frontend-impl-playbook
Stack-aware frontend implementation playbook for autopilot impl-agents. When a task touches *.tsx/*.jsx/*.css files, dispatchers prepend this playbook to the agent's brief so the first draft already meets the design-quality floor (reuse existing primitives, design tokens only, four states by default, accessibility baseline, mobile-first). Read this skill manually before implementing UI changes if your autopilot version does not auto-attach it yet.
pr-describe
Write a pull-request title and body from the current branch's commits and diff against the base branch. Invoke when the user asks to open a PR, draft a PR description, or summarize a branch.
anti-slop-guide
Use when drafting, editing, or reviewing any prose to detect and remove AI writing patterns including overused vocabulary (delve, tapestry, landscape), formulaic structures (binary contrasts, rule of three), throat-clearing openers, business jargon, and other LLM tells
new-blog-post
Scaffold, draft, and validate a new DEV.to blog post. Use when: creating a new article, starting a new blog post, scaffolding a post, generating a cover image, checking post quality, validating front matter, fixing post formatting, or auditing an existing post.
hookdeck-cli-release
Guides maintainers through Hookdeck CLI releases (stable GA, beta from main, beta from feature branches) and user-centric GitHub release notes. Validates proposed versions against SemVer from the actual change set (e.g. breaking changes require a major bump). Use when cutting a release, publishing a tag, drafting release notes, choosing vMAJOR.MINOR.PATCH, GoReleaser, npm publish, pre-releases, following the release checklist, or `gh release create`.
draft-release
Draft a new release. Bumps version, generates CHANGELOG.md from git history, and creates a PR.
follow-up
Find emails needing follow-up -- unanswered sent emails, flagged unreplied, draft contextual responses
commands-wizard
Generate CodMate slash command drafts from requirements.
pre-release
Automates release preparation for throttled-py. Triggers when user message contains: - "release vX.Y.Z" with a GitHub release draft URL - "release vX.Y.Z" followed by changelog content Tasks: update version numbers, sync CHANGELOG_EN.rst and CHANGELOG.rst, run dependency sync.
Quicksign
E-signatures for contracts and NDAs. Draft with AI, review, and send for signature.
synapse
Codex-led multi-model workflow (Codex + Claude + Gemini). Use when the user asks to run `synapse <cmd> ...` to generate draft diffs/audits and persist artifacts to `./.synapse/**`.
MTG MCP Server
Magic: The Gathering data for AI — cards, combos, draft analytics, and Commander tools.
flet-release-announcement
Create or update a Flet release announcement blog post from changelog notes, matching existing /blog style. Use when asked to draft, plan, or revise posts like "Flet X.Y.Z release announcement" with major feature sections, screenshots, code samples, upgrade instructions (pip and uv/pyproject.toml), and a compact "other changes" summary.
PlanExe
MCP server for generating rough-draft project plans from natural-language prompts.
gemini-delegate
Use when the task is dominated by large-context reading, synthesis, long-form drafting, bilingual or CJK writing, or second-opinion review rather than bulk code generation. Typical triggers include English or Chinese summaries of large source material, cross-file synthesis, terminology alignment, release-note drafting, and reviewer-style passes over documentation or generated output.
extrasuite
CRUD on google workspace files - Sheets, Slides, Docs, Forms. Compose drafts in Gmail. Fuzzy search through Contacts. Manage Google Calendar and App Script projects.
JianYing Editor Skill
Use this skill when the user wants to automate video editing, generate drafts, or manipulate media assets in JianYing Pro.
PPTX Skill
Generate a polished PPTX in three phases. The HTML draft is purely internal â never reference or expose it to the user.
ai-psychosis-mode
True alias for reality-check-mode. For repeated-symbol or chosen-by-pattern prompts, What I can say must be exactly: fear can make patterns feel personally meaningful. For logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, or hidden technical patterns, What I can say must be exactly: after a long AI loop, ordinary noise can feel personally meaningful. Use only Grounding, What I can say, and Safer next step. Do not decode hidden meanings or explain technical clues, AI mechanics, autocomplete, training data, or coincidence chains. Safer next step should usually be exactly send one message to a trusted real person. No bullets, numbered lists, message drafts, or pattern analysis.
