File Ops

har-debugger

by hynguyenvk-itr

Analyze HAR (.har) files alongside a bug description to identify slow, failed, or abnormal requests, correlate them to symptoms, and produce a concise root-cause report with evidence and next steps.

prd-to-json

by Tmeister

Convert .prd PRD markdown into .prd/prd.json with validation.

copilotkit

by CopilotKit

Use when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.

google-search

by YPYT1

Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.

wp-trac-search

by sirreal

Search WordPress Trac tickets

jq

by zhongjis

Extract specific fields from JSON files efficiently using jq instead of reading entire files, saving 80-95% context.

bybloshq

by Mwvndva

mcp-to-skill

by mengbo

Convert MCP server configuration to Agent Skill. Triggered when users mention "MCP to skill", "convert MCP service to skill", "generate MCP skill", "MCP conversion" or similar requests. Supports reading configuration from conversation context or file path.

truth-shield

by BAS-More

"Fact-verification layer v3 — catches hallucinations using 10 verification tiers, self-consistency sampling, isolated-context verification (CoVe), package existence checking (DepScope), and multi-judge arbitration. Cross-checks claims against local files, stored knowledge, live docs, web search, multi-model cross-check, and external fact-checkers. Every contradiction is persisted so the same lie is never repeated. MANDATORY TRIGGERS: 'verify this', 'truth-check this', 'fact-check this', 'shield this', 'truth shield', 'truth-shield', 'is this true', 'check your work'. STRONG TRIGGERS: 'are you sure', 'really?', 'source?', 'prove it', 'how do you know', 'is that right', 'double-check that'. PASSIVE MODE: 'shield on' / 'shield off'. Do NOT trigger on opinions, creative writing, brainstorming, or subjective preferences."

notion

by moldable-ai

Use Notion via aivault-backed capabilities (search, pages, blocks). No Notion API key is ever read by the skill runtime.

solarwinds-logs

by jakenuts

Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the logs CLI tool to be installed.

codeql

by aleister1102

Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on "run codeql", "codeql scan", "codeql analysis", "build codeql database", or "find vulnerabilities with codeql". Supports "run all" (security-and-quality suite) and "important only" (high-precision security findings) scan modes. Also handles creating data extension models and processing CodeQL SARIF output.

copy-editing

by Jackiexiao

"（中文）When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes."

jszip

by yusenthebot

Create, read and edit .zip files with JavaScript http://stuartk.com/jszip. Use when: reading and writing files with extras; directory operations; file pattern matching. NOT for: database replacement; network storage without proper SDKs.

update-cursor-settings

by janjaszczak

Modify Cursor/VSCode user settings in settings.json. Use when the user wants to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

ml-experiment-workflow

by Bardli

Use when starting, iterating, or documenting an ML / medical-imaging experiment in a self-contained folder — covers the L0–L4 information hierarchy (code → CSV → visualizations → PLAN.md → SUMMARY.md), PLAN.md/SUMMARY.md document lifecycle, versioned results folders for buggy vs fixed runs, required per-version visualizations, mandatory wandb logging with a documented metric table, detached background training, watchdogs, docs/INDEX.md cross-referencing, and archival of superseded design docs. Triggers — "set up experiment folder", "new finetune run", "v2 of this experiment", "results changed because of a flag", "write up the experiment", "archive this design doc", "make me a plot to check", "what metrics are we logging".

community-campaign-builder

by Andy160675

Build grassroots political campaign strategies integrating music promotion, community networking, and multi-platform outreach. Use when creating independent MP campaigns, community advocacy campaigns, or grassroots political movements requiring music-driven promotion and social media automation.

opencode-config-audit

by markfred5377

Comprehensive configuration audit skill for OpenCode desktop application. Detects configuration errors, security issues, duplicate files, and optimization opportunities. Supports self-check of installed skills.

image-assistant

by qingchunwuhui

配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词；先定“需要几张图+每张讲什么”，再压缩文案与隐喻，最后输出可直接复制的生图提示词并迭代。

index-manage

by adilasif

This skill should be used when the user wants to create, update, delete, or troubleshoot semantic search indexes. Trigger phrases include "index this codebase", "update the index", "refresh the index", "delete the collection", "check index status", "semantic search isn't working", or "why isn't it finding". Use for index administration, not for searching.

how

by ddaanet

Recall procedural knowledge from project decisions. Triggers on "how to do X", step-by-step techniques, or implementation guidance needs. Invoke with "/how <trigger>".

adm-zip

by yusenthebot

Javascript implementation of zip for nodejs with support for electron original-fs. Allows user to create or extract zip files both in memory or to/from disk. Use when: decompress zip files directly to disk or in memory buffers; compress files and store them to disk in .zip format or in compressed buffers; update content of/add new/delete files from an existing .zip. NOT for: database replacement; network storage without proper SDKs.

go-function-analysis

by BizShuk

Analyze Go function lengths within a workspace and generate statistics (p50, p90, p99). Use when you need to audit function complexity, identify long functions, or generate code metrics for Go projects. Only analyzes files matching */.go within the current workspace, excluding dependencies.

model-123

by phic2025

End-to-end clinical prediction model research workflow for Codex. Use when the user asks to review or optimize a prediction-model research proposal, search or synthesize literature for study design, inspect raw clinical datasets, finalize a protocol, run reproducible statistical analysis and machine-learning modeling, generate tables and publication-quality figures, review the analysis process, propose improvements, or draft a complete Chinese manuscript for a clinical prediction model study.