菜单
SkillsMP 已收集 heldernoid/agentic-build-templates 中的 144 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 144 个已收集 Skill。
Edit the visual grid layout of a garden bed, assigning crops to cells on a canvas editor. Use when asked to arrange crops in a bed, draw a planting layout, move crops around, visualize companion planting placement, or check for enemy crop adjacency in a…
原文语言：英语
Plan crop rotations, planting schedules, and companion planting for garden beds and fields. Use when asked to manage a farm, garden, or plot layout; schedule what to plant and when; check companion planting relationships; track rotation history; or generate a…
原文语言：英语
Log crop harvests with yield quantity, quality grade, field, and storage destination. Use when asked to record a harvest, check total yield for a crop or field, filter harvest history by date or grade, view analytics charts, or export harvest data. Triggers…
原文语言：英语
Query and interpret yield analytics data from harvest-logger. Use when asked about yield trends over time, comparing crop performance, finding the best-performing field, analyzing grade quality rates, running season comparisons, or generating data for…
原文语言：英语
Schedule and monitor irrigation zones with weather-aware skip rules and water usage tracking. Use when asked to manage irrigation timing, set up zone schedules, configure rain-based skip rules, check water usage, trigger manual watering, or apply seasonal…
原文语言：英语
Configure and troubleshoot weather-based irrigation skip rules using the Open-Meteo API. Use when asked to set up rain forecast skips, configure rain threshold values, debug why zones are or are not being skipped, check weather cache status, understand skip…
原文语言：英语
Manage per-animal health event records, follow-up scheduling, and treatment cost tracking. Use when asked to add a vet visit note, record a treatment with cost, set a follow-up date, view all events for one animal, filter events by type across the herd, or…
原文语言：英语
Track individual animals, record health events, vaccinations, weights, and breeding events. Use when asked to add an animal to the herd, log a vaccination, record body weight, track a treatment, set up a breeding event, check overdue vaccinations, or view the…
原文语言：英语
Analyze pest pressure trends, identify fields needing intervention, evaluate spray effectiveness, and provide IPM recommendations. Use when asked which fields need spraying, whether a spray worked for a specific pest, how pressure has changed over time, which…
原文语言：英语
Record field scouting observations, track pest and disease pressure, and manage spray application records. Use when asked to log a new pest sighting, check which fields have high pressure, find all codling moth observations, view spray history for a field, or…
原文语言：英语
Interpret soil test nutrient data, identify deficiencies, query trends, and generate comparison reports. Use when asked to identify which fields need lime, find all phosphorus-deficient fields, compare nutrient values between tests, generate a before/after…
原文语言：英语
Record soil test results, track nutrient levels over time, and log soil amendments. Use when asked to add a soil test, check which nutrients are deficient, view field nutrient history, record a lime or fertilizer application, or compare field health across…
原文语言：英语
Configure and troubleshoot sensor data ingest into weather-station-dashboard via MQTT or HTTP POST. Use when asked to set up MQTT broker connection, debug why readings are not appearing, configure a new sensor sending data over HTTP, check MQTT topic…
原文语言：英语
Query live and historical weather sensor data, manage stations and alert thresholds, and retrieve daily summaries. Use when asked to check current temperature, view recent readings for a station, find the highest temperature recorded this week, dismiss an…
原文语言：英语
Record, replay, and debug LLM agent runs. Use when you need to: capture agent step sequences (tool calls, LLM calls, events), replay a run step-by-step, diff two runs to find what changed between a passing and failing run, search across all recorded runs, or…
原文语言：英语
Submit agent run data to agent-debugger via the ingestion API. Use when you need to understand the ingestion wire format, troubleshoot ingest errors, batch-submit steps, or integrate agent-debugger into a new language or framework. Triggers include "ingest…
原文语言：英语
Route LLM API requests through a unified proxy with rate limiting, caching, and fallback. Use when you need to: call multiple LLM providers from one endpoint, add caching to reduce API costs, implement fallback between providers, enforce rate limits per team…
原文语言：英语
Configure and manage LLM request routing rules in ai-gateway. Use when you need to: direct specific models to specific providers, set up fallback chains, create routing rules by model pattern, or change provider priority. Triggers include "route gpt-4 to…
原文语言：英语
Explore high-dimensional text embeddings visually. Use when you need to: upload texts and compute embeddings, reduce dimensions with UMAP or t-SNE, explore semantic clusters in 2D or 3D scatter plots, find nearest neighbors by text query, label clusters, or…
原文语言：英语
Run UMAP or t-SNE dimensionality reduction on embedding datasets. Use when you need to project high-dimensional vectors to 2D or 3D, tune projection parameters, compare UMAP vs t-SNE results, or poll projection status. Triggers include "project embeddings",…
原文语言：英语
Run LLM evaluation test suites and detect regressions. Use when you need to: test LLM responses against expected outputs, score responses with exact match, regex, or AI judge, compare model performance across runs, detect quality regressions in CI, or…
原文语言：英语
Use an LLM as an automated judge to score responses against a rubric. Use when you need nuanced quality evaluation that can't be done with exact match or regex. Triggers include "score with AI", "llm-judge", "rubric-based scoring", "quality evaluation", or…
原文语言：英语
Web app for creating, editing, and validating JSONL fine-tuning datasets. Checks format compliance for OpenAI, Anthropic, and Llama formats, detects duplicates, scores quality, and exports clean datasets.
原文语言：英语
JSONL format guide for LLM fine-tuning. Covers OpenAI, Anthropic, and Llama formats, format validation rules, conversion between formats, and quality checklist.
原文语言：英语
In-browser token counter for GPT and other LLM models using tiktoken WASM. Use when you need to count tokens in a text, visualize how text is tokenized, compare token counts of two texts, estimate API costs, or save text snippets for later reference. Triggers…
原文语言：英语
Reference guide for cl100k_base tokenization and LLM cost optimization. Use when you need to understand how the GPT tokenizer works, why text splits the way it does, estimate token counts for common content types, understand context window limits, or find…
原文语言：英语
Plan, schedule, and publish social media posts across Twitter/X, LinkedIn, and Instagram from a single self-hosted calendar interface. Use when asked to schedule social posts, manage a content pipeline, preview platform-specific formatting, or bulk-import a…
原文语言：英语
Publish content to Twitter/X, LinkedIn, and Instagram via the content-calendar API. Use when asked to post to social media, schedule a tweet, publish a LinkedIn update, or post to Instagram through the content-calendar system. Triggers include "post to…
原文语言：英语
Operate the notification-hub API and web interface to manage notifications from GitHub, Slack, and Email sources.
原文语言：英语
Set up and maintain GitHub OAuth2 and Slack Bot Token integrations for notification-hub.
原文语言：英语
Handle file upload, validation, processing pipelines, and temporary file management in Node.js servers. Use when building file processing APIs with Express and multer, managing temporary files with cleanup, or implementing secure file handling patterns.…
原文语言：英语
Process PDF files with merge, split, rotate, compress, watermark, and password operations via a self-hosted web UI and API. Use when asked to combine PDFs, extract pages, reduce file size, add watermarks, or protect documents with passwords. Triggers include…
原文语言：英语
Implementation patterns for the pomodoro-dashboard timer engine, stats aggregation, and localStorage persistence layer. Use when building or modifying the core tracking logic.
原文语言：英语
Browser-only Pomodoro timer SPA with task tracking, focus stats, and a 12-week activity heatmap. All data stored in localStorage. No backend required.
原文语言：英语
REST API integration for qr-code-generator. TypeScript request helpers, batch pipeline patterns, and server-side code examples for embedding QR generation into other applications.
原文语言：英语
Generate QR codes via the web UI or REST API. Supports URL, WiFi, vCard, and plain text. Outputs SVG and PNG. Includes logo embedding and bulk CSV generation.
原文语言：英语
Rename files in bulk using pattern-based rules, regex capture groups, numbering sequences, case conversions, and date-based renaming. Use when renaming multiple files at once, adding prefixes/suffixes, numbering files, or organizing files by date. Triggers…
原文语言：英语
Build rename patterns using batch-renamer's pattern variable syntax for bulk file renaming. Use when constructing or understanding rename pattern strings, combining variables like {name}, {ext}, {index:N}, {date}. Triggers include "rename pattern", "pattern…
原文语言：英语
Set up and manage the clipboard-history background daemon. Use when configuring automatic clipboard capture, troubleshooting the daemon, or setting up auto-start on login. Triggers include "clipboard daemon", "auto-capture clipboard", "clp daemon", "start…
原文语言：英语
Access persistent clipboard history from the terminal. Use when retrieving previously copied text, searching clipboard history, or restoring old clipboard content. Triggers include "clipboard history", "what did I copy", "clp", "paste old content", "clipboard…
原文语言：英语