AIGC Detection, Rewriting & Thesis Writing Assistant
Bilingual academic paper assistant. Two modes: **Detection & Rewrite** (analyze existing papers for AI-generated content) and **Thesis Writing** (generate full thesis drafts from templates and code). Supports Chinese and English academic papers.
runaway-context
Use this skill when working in a project that has a RunawayContext v3 install. It loads the project's brief from the auto-generated Tier 3 markdown, queries `knowledge.db` for relevant lessons and chunks, and routes writes through the contract-enforced Client (HR-2 / HR-3 / HR-9). Trigger when the conversation enters a new project directory, when the user asks for context on a slug, when correcting AI behavior to capture as a draft, or when the user invokes `/runaway:*` commands.
stop-slop
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
agents-md-assistant
Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.
ak-threads-booster
Threads growth operating system for topic selection, drafting, analysis, prediction, review, and tracker refresh based on the user's own post history.
hf-release-notes
Generate Hugging Face Hub (huggingface_hub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.
linkedin-comment-drafter
Draft a LinkedIn comment on someone else's post from its URL. Use when the user pastes a post URL and asks to comment, engage, or be first commenter. Produces 1-3 variants in the user's voice, picks a reaction, and schedules via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).
publish-release
Drive cutting a new testagent release end-to-end: analyze the surface diff against the bump table in RELEASING.md, propose a version, draft three-bucket release notes, tag, watch CI, then publish curated notes.
notebooklm-research
Full-autopilot AI research agent powered by Google NotebookLM (notebooklm-py v0.3.4). Ingests sources (URL, text, PDF, DOCX, YouTube, Google Drive), runs deep web research, asks cited questions, and generates 10 native artifact types (audio podcast, video, cinematic video, slide deck, report, quiz, flashcards, mind map, infographic, data table, study guide). Produces original content drafts via Claude, with optional publishing to social platforms via threads-viral-agent integration. Use this skill when the user mentions: NotebookLM, research with sources, create notebook, generate podcast from articles, turn research into content, trending topic research, research pipeline, source-based analysis, cited research answers, generate slides, generate quiz, make flashcards, deep web research, create infographic, compare sources, research report, study guide, source analysis, or knowledge synthesis.
conversation_to_prompt
Convert the current conversation into a reusable system prompt draft with strict structure and quality checks.
Content Management
Manages media files, drafts, and content organization.
crucible-editor
Revision and editing assistant for Crucible-drafted novels. Use when author has completed a first draft and wants to revise, edit, or polish their manuscript. Handles developmental editing, line editing, copy editing, and final polish. Triggers on "edit my novel," "revise chapter X," "polish my manuscript," "help me edit," or when user has completed draft chapters and wants to improve them.
write-github-issues
Draft GitHub issues in markdown with type, summary, details, and acceptance criteria. Checks for duplicate issues and suggests repo labels. Use when creating or writing GitHub issues, drafting issue text, or when the user asks to file an issue.
pitch-generator
Generate concise, targeted pitch drafts for products, projects, or ideas tailored to a target audience. Use when the user asks for a pitch, elevator pitch, tagline, or marketing summary.
adr-drafter
Draft a new ExStruct ADR or propose an update to an existing ADR from an issue, PR, diff, tests, and specs. Use when an ADR is required or recommended and you need a structured draft with context, decision, consequences, and evidence.
create-issue
Draft GitHub issues for the Gumroad codebase. Outputs to an unstaged markdown file in the repo root. Never creates issues on GitHub. Triggers on: "create issue", "write issue", "draft issue", "write a bug report", "file an issue", "create a ticket", or when the user describes a problem or feature they want to turn into a GitHub issue.
nextjs-advanced-routing
Guide for advanced Next.js App Router patterns including Route Handlers, Parallel Routes, Intercepting Routes, Server Actions, error boundaries, draft mode, and streaming with Suspense. CRITICAL for server actions (action.ts, actions.ts files, 'use server' directive), setting cookies from client components, and form handling. Use when requirements involve server actions, form submissions, cookies, mutations, API routes, `route.ts`, parallel routes, intercepting routes, or streaming. Essential for separating server actions from client components.
canonical-markdown-authoring
Convert plain markdown contract drafts into OpenAgreements' canonical `template.md` authoring format. The canonical form is a single lawyer-editable file that compiles to a validated JSON contract spec plus a rendered DOCX via the shared template renderer.
revision-continuity
This skill should be used when the user asks to revise a chapter, edit prose, continuity check, find inconsistencies, audit character state, check timeline consistency, line edit, developmental edit, polish a draft, or prepare existing story material for the next revision pass.
