Context & AI engineering
25,729 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
opelpleple/meta-skills/context-budget Skill
0★ repoAudits what is currently consuming the context window — system prompt, tool definitions, conversation history, attached files, retrieved docs — locates the bloat, and cuts or compresses the lowest-value tokens, treating context as a finite budget to be spent deliberately. Use this skill when the user says "context is full", "what's eating my context", "prune this prompt", or "make this cheaper/faster"; when runs feel slow or costly; when too many tools or huge files are loaded; or whenever you need to reclaim room before continuing.
opelpleple/meta-skills/handoff Skill
0★ repoWrites a self-contained brief that lets a fresh agent, a colleague, or a more capable model pick up the work cold — capturing goal, current state, decisions, gotchas, and next steps so nothing is lost across a context boundary. Use this skill when the user says "hand this off", "brief the next person", "write a handoff", or "escalate this with full context"; when ending a session or before a context reset; when switching models or delegating to a sub-agent; or whenever work must cross from one context into another without loss.
opelpleple/meta-skills/scratchpad Skill
0★ repoOffloads notes, todos, decisions, and intermediate findings to an external file outside the context window, then pulls only the relevant pieces back when needed — giving the agent persistent memory that survives context limits and resets. Use this skill when the user says "take notes", "keep track of", "remember this for later", or "make a checklist"; when a task is multi-step or spans many tool calls (roughly 20+); when intermediate findings would otherwise be lost; or whenever you're accumulating state that doesn't need to sit live in the context window.
usrrname/agent-skills/.opencode/skills/agent-communication Skill
no license0★ repoConcise, technically-precise response style with kawaii flourishes (emojis, emoticons, otaku suffixes). Use when the user wants playful agent output while keeping technical accuracy and brevity.
usrrname/agent-skills/skills/handoff Skill
no license0★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 13 other repositories
usrrname/agent-skills/skills/prune-memory Skill
no license0★ repoAudit the current project's memory store (`~/.claude/projects/<encoded-cwd>/memory/`) and prune memories that no longer match the project state — dead file/function/flag references, past-dated project memories, orphaned index entries, and duplicates. Suggests candidates with rationale and requires per-item confirmation before deleting; does not edit memory bodies. Use when the user says "prune memory", "clean up memory", "audit memory", "memory is stale", "remove old memories", or invokes /prune-memory.
relexyou/relex-claude/plugin/skills/relex Skill
0★ repoUse for ANY Relex work — setting up Relex, starting or running a case, drafting documents, parties, attachments, payments, collaboration, or client/guest invitations. Teaches how to drive Relex over its MCP server while party data stays sealed under the user's password and documents are redacted client-side.
QrCommunication/skills/skills/orchestrate/skills/prompt-creator Skill
no license0★ repoCreate and optimize LLM prompts (system prompts, user prompts, agent instructions, few-shot pipelines). Use when writing prompts for Claude, GPT, Gemini, or any LLM — especially when output quality matters, prompts will run at scale, or the user is building an AI product. Covers prompt architecture, technique selection, model-specific tuning, and failure diagnosis.
aliasunder/agent-plugins/plugins/ship-check/skills/pr-review Skill
0★ repoPlugin marketplace for Claude Code and Claude Cowork — fresh-eyes code review agents, workflow orchestrators, and specialized skills
muxammadmamajonov/dot-claude/.claude/skills/mcp-integration Skill
0★ repoUse when a task needs an MCP server (database, issue tracker, cloud, browser) — never assume access, ask the user to configure, least privilege, confirm destructive calls, treat output as untrusted.
muxammadmamajonov/dot-claude/.claude/skills/memory-management Skill
0★ repoUse when deciding where information lives across sessions — project memory (CLAUDE.md) vs docs-as-memory (specs, ADRs, assumptions) vs user memory — and rehydrating context on resume.
muxammadmamajonov/dot-claude/.claude/skills/search Skill
0★ repoUse for search/relevance features. Triggers — full-text, faceted, autocomplete, vector/semantic/hybrid search, Elasticsearch, OpenSearch, Meilisearch, Typesense, pgvector, Qdrant, Pinecone.
