Skill reviews

Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic template into a per-model config (+ benchmarks) JSX under src/snippe

• References files that are not bundled: templates/config.jsx.tmpl, templates/benchmarks.jsx.tmpl, templates/page.mdx.tmpl
• 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

Uses PyMISP (the official MISP REST API library) to create events with structured IOCs (IPs, domains, hashes, URLs), enrich them with MITRE ATT&CK tags and galaxy clusters, manage

• 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

Detects unauthorized runtime drift in containers by monitoring binary execution, filesystem changes, and configuration deviation from the original immutable image, using Falco and

• 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

Implements and audits GCP VPC firewall rules using gcloud, covering auditing overly permissive rules, creating restrictive ingress/egress rules, hierarchical firewall policies, and

• The skill tells the model to perform an irreversible action with no human approval
• Linear process with no failure handling
• 6 mutating operations with no state check

Hardens AWS IAM configurations to enforce least-privilege access, covering IAM policy scoping, permission boundaries, IAM Access Analyzer integration, and credential rotation strat

• The skill tells the model to perform an irreversible action with no human approval
• Linear process with no failure handling
• 7 mutating operations with no state check

Update the OpenClaw and Hermes comparison columns of the ZeroClaw feature-and-support matrix. Use this skill when the user wants to refresh, fill, or verify parity data in docs/boo

• 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

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

• 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
• The response is described with custom markup (6 tags): a typed call is more reliable

Daily digest of AI releases from Anthropic, Meta, Vercel Labs, OpenAI and Google GitHub repos, the Claude Cowork changelog, the claude.dev blog and Hacker News, deduplicated agains

• 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
• Does not say what the result is

Design and implement multi-tenant SaaS architectures with row-level security, tenant-scoped queries, shared-schema isolation, and safe cross-tenant admin patterns in PostgreSQL and

• 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 result is

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit wr

• References files that are not bundled: url
• 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

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax an

• 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

Manage Railway deployments - view logs, redeploy, restart, or remove deployments. Use for deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, statu

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (11 tags): a typed call is more reliable
• Does not say what the result is

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI remains the default; Atlas Cloud is an expl

• 13 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

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “ge

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 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

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trig

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 20 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

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or e

• 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

3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.

• 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
• The skill tells the model to perform an irreversible action with no human approval

Playbook for changing vLLM's Transformers version bounds. Use when bumping the pinned or maximum Transformers version, raising the minimum Transformers version, or deleting vendore

• 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

How to fill and revise a canvas made from the Design (canvas) appifact type.

• 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
• The response is described with custom markup (37 tags): a typed call is more reliable

Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. One unified pipeline: normalize the source i

• References files that are not bundled: ../conventions/brain-first.md, ../conventions/agent-operator-protocol.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

Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a co

• References files that are not bundled: ../conventions/brain-first.md, ../conventions/test-before-bulk.md, ../conventions/untrusted-content.md
• 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

Extract a sanitized shared team/company brain from a personal brain. Strips internal ratings, compensation, performance assessments, retention and political dynamics from pages, ta

• References files that are not bundled: ../conventions/brain-first.md, ../conventions/test-before-bulk.md, ../conventions/regex-discipline.md
• 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

Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam

• References files that are not bundled: page.md, ../conventions/agent-operator-protocol.md
• 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

Share brain pages as beautiful password-protected HTML with zero LLM calls

• References files that are not bundled: ../people/jane.md, ../conventions/agent-operator-protocol.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or cr

• References files that are not bundled: STYLE_PRESETS.md, viewport-base.css, scripts/extract-pptx.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