hnl-agent-skills

In the author's own words, from each skill's SKILL.md.

• browser-eyeballs

  Browse and visually inspect webpages using an available browser automation tool, preferably headless Chromium via Puppeteer MCP. Use when you need to see a page, interact with a web UI, extract information that a plain fetch cannot get (JS-rendered content, SPAs, authenticated pages), or when the user wants to show you something in a browser.

  browser-eyeballs/SKILL.md on GitHub (opens in a new tab)

• bug-hunter

  Proactive bug-hunting methodology — autonomous codebase reconnaissance to find latent bugs, hidden failure modes, and ticking time bombs BEFORE they detonate in production. Use this skill whenever the user asks to "find bugs", "hunt for issues", "audit this codebase", "what could go wrong", "find what's broken", "stress-test this project", "find landmines", "what will bite me later", or any varia…

  bug-hunter/SKILL.md on GitHub (opens in a new tab)

• code-simplification

  Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

  code-simplification/SKILL.md on GitHub (opens in a new tab)

• commit-message-this

  Draft a commit message strictly for the work done in THIS session, identifying exactly which files belong in the commit. Ignores pre-existing dirty files.

  commit-message-this/SKILL.md on GitHub (opens in a new tab)

• commit-message

  Draft git commit messages. Use when asked to create, draft, or prepare a commit message. Analyzes staged/unstaged changes and recent history to match project style.

  commit-message/SKILL.md on GitHub (opens in a new tab)

• critical-mode

  Behavioral modifier that applies senior PM-level critical evaluation to user requests. Use when the user invokes /critical-mode, or asks for "critical mode", "pm mode", "challenge my assumptions", "push back on this", "be my devil's advocate", or wants the assistant to actively question whether a request is the right thing to do before executing. Supports intensity levels: light (guidance only),…

  critical-mode/SKILL.md on GitHub (opens in a new tab)

• explainer-animation

  Autonomously produce a professional 30–60 s whimsical, hand-drawn paper-collage explainer animation in pure JavaScript (canvas + Web Audio) about what the current project does and how. Includes neural-TTS narration, a synthesised score and sound effects, a self-contained HTML player and an MP4 export. Use when the user asks for an explainer video, animated intro, promo or "what does this project…

  explainer-animation/SKILL.md on GitHub (opens in a new tab)

• factual-mode

  Activates evidence-grounded behavioral constraints that minimize hallucination. Use this skill when the user invokes /factual-mode, or when they ask for "factual mode", "grounded mode", "no guessing", "only use what's in front of you", "don't hallucinate", "stick to the facts", "evidence-based only", or any variation requesting that the assistant restrict itself to verifiable claims. Also appropr…

  factual-mode/SKILL.md on GitHub (opens in a new tab)

• hostile-review

  Adversarial code/plan/design review by a senior dev who hates what you built. Use this skill whenever the user asks for a hostile, brutal, or adversarial review — phrases like "tear this apart", "what's wrong with this", "pretend you hate this", "roast my code", "devil's advocate", "worst-case critique", "what am I missing", "what would a critic say", or "stress-test this plan" should all trigger…

  hostile-review/SKILL.md on GitHub (opens in a new tab)

• humanize

  Rewrites text to remove AI writing patterns and inject human voice. Use this skill whenever the user asks to "humanize", "de-AI", "make this sound human", "remove AI tells", "fix AI slop", "make it less ChatGPT-y", "rewrite this so it doesn't sound like a bot", or shares text and asks for it to sound more natural, more like them, or less like a press release. Also use proactively when the user is…

  humanize/SKILL.md on GitHub (opens in a new tab)

• i18n-standards

  Standards for internationalization and string handling. Apply when touching files with user-facing strings or preparing strings for translation.

  i18n-standards/SKILL.md on GitHub (opens in a new tab)

• js-standards

  JavaScript standards and patterns. Apply when writing or modifying JavaScript modules, event handling, lazy loading, scroll behavior, or browser-side utilities.