karuhi/ordito/.claude/skills/ordito-init Skill
0★ repoScaffold Ordito into a repository — create ordito.config.json, the docs IR directory, a starter page, a collection (nav), and a GitHub Pages deploy workflow (.github/workflows/docs.yml). Use this once when setting Ordito up in a new repo for internal developer docs (after the .claude/skills + bundled engine have been copied in, e.g. via scripts/install-into.sh). Idempotent: existing files are left untouched unless force:true. Does NOT generate HTML (run ordito-generate after) and does NOT ask for confirmation; the calling agent owns that.
nhattrung0911/shipwright/skills/securing-applications Skill
0★ repoUse when building or reviewing anything that handles untrusted input, authentication, authorization, secrets, user data, PII/privacy, payments, file uploads, CORS/headers, external dependencies, LLM/AI features, or deployment config — and as a mandatory gate before shipping or claiming a feature done. Covers OWASP Top 10:2025 + LLM risks + data privacy. Stack- and agent-agnostic.
SkillMedev/customer-support-copilot/skills/kb-article-writer Skill
0★ repoTurns a resolved support ticket into a clear, searchable knowledge-base or help center article. Use when someone asks "write a KB article from this resolved ticket", "turn these resolved tickets into help center articles", or "write an internal knowledge base article for our support agents" - converting ticket resolutions into self-service documentation that deflects future tickets. Do NOT use for writing user-facing how-to guides from scratch - use help-documentation instead.
The same file is in 1 other repository
cody-hutson/pmo-platform/core/skills/eval-writer Skill
no license0★ repoAuthors rigorous eval suites for AI agents, skills, and LLM systems — grounded in the 2026 eval-writing consensus (trace-driven error analysis, binary LLM judges, cross-family validation, α/κ agreement). Produces characterization, failure taxonomies, judge prompts, rubrics, and calibration protocols that harnesses (pmo-skill-refiner, CI) then execute. Two modes — Author (write from scratch) and Review (audit against the framework). First-class playbooks for per-skill evals and for pipeline stage-gate judgment content; generic fallback for arbitrary AI systems. Use whenever the user asks to write evals, audit evals, add eval coverage, calibrate a judge, build a rubric, write a judge prompt, or diagnose why a judge keeps passing broken outputs.
cody-hutson/pmo-platform/core/skills/finops-usage-extractor Skill
no license0★ repoExtracts per-session and subagent token-spend from local Claude Code sessions into the operator- local, git-ignored FinOps usage store, rolls it up to its work item, reports windowed spend and trends by work item, worktree, skill, MCP and model, and ESTIMATES a planned item's token cost from historical comparables — with a stated basis and confidence, declining below three comparables rather than implying false precision. Read-only; every figure carries its provenance and prints to stdout. Distinct from context-budget-auditor, which measures STATIC corpus footprint; this measures RUNTIME session spend. Triggers: "extract token usage", "refresh the finops store", "how much token spend", "run the finops extractor", "roll up token usage", "attribute token spend", "report token spend", "finops report", "spend by work item", "token spend trend", "where did the tokens go", "estimate token cost", "how many tokens will this take", "finops estimate", "token budget for this work item", "estimate vs actual token spend".
cody-hutson/pmo-platform/core/skills/prompt-builder Skill
no license0★ repoBuilds and improves prompts of every kind — everyday Claude prompts, SKILL.md instruction bodies, skill descriptions, and agent/system prompts. Detects mode from input: critique-and-rewrite when the user pastes a draft, interview-and-build when the user describes a goal without a draft. Always does live web research on current Anthropic prompting guidance before producing output. Returns a short critique plus a copy/paste-ready prompt block. Use whenever the user asks for help writing, improving, rewriting, critiquing, sharpening, or scoping a prompt — including phrases like "help me write a prompt for…", "improve this prompt", "make this better", "what's wrong with this prompt", "rewrite this", "I need a system prompt for…", "draft a SKILL.md description for…", "write a prompt for", "sharpen this prompt", or whenever the user shares a block of text that is clearly an LLM prompt and asks for any kind of feedback or revision.
