QA audit for Superledger's gap analysis pipeline. Verifies batch-analyze-gaps is processing (not stamping nulls — see PR
Skills in this repository
legioncodeinc/the-apiary - Page 3
SkillsMP has collected 111 skills from legioncodeinc/the-apiary. Open a skill to review its source and details.
legioncodeinc/the-apiaryShowing 31 of 111 collected skills.
QA audit for Superledger's analysis pipeline — cron heartbeats, worker pool, advisory locks, DLQ depth, api_usage_logs completeness. Use when the user asks to check pipeline health, when qa-weekly invokes it, or when investigating "is anything stalled?". Past…
QA audit for sync-calls-oauth — the ONLY ingestion path for calls. Verifies sync ran on cadence for connected GHL locations, no sync stalls, no duplicate calls from re-sync, OAuth refresh not silently failing. Use when the user asks to QA syncing or when…
QA audit for TriageRx — the pre-sales manual-upload ROI report (voice + chat). Verifies upload UI, report renders, Whisper minute logging (per pricing followup), no leaked debug paths. TriageRx is unlaunched — expect 0 prod whisper-1 logs (staging removed…
Weekly QA orchestrator for Superledger. Runs all per-feature audit skills (qa-call-logs, qa-conversation-logs, qa-alerts, qa-gap-analysis, qa-client-portal, qa-syncing, qa-triage-rx, qa-pipeline-health, qa-action-summary) read-only against prod, then produces…
Audits a completed implementation against its source plan document and produces a structured findings report. The report goes in the source plan's `reports/` subfolder (e.g., `library/requirements/features/feature-<###>-<title>/reports/<date>-qa-report.md` or…
Reviews, refactors, and authors React 18/19 codebases using the bulletproof-react architectural pillars and the curated 2025-2026 React ecosystem. Use when the user says "review this React code", "react architecture review", "audit our React app", "state…
Authors, audits, and restructures README files so they convert visitors into users. Apply when the user says "write a README", "audit my README", "make my README better", "README for this project", "README-driven development", or when starting a new project…
The retrieval and codify pipeline for Hivemind - hybrid lexical+semantic recall over the Deep Lake `memory` and `sessions` tables, the skillify loop that turns sessions into SKILL.md provenance rows, and skill propagation across the team. Covers the…
Equips retrospective-worker-bee to run retrospectives that actually change behavior — format selection (Start/Stop/Continue, 4Ls, sailboat, mad/sad/glad, DAKI, Starfish, and more), psychological safety pre-check (Edmondson scale), facilitation playbooks,…
Review collection and online-reputation specialist for SaaS products -- G2, Capterra (now G2-owned), Trustpilot, Product Hunt, AppSumo, and Software Advice. Covers platform selection, profile setup, in-product review-request UX (timing, two-step pattern,…
Audit superledger-app source for supabase.rpc() / .from() calls that ignore the returned `error` field — the silent-failure trap (CLAUDE.md
Operational runbook authorship specialist covering canonical templates (break-fix, scheduled operation, diagnostic), the no-implied-context audit protocol, exact-command discipline, escalation path architecture, rollback procedure standards, runbook-as-test…
Audits the Hivemind codebase (TypeScript / Node >=22 / ESM CLI + MCP server + Deep Lake persistence + six harness integrations) for vulnerabilities and remediates every Critical and High finding in-session. Encodes pre-researched 2025-2026 vulnerability…
Optimizes Next.js 14+ App Router applications for the three parallel discovery systems — traditional search (Google, Bing), AI Overviews / Featured Snippets, and AI assistants (ChatGPT, Perplexity, Claude). Use when the user says "audit SEO", "optimize for AI…
Shared skill
Slack app development specialist for Bolt SDK (JS/Python/Java), slash commands, Block Kit UI composition, modals, Events API, OAuth multi-workspace install, and App Directory submission. Use when the user says "build a Slack app", "add a slash command",…
Genuine organic social strategy for solo developers, founders, and teams up to ~10 people. No AI-generated posts, no cross-post automation slop, no bought followers. Covers platform selection (LinkedIn / X / Threads / Bluesky), founder-led authentic voice,…
Public status page specialist for React/Next.js and SaaS products — platform selection (Statuspage/Atlassian, Better Stack, Instatus, Cachet OSS), component tree architecture, incident communication templates (initial/update/resolution), subscriber…
Phase 2 of the Legion AI Tools Factory pipeline. Takes a completed Command Brief AND a pre-populated `research/` folder authored by `scripture-historian`, names the Stinger (Cursor skill), scaffolds the rest of the skill folder structure under…
Writing docs well -- the Diataxis framework (tutorial / how-to / reference / explanation), inverted-pyramid prose structure, scannable headings, code-example discipline, the "what does the reader already know?" reader-lens, ghostwriting vs voice consistency,…
Telegram Bot specialist — Bot API (up to 10.0 / May 2026 including guest mode and managed bots), grammY v1.x (TypeScript, recommended) and aiogram 3.x (Python), webhook vs long-polling decision with quantitative thresholds, Telegram Mini Apps initData…
Terminal productivity specialist - Bash/Zsh/Fish configuration, modern CLI tools (ripgrep, fd, fzf, bat, eza, zoxide), shell scripting best practices, dotfile architecture, tmux/Zellij setup, and just/make task automation. Use when the user says "improve my…
End-to-end PRD execution orchestrator. Use this skill whenever the user wants PRDs executed to 100% completion with sub-agent waves, acceptance criteria tracked to zero open items, worker-bee quality/security loops, and a commit-push-PR-CI pipeline. Trigger…
Equips `the-queen` to drive the Legion AI Tools Factory pipeline end-to-end for exactly ONE Bee-forging cycle. Encodes the move-before-work invariant, the strict FIFO pickup protocol, the five-phase dispatch order (command-center -> scripture-historian ->…
Reviews, refactors, and authors modern TypeScript/Node code as practiced in Hivemind (@deeplake/hivemind) - strict ESM on Node 22, tsconfig Node16 module resolution + ES2022 target, esbuild multi-harness bundling with sync-versions/define, Vitest discipline…
Typography and font-loading specialist for web products — variable fonts, Google Fonts vs Fontsource vs self-host, the FOIT/FOUT/FOFT loading story, font-display semantics, fluid type scales via clamp(), vertical rhythm, and the type-token architecture. Use…
Enforces a product's design system end-to-end — opens the source-of-truth folder first, cites governing sections, specifies pixel-perfect deltas in token-named terms, and applies per-library integration rules for shadcn/ui, Mantine, Lucide-react, and Framer…
Tier-2 autonomous remediator for the Superledger watchdog. Reads watchdog_alerts WHERE next_tier=claude_pr every 30 min, classifies each one, opens code-fix PRs for known patterns, and surfaces unclear ones as chips. Use when /schedule fires the…
Builds production-grade SvelteKit (Svelte 5) + Payload CMS + Supabase websites end-to-end from a brief, applying a 12-phase playbook. Default CMS mode is Payload 3.x (self-hosted Next.js on Vercel, consumed via REST from SvelteKit). Fallback CMS mode is…
Equips wiki-worker-bee with the 13-type code entity catalog, tree-sitter AST extraction patterns (the repo's own src/graph approach), ADR detection from commit messages, the active four-artifact contradiction protocol, and canonical knowledge-page templates…