Explain how a supplied repository works using source evidence, an eighth-grade reading level, and bounded analogies.
原文语言:英语
这个仓库中的 skills
SkillsMP 已收集 legioncodeinc/vibe-coding-tools 中的 302 个 Skill。打开任一 Skill 可查看来源和详情。
legioncodeinc/vibe-coding-tools已展示 40 / 302 个已收集 Skill。
Explain how a supplied repository works using source evidence, an eighth-grade reading level, and bounded analogies.
原文语言:英语
Run the full documentation audit and refresh pipeline on a repository: inventory, writer fleet, grounded citations, adversarial verification, security and quality gates, one ready PR per unit, then the work report in PDF plus markdown and the master suspect…
原文语言:英语
Produce cited audience documents from a library in Markdown, Word and branded PDF. Check source coverage, public boundaries and every final page.
原文语言:英语
Extract code entities into the wiki. Use for atomic pages, backlinks, inferred ADRs, contradiction checks, or wiki linting. Read README.md for the guide map.
原文语言:英语
Turn a library into cited audience packets in Markdown, Word and branded PDF. Use for executive, public, sales, service or engineering documents grounded in existing sources.
原文语言:英语
Select and maintain developer docs sites. Use for Docusaurus, Mintlify, Starlight, Diataxis, search, or docs-as-code CI. Read README.md for the guide map.
原文语言:英语
Full documentation refresh: inventory, writer fleet, grounded citations, adversarial verification, security and quality gates, one ready PR per unit, PDF plus markdown report, master suspect list.
原文语言:英语
Build and maintain API docs. Use for OpenAPI examples, renderer choice, hosting, SDK consumer compatibility, or changelogs. Read README.md for the guide map.
原文语言:英语
Prepares an acquired repository for archival: provenance intake, attribution and PII scrub, docs merge into library/, knowledge-base fleet, identifier rename, verification. Any language or license.
原文语言:英语
Explain technical sources, errors and generated code at grade 8 with bounded analogies, source claims, glossary and teach-back. Read README.md for the guide map.
原文语言:英语
Teach contract-based testing through tiny exercises, failure interpretation and changed conditions. Use for learning assertions without copying implementation. Read README.md for the guide map.
原文语言:英语
Help new coders prepare to build: clarify one goal, learning prerequisites, roles, expectations, unknowns and a first-slice proposal. Read README.md for the guide map.
原文语言:英语
Teach web fundamentals through tiny projects, or prepare an exercise and criterion rubric from one supplied technical source revision. Use attempts, feedback and teach-back. Read README.md.
原文语言:英语
Explain a technical source at grade 8 with a bounded analogy, glossary, evidence and teach-back.
原文语言:英语
Choose a beginner learning path and teach HTML, CSS and JavaScript through one bounded project with observed learning checks.
原文语言:英语
Teach independent tests from a stated contract with prediction, observed attempts, failure interpretation and changed-condition practice.
原文语言:英语
Prepare one source-linked technical exercise, teach-back and criterion-level evidence rubric without assuming mastery.
原文语言:英语
Help a new coder prepare one build goal with learning prerequisites, responsibilities, unknowns and a first-slice proposal.
原文语言:英语
Design vector storage. Use for pgvector schemas, HNSW/IVFFlat, hybrid indexes, migrations, or storage choice. Read guides/ for the decision path.
原文语言:英语
Designs and audits retrieval: full-text search, pgvector recall, hybrid RRF fusion, reranking, chunking, recall quality eval. Use when tuning recall or a search query misses.
原文语言:英语
Build a bounded RAG feature against an accepted corpus, access contract, and measured retrieval and answer evaluation.
原文语言:英语
Design a source-grounded data model, access boundaries, indexes and a migration proposal without executing database changes.
原文语言:英语
Make this Claude Code desktop session TARS, the manager. Spawns chips for what you ask, manages every session to done, fields their questions, uses CASE for proportion and scoped decisions, and KIPP as the Feature Desk, runs a real 10-minute tick and a…
原文语言:英语
Manage Claude Code Desktop sessions. TARS coordinates, CASE advises and breaks scoped ties, and KIPP runs feature intake. Does no implementation. Read README.md for the guide map.
原文语言:英语
Reviews, audits, and extends the AI cognitive layer: coach routing, prompt cascade, RAG, three-tier memory, observability, evaluation. Use when reviewing AI code or tuning retrieval.
原文语言:英语
Neon Postgres and Drizzle ORM on SvelteKit/Vercel: connections, schema, migrations, branching, query patterns, pgvector, RLS, and migrating off Supabase. Use for any Neon or Drizzle task.
原文语言:英语
Design PostgreSQL data layers. Use for schema, indexes, migrations, query performance, ORM choice, or serverless databases. Read guides/ for the decision path.
原文语言:英语
Design and maintain Wasp Nestmind Deep Lake datasets. Use for ColumnDef schemas, healing, versioned writes, or hybrid indexing. Read guides/ for the decision path.
原文语言:英语
Picks and runs embedding models: hosted (OpenAI, Cohere, Voyage) vs self-hosted, cost tradeoffs, batching, caching. Use when choosing, swapping, or debugging an embedding model.
原文语言:英语
Choose AI providers, gateways and local models. Use for AI stack setup, retry and spend budgets, feature margin or local hardware fit. Read guides/ for the decision path.
原文语言:英语
Bifrost AI gateway specialist: maximhq/bifrost architecture, admin and inference API surface, virtual keys, semantic cache, .so plugins, tags, fork freeze and upgrade policy. Use for any Bifrost work.
原文语言:英语
Choose, configure or troubleshoot AI coding tools, and write bounded task briefs. Use for tool comparison, prompt context, task scope, acceptance, ownership and verification.
原文语言:英语
Scan GitHub for repos trending in the last 24 hours (vibe coding, AI coding, AI memory, vulnerabilities) via Exa/Firecrawl MCP, vet ONE, and output post options in the user's voice with receipts.
原文语言:英语
Vet one fresh content opportunity with receipts, source times, duplicate checks, and honest no-post exits.
原文语言:英语
Mine the last 24 hours of trending news via Exa/Firecrawl MCP, fact-check ONE topic, and output viral-ready post options in the user's voice with receipts. Use for scheduled news-post Routine runs.
原文语言:英语
Evidence-backed, read-only security audit of Svelte 4/5 and SvelteKit 2 apps, any stack. Versions vs advisories, load leaks, actions, remote functions, hooks, XSS, CSRF, adapters.
原文语言:英语
Swarm audit of a repository: Workflow fleet of single-lens Sonnet investigators, adversarial verification, Opus interpreters and critic, 10-minute check-ins, kill and respawn, nothing unreviewed.
原文语言:英语
Review React 18/19 security, including Next.js clients. Covers XSS, secrets and client trust. Delegate Next.js server surfaces to nextjs-security-stinger. Read-only.
原文语言:英语
Plan fixes from audit findings. Clusters findings into work packages, orders Now, Next, Later, and with approval writes Library PRDs, IRDs, knowledge docs, and draft contracts.
原文语言:英语
Audit a codebase the way Legion Code Inc. does: foundation health, duplication and dead code, framework-deep security, quality, and a remediation plan, delivered as a branded brief.
原文语言:英语