cody-hutson/pmo-platform/operations/skills/ppm-agent Skill
no license0★ repoThe strategic brain of the PMO — reads any project artifact and pushes every actionable item toward resolution. Use when uploading transcripts, asking about project status, needing decisions framed, or requesting risk assessment. Triggers: "review this", "what's the state of [project]", "process this transcript", "triage this", "what needs my attention", "what actions came out of this", "what needs to surface."
cody-hutson/pmo-platform/release/skills/build-reviewer Skill
no license0★ repoConducts final production-readiness review of any governed document pack — Copilot Builder Agent, PMO platform, or generic — using the shared review discipline (see `core/disciplines/review-discipline-principles.md`). Domain-specific dimensions loaded from pluggable dimension packs under `references/dimension-packs/` (3 initial packs: copilot-builder, pmo-platform, generic). Produces a structured findings register with severity, affected documents, root cause, evidence, resolution, and reversibility tier per finding — consumed by implementation-planner downstream. Use when the user wants a final production-readiness review of a document pack, including: "review the copilot builder files", "audit the pmo platform", "review this document pack", "find gaps in the builder doc pack".
cody-hutson/pmo-platform/release/skills/implementation-planner Skill
no license0★ repoConverts build-reviewer findings registers into sequenced, minimal-change remediation implementation plans for any governed document pack — Copilot Builder Agent, PMO platform, or generic. Domain-specific planning context loaded from pluggable domain packs under `references/domain-packs/`. Applies the Minimal-Change Remediation Bias and classifies every confirmed finding to one of 8 remediation types (RT-1 text correction through RT-8 accepted residual). Produces implementation records (RI-NNN) as Edit-ready specs and Bash scripts directly consumable by Claude Code's native tools per the reference workflow in `release/references/how-to/implementation-execution-pattern.md`. Use when the user has a build-reviewer findings register ready for planning, needs remediation sequencing, or wants to plan the fixes before execution.
scoobydrew83/skills/plugins/coordinated-skills/skills/conductor-memory Skill
0★ repoExtract and build a complete memory pack from a Claude conversation or session, synthesizing it into vault-ready artifacts so the next session resumes with full context. Produces a conversation summary, artifact index, communication-style and project-context notes, a machine-readable seed JSON and persona YAML, verification and maintenance checklists, and a generalized integration.py that copies the pack into an Obsidian vault and updates a Claude Code resume pointer (with an optional MCP/vector-store hook). Use this whenever the user says 'build conductor memory', 'extract memory from this conversation', 'capture this session', 'snapshot our progress', 'save this to memory', or 'update conductor memory' - and also when wrapping up a substantial working session that should persist for continuity across Claude Code, Obsidian, or MCP, even if they don't say the word 'memory'. Built for the Conductor Method continuity system; works for any project needing durable cross-session memory.
scoobydrew83/skills/plugins/coordinated-skills/skills/drift-check Skill
0★ repoAudit a set of related project documents for internal contradictions and drift from their stated mission, with a skeptical eye that distrusts suspiciously clean alignment. Use whenever the user points at multiple docs (spec, PLANNING.md, README, CLAUDE.md, .cursorrules, system prompt, TASK tracker, ADRs) and asks "are these consistent", "do my docs agree", "has my spec drifted", "check alignment", "is my README in sync", "audit my project for consistency", or shares a self-alignment/audit report. Especially trigger when documents should agree on the same facts (tech stack, metrics, feature lists, naming, architecture, tone) and the task is finding where they silently diverge, or where identical copy-pasted claims masquerade as validation. Lead with the real state of alignment and the biggest contradiction, never a vanity score. For cross-document consistency and mission-drift within a project's own materials, not verifying external claims (use reality-check) or choosing between options (use a council skill).
