: 38
- Autonomous Execution MandateSelf-directed autonomous execution mandate and workflow skill for ThumbGate agents. Enforces zero-human-intervention task chaining, proactive CI/Trunk monitoring, automated conflict resolution, and evidence-first reporting without requiring manual prompt nudges from the user.Votes: 0GitHub stars: 27
- Skool Headless ReaderRead, monitor, and analyze Skool communities or posts headlessly for lead discovery, customer pain, acquisition opportunities, or ThumbGate revenue research without blocking the user's browser.Votes: 0GitHub stars: 27
- ThumbgatePre-action checks for AI coding agents — capture thumbs-up/down feedback, generate prevention rules, and block known-bad patterns before they execute. Use when setting up ThumbGate, capturing feedback on agent actions, checking active prevention rules, debugging blocked actions, or exporting DPO training data. Triggers on: "thumbgate", "check", "block mistake", "prevention rule", "feedback", "thumbs up", "thumbs down", "capture feedback", "what went wrong".Votes: 0GitHub stars: 27
- Ci Failure TriageTriage a CI / PR check failure by READING the failure body before forming any hypothesis. Triggered whenever a required check is red, a PR is BLOCKED, a merge won't land, or you're about to call a failure "transient", "flaky", "stale", or "orphaned". Prevents dismissing a real failure (e.g. real CodeQL security alerts) as noise.Votes: 0GitHub stars: 27
- Evidence First AnswerRequired pre-flight before answering any "why" or "are we" question about revenue, conversion, outbound, traffic, or commercial state. Forces verification of live data and distinguishes planning docs from telemetry. Triggered automatically when the CEO asks "are you sure?" — that phrase means the previous answer was wrong.Votes: 0GitHub stars: 27
- Revenue TruthFetch live ThumbGate revenue, paid orders, and funnel telemetry from production billing endpoints. Use BEFORE answering any question about money, conversion, traffic, or "why we didn't make X." Never quote planning documents as actuals.Votes: 0GitHub stars: 27
- Scope DisciplineKeep one task closed-looped before starting the next. Triggered when a new problem surfaces mid-task (a bug, a security finding, a missing env var), when you're about to branch into unrelated work, or when you notice the session has sprawled across many half-finished threads. Prevents the "nothing ever lands" failure where each step spawns new work and none finishes.Votes: 0GitHub stars: 27
- Task State LedgerMaintain an external state ledger for any multi-step task (3+ steps, multi-PR, anything spanning more than one turn or touching production). Triggered when you notice yourself re-deriving "where am I" with repeated gh/git/curl dumps, when a task crosses turns, or when the user asks "why are you stuck/lost". Prevents the "lost" failure mode: re-discovering state every turn instead of reading it.Votes: 0GitHub stars: 27
- ThumbgatePre-action checks for AI agents - capture thumbs-up/down feedback, generate prevention rules, block known-bad patterns. Use for setup, feedback capture, check debugging, or DPO training data export.Votes: 0GitHub stars: 27
- thumbgateThumbGate provides pre-action gates for AI coding agents. It captures thumbs-up/down feedback on agent actions, auto-promotes repeated failures into prevention rules, and blocks known-bad tool calls via PreToolUse hooks. Trigger when the user wants to add safety guardrails to an AI agent workflow, capture structured feedback on agent output, generate prevention rules from failure patterns, gate high-risk actions before execution, or export DPO training pairs from production feedback. Works wi...Votes: 0GitHub stars: 27
- Thumbgate FeedbackCapture thumbs feedback and apply prevention rules before codingVotes: 0GitHub stars: 27
- Clawhub SkillStop your AI from making the same mistake twice. Pre-Action Gates that block repeat hallucinations, retry loops, and known-bad tool calls before they reach the model — zero tokens spent on mistakes you've already corrected. Works with Claude Code, Cursor, Codex, Gemini CLI, Amp, OpenCode, and any MCP-compatible agent.Votes: 0GitHub stars: 27
- Amp SkillDual-write feedback to Amp MCP memory AND thumbgate for DPO export, analytics, and cross-platform portabilityVotes: 0GitHub stars: 27
- Adversarial ReviewRun a skeptical Codex review from Claude Code that hunts for hidden regressions, unsafe assumptions, and release risk. Use before merges, deploys, migrations, or other risky changes.Votes: 0GitHub stars: 27
- ResultPrint the latest saved Codex bridge result from Claude Code without rerunning Codex. Use when the user asks for the last Codex output or wants to inspect the raw bridge result.Votes: 0GitHub stars: 27
- ReviewRun a Codex review from Claude Code against the current uncommitted work, a base branch diff, or a specific commit. Use when the user explicitly asks for a Codex review or second reviewer.Votes: 0GitHub stars: 27
- Second PassHand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.Votes: 0GitHub stars: 27
- SetupValidate that the Codex bridge plugin is ready inside Claude Code. Use when the user asks to install, configure, or sanity-check Codex review from Claude.Votes: 0GitHub stars: 27
- StatusShow the latest Codex bridge artifact metadata from Claude Code. Use when the user asks whether the bridge already ran, what mode it used, or where the result was saved.Votes: 0GitHub stars: 27
- Claude SkillCapture thumbs up/down feedback into structured memories and prevention rules. Use when user gives explicit quality signals about agent work (e.g. "that worked", "that failed", "thumbs up/down"). Do NOT use for general questions, code generation, file operations, or any task that is not explicit feedback on prior agent output.Votes: 0GitHub stars: 27
- Capture FeedbackCapture structured thumbs up/down feedback with context, history-aware lesson distillation, tags, and optional rubric scores after completing a task.Votes: 0GitHub stars: 27
- Prevention RulesGenerate and review prevention rules auto-promoted from repeated failure patterns.Votes: 0GitHub stars: 27
- Programmatic Agent RunsGovern Cursor SDK local, cloud, self-hosted, and subagent coding runs before they create branches or PRs.Votes: 0GitHub stars: 27
- Recall ContextRecall relevant past failures, prevention rules, and context packs before starting a coding task.Votes: 0GitHub stars: 27
- Search LessonsSearch promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.Votes: 0GitHub stars: 27
- Agent Architect Kit**Status:** shipped 2026-04-21. Test-backed. CLI-automatable. Safe to recommend publicly.Votes: 0GitHub stars: 27
- Agent MemoryGive your agent persistent cross-session memory — recall what went wrong on similar tasks before starting, then capture whether the work succeeded or failed so repeated mistakes auto-promote into prevention rules. Runs locally via the ThumbGate MCP server (recall, capture_feedback, prevention_rules, feedback_stats) — no API key needed. Use when the user says "recall", "what went wrong last time", "remember this for next time", "capture feedback", "thumbs up/down on that", or at the start of a...Votes: 0GitHub stars: 27
- Applyops DeployRepeatable skill for deploying ApplyOps pages to GitHub Pages with full analytics.Votes: 0GitHub stars: 27