Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsAuthors › IgorGanapolsky

IgorGanapolsky

@IgorGanapolsky on GitHub →

15 Claude Code skills authored by IgorGanapolsky.

updated 2026-05-23 · showing 1–15 of 15 by quality score

Average Pro QualityScore: 63.0/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Generate and review prevention rules auto-promoted from repeated failure patterns.
Read, monitor, and analyze Skool communities or posts headlessly for lead discovery, customer pain, acquisition opportunities, or ThumbGate revenue research without blocking the…
Capture structured thumbs up/down feedback with context, history-aware lesson distillation, tags, and optional rubric scores after completing a task.
Recall relevant past failures, prevention rules, and context packs before starting a coding task.
Search promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.
Stop 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…
Hand 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…
Automated Bluesky reply monitoring and draft queueing for ThumbGate's acquisition engagement loop. Polls the AT Protocol notifications endpoint every 15 minutes, writes…
Dual-write feedback to Amp MCP memory AND thumbgate for DPO export, analytics, and cross-platform portability
Govern Cursor SDK local, cloud, self-hosted, and subagent coding runs before they create branches or PRs.
Capture thumbs up/down feedback into structured memories and prevention rules. Require one sentence of why before claiming memory promotion.
Pre-action checks for AI coding agents — capture thumbs-up/down feedback, generate prevention rules, and block known-bad patterns before they execute.
Recall past mistakes and capture feedback so your agent stops repeating errors. Works locally via MCP server — no API key needed.
Automated skill to handle architecture, autonomy, crisis, debug, deployment, error, execution, external-assessment, feedback, inefficiency, negative, railway, revenue, roi,…
Print 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.
Search all 15 skills by IgorGanapolsky →