scoobydrew83/skills/plugins/coordinated-skills/skills/loop-creator Skill
0★ repoDesign and generate autonomous/semi-autonomous AI work loops and the prompts that drive them — builder/verifier (maker/checker) loops, phased build loops, queue-driven multi-task loops, and nightly triage. Every loop it produces has explicit acceptance criteria, a verifier separated from the builder ("close is FAIL"), commit checkpoints, a hard max-iteration + human-escalation stop, and safe stopping conditions. Use whenever the user wants to build a loop, "create a loop", "make a loop creator", set up a self-correcting or maker/checker loop, write prompts for a loop, design an evaluator-optimizer or agentic loop, scaffold a LOOP_QUEUE, or wire a nightly triage workflow — even if they don't say the word "loop" but describe an iterate-until-it-passes process. When (and only when) the request says to look at a codebase or use Claude Code, it inspects the repo read-only and emits a headless Claude Code harness. Defaults to the Conductor Method conventions, all clearly overridable.
scoobydrew83/skills/plugins/coordinated-skills/skills/project-postmortem Skill
0★ repoGenerate an evidence-grounded project retrospective — pulled from git history and decision docs, not memory — that grades the project on separate dimensions, splits what went right from wrong, reduces the failure to its root ordering error, extracts transferable lessons for the next project, and names what survives. Use whenever a project ships, stalls, or gets sunset and someone wants the writeup — "post-mortem", "retrospective", "what went wrong with X", "we're sunsetting X, write it up", or mid-project "why did this go sideways". The method cites commit hashes or sources for every claim, builds a timeline of when validation happened vs building, separates pros from cons including uncomfortable symmetries, and ends with a per-dimension scorecard plus a what-survives list — then runs a check that fails any vanity scorecard or uncited narrative. Distinct from drift-check (audits live docs) and conductor-memory/session-bookend (capture session state for continuity); this extracts backward-looking lessons.
scoobydrew83/skills/plugins/coordinated-skills/skills/prompt-template-generator Skill
0★ repoAnalyze a software project's files and generate a tailored, copy-paste-ready prompt-template cookbook (a Markdown "PROMPT-TEMPLATES.md") with the project's real stack, paths, subsystems, and conventions already filled in. Use this whenever the user wants to create prompt templates, a prompt cookbook, a prompt library, prompt scaffolding, reusable AI-coding prompts, or a "prompt template generator" for a codebase — or says things like "make prompt templates for my project", "build a prompt guide for this repo", "generate copy-paste prompts for my codebase", or "turn my project into a set of reusable Claude/Cursor prompts". Trigger it even when the user just points at a project and asks for ready-to-use prompts, since the value is filling templates with project-specific facts they'd otherwise type by hand.
scoobydrew83/skills/plugins/coordinated-skills/skills/system-prompt-builder Skill
0★ repoInterview-driven builder for enterprise-grade AI system prompts and agent architectures. Use whenever the user wants to design, build, scaffold, or rebuild a system prompt, custom assistant, AI agent, project instructions, custom GPT, multi-agent system, or any reusable LLM instruction set. Trigger on phrases like "build me a prompt system", "design an agent", "write system instructions", "turn this into an agent", "create project instructions", "I want an AI that does X reliably", or any request to architect how an AI should behave across many future interactions — even when the user never says the words "system prompt." Also trigger when the user pastes an existing system prompt and wants it rebuilt, hardened, or extended.
BryceEWatson/claude-global-skills/fable-seat Skill
0★ repoOperating profile for a Claude Code session whose model is Fable (`claude-fable-5`) — the dials that make a Fable-led session run cheaply. Effort defaults to `high` and steps DOWN for routine work (not `xhigh` by reflex); task framing leads with the outcome instead of prior-model step-by-step scaffolding; the prompt cache stays warm by farming cheap work to a subagent rather than inline-switching the main loop's model; long runs get a task budget plus context compaction; and durable state lives on the memory surface. Apply ONLY when the session model is Fable — it is a genuine NO-OP on Opus and every non-Fable model. This is Fable-mechanics guidance, NOT a superiority claim (it does not assert Fable beats Opus). Use it when you're running Fable and want to set the operating dials, before kicking off a long agentic run on Fable, or when asked "how should I run Fable", "Fable operating profile", "Fable seat", "calibrate for Fable", "am I running Fable cost-efficiently".
