Skill reviews

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or

• References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/output-versioning.md, ../shared-references/output-manifest.md
• The skill tells the model to perform an irreversible action with no human approval
• 4 referenced file(s) missing: ../shared-references/external-cadence.md, ../shared-references/output-versioning.md, ../shared-references/output-manifest.md

Alibaba Cloud OSS scheduled local-folder sync skill using aliyun CLI, including integrated ossutil commands for incremental upload. Use when the user wants to schedule recurring lo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficientl

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Migrate KMP projects from CocoaPods (kotlin("native.cocoapods")) to Swift Package Manager (swiftPMDependencies DSL) — replaces pod() with swiftPackage(), transforms cocoapods.* imp

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Create new Umbraco backoffice extensions using the official dotnet template

• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Process documents with Nutrient DWS. Use when the user wants to generate PDFs from HTML or URLs, convert Office/images/PDFs, assemble or split packets, OCR scans, extract text/tabl

• References files that are not bundled: scripts/*.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill

Autonomous multi-round research review loop. Repeatedly reviews via external reviewer backend (Codex or manual), implements fixes, and re-reviews until positive assessment or max r

• References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/output-versioning.md, ../shared-references/output-manifest.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Creates a complete EC2 Image Builder pipeline that builds a custom AMI with pre-installed software, distributes it to target regions, executes the pipeline, and creates a launch te

• The skill tells the model to perform an irreversible action with no human approval
• Prose only: no discrete steps
• Does not say what the result is

A guided, zero-friction installer and maintenance assistant for OpenClaw. Use this skill when the user wants to install OpenClaw, set up OpenClaw on a local machine or remote serve

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.5 review. Use when the user says "refine m

• References files that are not bundled: ../shared-references/output-versioning.md, ../shared-references/output-manifest.md, ../shared-references/output-language.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向"

• References files that are not bundled: ../shared-references/external-cadence.md, ../shared-references/output-composition.md, ../shared-references/output-versioning.md
• The skill tells the model to perform an irreversible action with no human approval
• 5 referenced file(s) missing: ../shared-references/external-cadence.md, ../shared-references/output-composition.md, ../shared-references/output-versioning.md

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running an

• References files that are not bundled: ../shared-references/external-cadence.md, ../../tools/watchdog.py
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: ../shared-references/external-cadence.md, ../../tools/watchdog.py

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Use when writing or reviewing Kotlin code that stores CoroutineScope, launches from init/non-suspending APIs, calls runBlocking, or catches broad exceptions around suspend calls.

• References files that are not bundled: ../kotlin-flow-state-event-modeling/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Generates Promoted In-App Purchase setup with StoreKit 2 product configuration, paywall integration, and App Store product page display. Use when setting up promoted purchases that

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Linear process with no failure handling

Generates data export/import infrastructure for JSON, CSV, PDF formats with GDPR data portability, share sheet integration, and file import. Use when user wants data export functio

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start

Graduate a workflow insight from learned/<topic>.md into AGENTS.md as a permanent constraint. Use when a lesson is stable enough to apply to every future session.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• No condition that starts the skill

Use when converting Java source files to idiomatic Kotlin, when user mentions "java to kotlin", "j2k", "convert java", "migrate java to kotlin", or when working with .java files th

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Guidance for using asc cli in this repo (flags, output formats, pagination, auth, and discovery). Use when asked to run or design asc commands or interact with App Store Connect vi

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Databricks Lakebase Postgres: projects, scaling, connectivity, Lakebase synced tables, and Data API. Use when asked about Lakebase databases, OLTP storage, or connecting apps to Po

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

OmniStudio OmniScript creation and validation with 120-point scoring. Use when building guided digital experiences, multi-step forms, or interactive processes that orchestrate Inte

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Expert blueprint for roguelikes including procedural generation (Walker method, BSP rooms), permadeath with meta-progression (unlock persistence), run state vs meta state separatio

• References files that are not bundled: scripts/meta_progression_manager.gd, scripts/roguelike_patterns.gd, scripts/dungeon_generator_walker.gd
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill

Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies b

• References files that are not bundled: scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS response

• References files that are not bundled: ../../CONNECTORS.md
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: ../../CONNECTORS.md

Tunnel SOCKS5 traffic through Google Drive API requests to bypass restrictive networks and DPI inspection.

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is