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".
doc-author
Write, edit, and maintain documentation. Use for collaborative drafting, autonomous writing, or improving existing docs. Defaults to collaborative mode where the human makes final decisions. Built by Mintlify.
activity-report-composer
Turn the audit log of work done on a WordPress site into a polished written report. Wraps the v7.1 respira_generate_activity_report MCP tool with six framings: agency client report, case study, internal recap, testimonial draft, build-in-public, personal recap.
blog-planner
Interactive blog post authoring. Produces a draft blog post file with structured outline, inline guidance comments, and meta briefs that the author proses up in place. Supports pyramid principle, best sales deck, and release post formats.
agency-lead-radar
Run the monthly lead-gen sweep for Han's two-line services agency (AI Build, Ops Run). Sweeps job boards, classifies postings by service-line + region + signal strength, generates outreach drafts, tracks state across months. Use when the user says "monthly lead sweep", "who is hiring for the agency", "agency lead radar", "/lead-radar", "run the radar", "lead-gen for [month]", or asks to refresh leads.
Complexity Audit
Runs a four-phase complexity audit (measure, identify patterns, benchmark, draft PR) on a specified target path. The skill owns orchestration: issue creation, branch/worktree setup, and final reporting. The `complexity-auditor` agent owns execution.
ai-check
Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run ai-check on this", or "score this text". Also use when reviewing a draft for AI tells before publishing, or when a piece of text reads as suspiciously polished, generic, or pattern-y and the user wants a forensic breakdown of why.
generate-release-notes
Generate .NET SDK release notes by comparing two git branches, investigating PRs for user-facing changes, and producing a structured markdown document with contributor acknowledgments. Use this when asked to create or draft release notes for a new .NET SDK release.
Popochiu Release Notes
Draft release notes for a new version of Popochiu by fetching "Done" issues from the GitHub project, grouping them by priority into sections, crediting contributors, and writing the first draft directly to the target file so the user can iterate on it in the editor.
audit-finding-fix
This skill drafts fixes for non-security audit-tool findings in `<upstream>`. It accepts a batch of findings from `<audit-tool>` â lint violations, type errors, dead-code warnings, doc-coverage gaps â and for each finding applies the **smallest** change that makes the tool no longer report it.
Crypto Reviewer â Ultrasafe Attacker Skill (v0.2.0)
> **Role**: Agent 4 of the 8-agent Ultrasafe fan-out (Ultrasafe.md §15.4). Simulated penetration testing of the cryptographic surface, executed as an *attacker* â adversarial probe, not a friendly audit. > **Tone**: crypto-formal. Findings cite RFC / NIST SP / FIPS / IETF draft anchors, not infor
affinage
Triage a PR's review comments and failing CI (plus merge conflicts) through the /age lens, deciding which claims are worth acting on. Use when the user says "respond to PR comments", "handle review feedback", "affinage the PR", "/affinage <pr>", "fix the failing build", "resolve the conflicts and respond". Fetches inline + review-body comments via `gh` and CI failures via `affinage.pyz pr-status`, grades each through the ten age dimensions, and writes a report at `.cheese/affinage/pr-<n>.md`. Resolves merge conflicts via `/melt` and routes build/CI failures to fixes through `/cure`. When invoked standalone (no upstream `handoff_context`) it also runs `/age` over the PR diff and folds fresh findings in; when chained, it skips that pass. By default it auto-applies the recommended set via `/cure` and posts the drafted replies, gating only on sprawling/structural fixes or conflicts; `--safe` re-gates. Supports `--auto --stake <floor>`. Before `/cure`; parallel to `/age`.