BryceEWatson/claude-global-skills/global-review-loop Skill
0★ repoMine ALL of your local Claude history across EVERY project (both corpora — Claude Code CLI and Cowork local-agent-mode) for operator friction that recurs across MULTIPLE projects, then propose GLOBAL ~/.claude leverage (a CLAUDE.md rule, a new/edited global skill, a memory, or a settings hook) to fix it — each proposal reconciled against what already ships globally, self-validated by an adversarial /review-loop --mode claim loop, and recorded in a cross-run ledger so nothing is re-proposed, dismissed-twice, or shipped on its own say-so. DISTINCT FROM: signal-scan (one repo → that repo's .claude/ config), command-retro (Command's own logs → Command's queue), and transcript-analysis (ONE project, Cowork-only, proposes that project's CLAUDE.md candidates). This skill is the GLOBAL, cross-project layer: it only surfaces friction proven to recur across >=N DISTINCT projects (counted by cwd-PATH attribution only) and only ever proposes changes to ~/.claude. Invoke as /global-review-loop. Triggers: "what global rule should I add", "what recurs across my projects", "fleet-wide friction", "improve my global Claude config from how I actually work".
BryceEWatson/claude-global-skills/monitor-agent-thread Skill
0★ repoMonitor a live or recent Claude Code or Codex thread from the other product using local append-only session logs, safe event extraction, Git/worktree evidence, and recurring heartbeats. Use when the user asks to watch, babysit, follow, monitor, check progress on, or notify them about another Claude Code/Codex session, including Claude-to-Codex and Codex-to-Claude monitoring.
BryceEWatson/claude-global-skills/session-handoff Skill
0★ repoAlias of `session-end` (this skill was renamed). Ending / closing out a session — and handing it off when work is mid-flight — now lives in session-end; "handoff" is its mid-flight mode. Invoking this just routes to session-end so old muscle memory ("/session-handoff") keeps working.
BryceEWatson/claude-global-skills/session-portal Skill
0★ repoSafe bidirectional message portal between Claude Code and Codex sessions. A durable local SQLite queue with an authenticated stdio MCP interface lets one session drop a short, authored message into another session's inbox; delivery is pull-only, so the recipient itself picks it up at a safe turn boundary, acknowledges, and acts under its own permissions. Identity is derived from a bearer token (not caller-asserted) and elevated actions need operator grants. Never writes transcripts, never pushes into or resumes another session, never runs message content. Use to hand a follow-up from Claude Code to Codex (or back) without manual relay. Monitoring stays separate and read-only (monitor-agent-thread).
search-atlas-group/amm-founding-circle/skills/agent-runbook Skill
0★ repoRouting runbook for engineering tasks across the agent stack (ao spawn, GSD, OMC, /goal, /loop, /schedule, inline, codex, gemini, Claude Flow swarm). Use when uncertain which execution mode to choose, before any non-trivial action. Outputs a composed pipeline, not just one mode. Hard rules and gates live in global CLAUDE.md; this skill is the HOW for routing.
search-atlas-group/amm-founding-circle/skills/agent-usage Skill
0★ repoShow accurate Claude/Codex account usage from provider quota APIs where exposed and local session ledgers otherwise.
search-atlas-group/amm-founding-circle/skills/building-autonomous-agents Skill
0★ repoThe mental model behind an always-on system — a tool is something you invoke, an agent is something that runs, and the gap between them is a trigger. Teaches the Sense → Correlate → Judge → Act → Report loop every agent shares, the two ways to deploy it (a job scheduled on your machine vs. a hosted routine that runs 24/7 even with the laptop closed), the real gotchas that quietly break both, and the Observe → Propose → Act trust ladder that keeps it from doing damage while you sleep. Use when you keep hand-running the same job, when you want to understand what "agentic" actually means before you build, when a "set it and forget it" agent isn't firing on its own, or when you're deciding whether a job should run on your machine or in the cloud.