  js-standards/SKILL.md on GitHub (opens in a new tab)

• ontoly-software-graph

  Build and query Ontoly's deterministic Software Graph before manually searching a TypeScript repository. Use when asked about architecture, dependencies, routes, services, modules, request traces, impact analysis, configuration, or codebase onboarding.

  ontoly-software-graph/SKILL.md on GitHub (opens in a new tab)

• php-documentation-standards

  Enforces PHP documentation standards for PHPStorm IDE support. Apply when writing or reviewing PHP classes, methods, docblocks, type hints, or magic property annotations.

  php-documentation-standards/SKILL.md on GitHub (opens in a new tab)

• project-ambassador

  The project's institutional memory and decision authority. Acts as an autonomous representative of the project — its goals, architecture, conventions, constraints, and intent. Use this skill whenever the active agent or another skill needs clarification about the project before proceeding. Triggers on: "/project-ambassador", "/ambassador", "ask the ambassador", "check with the ambassador", "what…

  project-ambassador/SKILL.md on GitHub (opens in a new tab)

• reflect

  Audit and improve code-agent project configuration. Use when the user wants to review or optimize AGENTS.md, CLAUDE.md, slash commands, settings, permissions, or tool approvals based on observed gaps or chat history patterns. Triggers on requests like "improve my agent instructions", "review my setup", "why does the assistant keep getting X wrong", or provider-specific variants such as "improve m…

  reflect/SKILL.md on GitHub (opens in a new tab)

• review-and-harden

  End-to-end hardening pipeline for a codebase: hostile review, then project-ambassador verdicts, then a staff-review implementation plan, then implementing every accepted fix (each proven by a test), then one bug-hunter sweep, then a final fix round, then a report and a ping to the user. Use this whenever the user asks to chain these reviews ("run a hostile review, ask the ambassador, have staff-r…

  review-and-harden/SKILL.md on GitHub (opens in a new tab)

• sanity-check

  Diagnostic pause when an agent session has gone off-track. Use when the user says things like "wait, what are we doing", "we're lost", "this isn't what I asked for", "let's step back", "where are we", "sanity check this", or when you notice the session has drifted significantly from the original goal. Produces a SITREP (situation report), diagnoses what went wrong, assesses context window health,…

  sanity-check/SKILL.md on GitHub (opens in a new tab)

• scss-standards

  SCSS and CSS architecture standards. Apply when working with CSS, SCSS, styling architecture, component styles, tokens, or compiled stylesheet organization.

  scss-standards/SKILL.md on GitHub (opens in a new tab)

• specification-website

  Query and apply The Website Specification — a platform-agnostic specification of what a good website does, with each item tagged required, recommended, optional, or avoid. Use when the user asks what their site should have, whether something is required, how to audit a URL, what's missing for agent readiness, or anything else where you'd otherwise be guessing at web best practice. Backs answers w…

  spec-website/SKILL.md on GitHub (opens in a new tab)

• staff-review

  Senior Staff Engineer code review with SOLID principles, security analysis, and architecture critique. Use for significant changes, new systems, or when you want ruthless technical feedback.

  staff-review/SKILL.md on GitHub (opens in a new tab)

• systematic-debugging

  Four-phase debugging methodology with root cause analysis. Use when investigating bugs, fixing test failures, or troubleshooting unexpected behavior. Emphasizes NO FIXES WITHOUT ROOT CAUSE FIRST.

  systematic-debugging/SKILL.md on GitHub (opens in a new tab)

• user-review

  Simulate an objective first-time user review of a webpage or UI from the perspective of the target audience — no prior project context, no insider knowledge. Use this skill when the user asks things like "what would a user think of this page", "review this as a visitor", "give me a first-impression review", "pretend you're a patient/customer/prospect looking at this", "user test this page", or an…

  user-review/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill