Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
6448 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| avoid-duplicate-system-messagesalivirgo/Major-AI-SkillsConsolidate repeated system instructions into a stable prompt prefix when configuring an application's prompt caching. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| binary-file-suppressionalivirgo/Major-AI-SkillsDetect binary, compiled, and media files before text ingestion so agent context contains readable source and metadata. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| browser-subagent-task-boundingalivirgo/Major-AI-SkillsDefine a browser subtask's target, step budget, completion criteria, and return format before delegating navigation. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| build-your-ai-common-sense-habitalivirgo/Major-AI-SkillsBuild a repeatable prompting habit around clear goals, relevant context, verification, and human review. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| cached-system-instructionsalivirgo/Major-AI-SkillsStructure stable system instructions and variable input separately when configuring supported prompt-cache workflows. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| chromadbalivirgo/Major-AI-SkillsBuild and operate Chroma collections for RAG: PersistentClient vs HttpClient, embedding-function contracts, metadata/where filters, and dimension-safe upsert/query paths agents routinely break. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| compact-yaml-frontmatteralivirgo/Major-AI-SkillsWrite concise YAML metadata for skills and documents with clear names, descriptions, and supported routing fields. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| compressed-system-promptsalivirgo/Major-AI-SkillsShorten repeated system-prompt wording while preserving task scope, requirements, and instruction priority. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| gcloud-clialivirgo/Major-AI-SkillsOperate gcloud with named configurations, ADC vs CLI auth, Workload Identity Federation, and project-scoped GKE/Cloud Run/GCS workflows agents mis-target. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| grafanaalivirgo/Major-AI-SkillsBuild operable Grafana dashboards with template variables, provisioning-as-code, and unified alerts wired to Prometheus/Loki; avoid high-cardinality panels agents love to ship. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| learn-new-skills-ten-times-fasteralivirgo/Major-AI-SkillsPrioritize core concepts, explain them in plain language, and practice retrieval when learning a new subject. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| llm-cost-latency-benchmarkalivirgo/Major-AI-SkillsBenchmark AI workflow cost and latency with TTFT/TPOT/ITL/e2e percentiles, cache-aware token billing, goodput under SLOs, and a quality floor. Use before claiming a model, prompt, or infra change is cheaper or faster. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| never-paste-private-passwordsalivirgo/Major-AI-SkillsReplace passwords, API keys, payment details, and personal identifiers with placeholders before sharing prompts or examples. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| one-shot-subagent-promptsalivirgo/Major-AI-SkillsWrite self-contained delegated tasks with relevant context, boundaries, completion criteria, and a useful return format. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| openai-apialivirgo/Major-AI-SkillsIntegrate OpenAI Responses (preferred) and Chat Completions with structured outputs, tools, embeddings, retries, and store/privacy controls agents routinely miss. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| prompt-cache-controlalivirgo/Major-AI-SkillsConfigure supported prompt caching around stable instructions and tool schemas, checking current provider behavior and usage metrics. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| prompt-regression-gatealivirgo/Major-AI-SkillsGate prompt, model, tool-schema, or packer changes with paired runs on a frozen eval set, slice-level regression checks, relative baselines, and explicit go/no-go thresholds. Use before merging prompt PRs or swapping models. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| qdrantalivirgo/Major-AI-SkillsOperate Qdrant collections with query_points, payload indexes, HNSW/quantization tuning, and hybrid dense+sparse fusion agents routinely misconfigure. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| reuse-saved-prompt-templatesalivirgo/Major-AI-SkillsCreate parameterized prompt templates for recurring work and keep their assumptions and inputs explicit. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| save-favorite-prompts-cheat-sheetalivirgo/Major-AI-SkillsOrganize reusable prompts in a concise reference with clear task labels and editable placeholders. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| servicenow-desktopalivirgo/Major-AI-SkillsAutomate ServiceNow agent and integration workflows using MID Server, Agent Client Collector, and Table REST APIs. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| shopify-appalivirgo/Major-AI-SkillsShip Shopify apps with session-token auth, HMAC-verified webhooks, cost-aware Admin GraphQL, least-privilege scopes, and uninstall-safe token lifecycle—patterns agents routinely get wrong. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| skip-polite-filler-wordsalivirgo/Major-AI-SkillsShorten repetitive prompt wording while preserving clear instructions and the intended tone. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| speculative-decoding-promptingalivirgo/Major-AI-SkillsUse supported predicted-output or speculative-decoding features for edits with a largely known output and measure their benefit. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| subagent-transcript-indexingalivirgo/Major-AI-SkillsLocate relevant decisions or results in structured subagent transcripts without replaying every historical message. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| system-prompt-minifieralivirgo/Major-AI-SkillsReduce redundant prompt whitespace and repeated wording while checking that requirements remain intact. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| try-different-angles-if-first-failsalivirgo/Major-AI-SkillsReframe an unproductive prompt using a new example, decomposition, or perspective while preserving the goal. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| use-voice-typing-for-fast-promptsalivirgo/Major-AI-SkillsTurn dictated context into a clear prompt with explicit goals, constraints, and corrected names or numbers. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| levelscodezeroexe/levelsConduct the connected level skills as one workflow. Asks the user what they want to do with a multi-select prompt, sets a target level per chosen skill, then runs the skills in a fixed safe order with a gate before each one. Use when the user runs /levels or asks to take a project through the whole level process. | Stars: 2 | Updated | Claude CodeCodex | Unverified | Install |
| levels-helpcodezeroexe/levelsExplain the level skill set to a new user: what it is, which skill to start with, how a run goes, what the arguments mean and what it costs. Read-only and cheap. Use when the user runs /levels-help or asks how the level skills work, what they do or how to start. | Stars: 2 | Updated | Claude CodeCodex | Unverified | Install |