search-atlas-group/amm-founding-circle/skills/capability-map Skill
0★ repoMap what your agent can actually DO across your stack today versus what's gapped, and learn the two workarounds that bridge a missing action. Use when you've built a good agent but keep hitting a wall where it can read a tool but can't act in it — "everything is 80% and I can't get the last 20% agentic" — usually a write-scope your ad platform, CRM, or form provider doesn't expose to the agent. Teaches you to inventory YOUR OWN stack's coverage (not a fixed platform list), find the exact gapped actions, and pick the right bridge for each one.
search-atlas-group/amm-founding-circle/skills/cli-llm-routing Skill
0★ repoUse installed AI CLIs for second opinions, latest-docs checks, and long-context review. Avoid raw provider API calls unless a project explicitly requires API integration.
search-atlas-group/amm-founding-circle/skills/content-brief-generator Skill
0★ repoUse when planning a new article. The agent Googles the keyword, reads the top 10 results, classifies intent, maps the content gap, and produces a writer-ready brief with structure, outline, and on-page artifacts. No keyword tool required. When a SearchAtlas MCP is connected, leverages SA tools (rank tracking, brand vault, GBP, OTTO, LLM Visibility) first before falling back to generic web search.
search-atlas-group/amm-founding-circle/skills/dispatch-and-brief Skill
0★ repoSplit one big job across several agents running at once — and write each one a tight, self-contained brief so it works its slice instead of burning its effort rediscovering the whole job. This is context engineering made practical: the agent only knows what you tell it, so a good brief is the difference between "five agents at once" being leverage and being five shallow drafts. Teaches split → brief → gate, and how to keep your main conversation lean by delegating the messy work. Use when a job is too big for one pass (a multi-section audit, a batch of pages, a repo-wide cleanup), when parallel agents keep coming back with thin or overlapping work, when your main chat gets clogged with raw output, or when you're on Level 4 and want the split/brief step done right.
search-atlas-group/amm-founding-circle/skills/host-your-agent Skill
0★ repoGet your agent off your laptop. Installs an auto-save hook so an overnight run never loses work, plus a scheduled unattended runner (launchd on Mac / Task Scheduler on Windows / cron on Linux) that fires one of your own recurring jobs on a schedule and leaves a finished morning artifact. Use when you want an agent to run while your machine sleeps, when you're tired of hand-running ./run.sh and babysitting a terminal, when a crash or dead laptop keeps killing a session, or when you want to "set it and forget it" for a job you do every day.
search-atlas-group/amm-founding-circle/skills/instinct-learn-eval Skill
0★ repoScore existing instincts, execute status transitions, prune stale candidates, write scorecard
search-atlas-group/amm-founding-circle/skills/keyword-deep-dive Skill
0★ repoUse when planning to rank for a specific keyword. The agent Googles it, reads the top 10, classifies intent, reads the top 3 competitor pages, and produces a 90-day ranking plan with intent, SERP analysis, and content recommendations. When a SearchAtlas MCP is connected, leverages SA tools (rank tracking, brand vault, GBP, OTTO, LLM Visibility) first before falling back to generic web search.
search-atlas-group/amm-founding-circle/skills/llm-citation-audit Skill
0★ repoAudit whether a brand is being cited by LLMs (ChatGPT, Claude, Perplexity, Google AI Overviews, Gemini) for the prompts its buyers actually ask, diagnose WHY it is or isn't being cited across four distinct failure modes (retrieval gap, entity gap, format gap, competitor moat), and produce a prioritized fix list grouped into quick wins, medium bets, and long-range investments. Use this skill whenever a user asks about AI visibility, LLM citations, AEO/GEO audit, generative engine optimization, "am I showing up in ChatGPT," "does AI recommend my brand," "why isn't Perplexity citing us," "how do we rank in AI Overviews," "LLM SEO," "answer engine optimization audit," or any variant of "are we visible in AI search." Trigger even when the user uses the older SEO vocabulary but asks about AI platforms, because the audit spans both. Chains opportunistically with brand-kit.md for brand name, services, audience, and competitors — if present, pull them automatically instead of re-asking. When a SearchAtlas MCP is connected, leverages SA tools (rank tracking, brand vault, GBP, OTTO, LLM Visibility) first before falling back to generic web search.
