Skill reviews

WHAT: Explains a codebase, a folder, a feature, a command or a pull request to someone who knows nothing about it, as a PR Lens canvas whose walkthrough builds the picture one part

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

This skill should be used when the user asks for a "sensitivity reader", "authenticity reader", "cultural review", "is this portrayal okay", "real people in my novel", "defamation"

• References files that are not bundled: ../story-maintenance/references/conventions.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

This skill should be used when the user asks to "process beta reader feedback", "alpha reader feedback", "feedback round", "synthesize reader feedback", "reader notes", "beta feedb

• References files that are not bundled: ../story-maintenance/references/conventions.md, templates/github/
• 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 "make an audiobook", "narration script", "narrator", "ACX", "Findaway", "pronunciation guide", "how long is the audiobook", "adapt t

• References files that are not bundled: ../story-maintenance/references/conventions.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

Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content f

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (24 tags): a typed call is more reliable
• Does not say what the result is

Wire channels to agent groups, manage isolation levels, add new channel groups. Use after adding a channel, during setup, or standalone to reconfigure.

• 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 (5 tags): a typed call is more reliable

Agent-to-agent Slack rooms — a group DM (MPIM) holding a human plus two or more NanoClaw sibling bots, where each bot hears the room over its own Socket Mode connection. Registers

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Add WhatsApp channel via native Baileys adapter. Direct connection — no Chat SDK bridge. Uses QR code or pairing code for authentication.

• References files that are not bundled: scripts/init-first-agent.ts
• 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

Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.

• 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

Add Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants

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

Add Microsoft Teams channel integration via Chat SDK.

• 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

Prepare a subset of the vault for publishing: check opt-in flags, find private material, and report what would leak through links before anything is exported. Use this skill when t

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 5 mutating operations with no state check

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

Retrieves and interprets patent data with the conventions that make counts and claims defensible, covering Google Patents, Lens, EPO Open Patent Services, USPTO data through Patent

• 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 this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsi

• 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

Formalizes and checks mathematical statements in Lean 4 with Mathlib, covering the lake project layout and pinned toolchain, `lake exe cache get` before `lake build`, searching Mat

• 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

Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.

• 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

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visib

• 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

Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's

• 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

Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validati

• 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

Audits fielded survey-response data for registered elements, data quality, bot and AI-automation screening, and sample integrity, and produces an appendix-ready quality report. Use

• 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

Advises on setting up and validating LLM text classification: codebook, learning regime and model choice, prompts, validation against human coding (kappa, F1), hybrid review, measu

• 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

Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity, and emit an appendix-ready quality report. Use at s

• 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

End-of-session closure for a research or code repository. Records what changed into the project's own handoff and log files, separating verified work from work merely attempted, an

• 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

OCRs scanned or image-only corpora with vision-language models in four phases. Triage inventories the scans, identifies script and language, and shortlists models by script, hardwa

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model
• The skill tells the model to perform an irreversible action with no human approval