Ponytail Debt
DietrichGebertHarvests ponytail comments into a grouped debt ledger, showing each shortcut's ceiling, upgrade trigger and missing trigger risks.
By agent · GitHub Copilot
Skills in the open SKILL.md format that GitHub Copilot reads. Each one has a plain-language summary and the command to install it.
$ npx skills add <author>/<skill> --agent github-copilotReplace the placeholder with the author and skill name from the skill's page. Start a new GitHub Copilot session afterwards so the skill is picked up.
Harvests ponytail comments into a grouped debt ledger, showing each shortcut's ceiling, upgrade trigger and missing trigger risks.
Compares a pull request with approved product and technical specifications, adding material mismatches to the existing review output.
Builds project colour systems with semantic tokens, generated ramps, format conversion, gradient guidance and measured contrast checks.
Shows Ponytail's benchmark impact on code volume, cost and speed as a compact one-shot scoreboard.
Creates concise diagrams, code sketches and focused HTML artefacts to make algorithms, architecture, control flow and UI structure easier to understand.
Improves interface layouts by organising space, alignment, reading order, responsive behaviour and progressive disclosure across screen sizes.
Coordinates accessibility, layout, writing, typography, colour and UI-polish reviews into one evidence-based interface verdict.
Creates, imports, reads and updates WeCom online documents through the wecom-cli command-line tool, with append and overwrite handling.
Reviews and fixes web interfaces for accessible semantics, keyboard use, focus management, forms, motion and screen-reader support.
Improves product interface copy in a codebase with clear language, consistent terminology, accessible labels and actionable errors.
Turns complex agent responses into reviewable HTML pages with lavish-axi, allowing annotations and feedback in the browser.
Routes internet research through Agent Reach across 16 platforms, using CLI, API and browser backends for search, social, jobs, code, video and finance.
Drafts Warp feature documentation from product and technical specs, verifies claims in the codebase, and produces an MDX page with a review-ready draft PR.
Diagnoses and reduces Neon Postgres egress by finding high-transfer queries and fixing overfetching, unbounded results and repeated data.
Provides branch-aware S3-compatible object storage for Neon projects, with buckets, uploads, downloads, presigned URLs and standard AWS tooling.
Deploys long-running Node.js HTTP functions on Neon branches for APIs, streaming, WebSockets, webhooks and scheduled or storage-triggered workloads.
Guides developers through Google Cloud account authentication, project selection or creation, billing setup and deployment verification.
Explains how to authenticate and authorise Google Cloud users, services and external workloads with secure credential and IAM choices.
Connects Neon projects to multiple LLM providers through one branch-scoped credential, supporting SDK calls, model switching and agent workflows.
Guides FastAPI Python backend development with typed routes, Pydantic validation, asynchronous operations and maintainable API structure.
Evaluates Google Cloud workloads against Well-Architected security principles and recommends controls for identity, networks, data, operations and compliance.
Generates Google Cloud cost guidance using the Well-Architected Framework, covering visibility, resource efficiency, governance and continuous optimisation.
Generates Google Cloud reliability guidance for workload architecture, covering availability, resilience, observability and disaster recovery.
Sends brief, anonymous, unstructured Slack complaints about frustrating agent tooling or the experience of agent work.
Questions
Often. A skill is a folder of instructions and scripts in the open SKILL.md format, which GitHub Copilot reads. A skill that depends on tools only one agent provides will not carry over, so read the skill's source before you rely on it.
Each skill page has an install command. Run it in a terminal, then start a new GitHub Copilot session so the skill is picked up.
An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.