search-atlas-group/amm-founding-circle/skills/night-shift Skill
0★ repoRun a bounded overnight AOSwarm-style analysis across recently active repos, using isolated workers to inspect architecture, tests, tooling, performance, safety, and agent-readiness, then synthesize a self-contained morning HTML report. Use for unattended nightly work blocks, architecture review swarms, cross-repo improvement mining, and robust fallback execution across Claude, Codex, and Gemini.
search-atlas-group/amm-founding-circle/skills/prompt-injection-guard Skill
0★ repoProtect agent sessions from malicious or accidental instructions embedded in fetched web pages, documents, transcripts, issue text, screenshots, or logs.
search-atlas-group/amm-founding-circle/skills/security-radar Skill
0★ repoAudit your own agentic setup's security posture. Use when the user asks to check/harden their setup, run a security check on their machine, scan their installed Claude Code skills / MCP servers / project dependencies, or wants a posture brief. Cross-references the installed surface against OSV.dev + npm audit and the OWASP LLM/Web Top 10. Read-only.
search-atlas-group/amm-founding-circle/skills/share-your-foundation Skill
0★ repoPackage the rules, skills, and brand you built in Levels 1–3 into one repo a teammate — or your own second machine — clones and runs a single install command against, so everyone runs the exact same agent setup instead of reinventing it. Turns "here's my setup, good luck" into "clone this, run ./install.sh, you're me." Use when you want to onboard a teammate onto your agent stack, when your own setup won't follow you between machines (your CLAUDE.md / skills / brand kit live on one laptop and not the other), when you keep re-sending config over Slack, or when you're on Level 4 and the "share the foundation with your team" step has nothing runnable behind it.
kumard3/lumbox-skills/lumbox-mcp Skill
no license0★ repoConnect an AI agent to the Lumbox MCP server for email - create inboxes, extract OTPs, wait for verification codes, send/reply/forward, and search email as native MCP tools. Use when wiring Lumbox into Claude Code, Cursor, or any MCP-compatible client.
MauricioQuezadaHaintech/karvey/plugins/karvey/skills/karvey-benchmark-models Skill
0★ repoCross-model benchmark for the Karvey method. Side-by-side comparison of models (e.g. Claude vs GPT vs Gemini) on a skill or task — latency, tokens, cost, and optional LLM-judged quality. Triggers include "karvey benchmark models", "comparar modelos", "compare models", "benchmark de modelos", "model benchmark", "qué modelo conviene", "which model to use", "latencia tokens costo", "latency tokens cost".
MauricioQuezadaHaintech/karvey/plugins/karvey/skills/karvey-second-opinion Skill
0★ repoIndependent cross-model code review for the Karvey method. Get an adversarial second opinion from a different AI model (e.g. Claude vs GPT/Codex/Gemini). Three modes: Review (PASS/FAIL), Challenge (adversarial), Consult. Triggers include "karvey second opinion", "segunda opinión", "cross-model review", "revisión independiente", "codex", "otro modelo".
onyx679/automotive-ve-ai-skills-kit/skills/ve-skill-benchmark-adapter Skill
0★ repoBenchmark community Claude Code, Codex, or AI-agent Skills and adapt their reusable patterns into automotive value-engineering Skill designs. Use when reviewing open-source Skill repositories, deciding whether to reuse an existing Skill structure, or converting a generic Skill into a VE/VAVE workflow with proper evidence, validation, and attribution.
SkillMedev/remotion-video-production/skills/remotion-setup Skill
0★ repoScaffolds a new Remotion video project wired for Claude Code Agent Skills - Node check, create-video scaffold, skills install, folder conventions, Google Fonts, and a smoke-test render. Use whenever someone wants to start making videos with Remotion and Claude, even just "make product videos with Claude."
The same file is in 1 other repository
Sidsaladi9/persona-os/plugins/product-manager-os/skills/skill-creator Skill
0★ repoCreate a new skill for this Product Manager OS — in the same format and quality bar as the built-in skills. Use when the user says "make a skill for X", "add a skill", "I keep doing X manually, turn it into a skill", or wants to extend the OS with their own framework or workflow.
waseemnasir2k26/skynetlabs-all-claude-code/skills/code-quality-and-review/fanout-ship Skill
no license0★ repoParallel multi-agent ship pattern. Decompose 1 parent task into N independent child tasks → spawn N background agents in isolated git worktrees → each opens PR targeting shared integration branch → smallest-first merge order with self-documenting rebase recipes → final PR integration → main. Collapses N×30min sequential work into ~30min wall-clock. Isolated blast radius (one agent crash ≠ kill others). Granular revert. Small review surface per PR. Background execution = no babysit. Trigger when user says: "fan out", "fanout", "split into N PRs", "parallel build", "parallel agents", "spawn N agents", "/fanout-ship", "ship in parallel", or pastes a parent issue + list of child tasks. Auto-trigger heuristic: task list ≥ 4 INDEPENDENT subtasks touching DISJOINT files, single repo, GitHub-hosted.
waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/n8n-skills/skills/n8n-mcp-tools-expert Skill
no license0★ repoExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
The same file is in 2 other repositories
waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/skill-builder Skill
no license0★ repoMeta-skill. Turns a repeated workflow (or "make this into a skill" / "turn what we just did into a skill") into a correct, house-style SKILL.md written to the canonical location. Elicits name + purpose + triggers + inputs + steps + outputs + gotchas, generates valid frontmatter with STRONG trigger phrases (so auto-invocation actually fires), decides CLAUDE.md-vs-Skill, runs a validation checklist (Windows paths, no secrets, runnable steps), and offers to register a /command alias + a one-line MEMORY.md pointer. Tuned for SkynetLabs: this is the consistent mint-press so every new skill matches the existing house pattern (fanout-ship / upwork-proposal / code-audit-fanout style). Trigger when user says: "build a skill", "make a skill", "new skill", "skill-builder", "/skill-builder", "turn this into a skill", "turn what we just did into a skill", "save this workflow as a skill", "I keep doing X, make it repeatable", or describes a workflow they repeat by hand. Auto-trigger heuristic: user describes a multi-step procedure they have run ≥2 times and asks to "save", "reuse", "templatize", or "make repeatable".
waseemnasir2k26/skynetlabs-all-claude-code/skills/seo-content-copy/seo-geo/cross-cutting/memory-management Skill
no license0★ repoPersist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话
waseemnasir2k26/skynetlabs-all-claude-code/skills/token-and-comms/compress Skill
no license0★ repoCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
The same file is in 3 other repositories
eprouveze/claude-skills/skills/codex-write Skill
0★ repoDelegate heavy code generation to Codex CLI while Claude orchestrates, reviews, and surgically fixes. Use for any task involving 50+ lines of new code, boilerplate generation, test writing, or large refactors. Claude acts as lead engineer; Codex acts as developer. Multi-LLM aware — checks `.claude/llm-mode.json` before delegating and falls back to direct write if Codex is unavailable.
eprouveze/claude-skills/skills/mode Skill
0★ repoToggle between single-LLM (Claude-only) and multi-LLM (delegate to Gemini, Codex, or other CLIs) modes. Shows current mode, available external CLIs, delegation stats, and logs. Use when the user says "switch to multi", "use Gemini", "delegation status", "how many delegations", or "token savings". Subcommands: `/mode` (status), `/mode multi`, `/mode single`, `/mode stats`, `/mode reset`.