Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
sergekostenchuk/mouse-trail-masking-reveal
Skill Codex
Build, repair, tune, and validate interactive cursor-trail mask reveal hero effects in frontend projects. Use when implementing canvas-based base/reveal compositing, soft radial cursor masks, fading cursor trails, reveal debug controls, full-screen hero scenes without site text, or browser smoke checks for cursor…
yogsoth-ai/north-star-crystallization
Skill Claude CodeCodex
Understand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.
Skill Claude CodeCodex
A command-line tool for checking Taiwanese parcel deliveries by tracking number. It supports several Taiwanese courier services and can show current status, pending parcels, and lookup history.
Skill Claude CodeCodex
An AI assistant workflow for choosing university applications in China's Gaokao system, the national college entrance examination. It compares scores and rankings with school and major choices while accounting for regional admission rules.
forsvn-labs/transcript-to-epub
Skill Claude Code
Turn a YouTube URL or a local timestamped transcript into a designed, attributed EPUB reading edition. Auto-detects speakers/channel, cleans timestamps, always credits the original creators, and builds both a clean Markdown book and a book.epub.
Skill Claude CodeCodex needs its repo
A runbook for one cycle of an AI-assisted change review: collect files, run checks, make a decision, save a record, and follow the result.
Skill Claude CodeCodex
Use when committing changes with git — staging files and writing commit messages. Makes the agent keep each commit focused on one logical change and write a clear, conventional message explaining why, instead of dumping unrelated edits into a single vague "update" commit.
alexconner-79/high-plains-drifter
Skill Claude CodeCodex
Align a design to your real Storybook components instead of reconstructing it. Use when turning a Figma frame into React built from an existing component library (Build mode), or when pulling scrappy exploratory code into line with the library once a direction feels right (Align mode). Triggers include "build this…
Skill Claude CodeCodex
Compacted communication mode. Cuts token usage 50%90% by speaking like Feynman while keeping full technical accuracy. Intensity levels: short, long, cc. Use when user says "twofold mode", "2f mode", "sl mode", "use 2f", "use twofold", "use sl", "be brief", "trả lời ngắn", "shorthand longform", "simple lengthy" or…
ZhenHaoFu810/research-talkcraft
Skill Claude CodeCodex
The Skill runs in one of two modes. The mode must be visible in reasoning and output.
Skill Claude CodeCodex
Run a read-only Kempt health check on the local AI-coding-agent state (/.claude, /.codex) and explain the agent-debt report. Use when the user asks why their coding agent feels slow, confused or inconsistent, mentions "agent debt" / "agent 体检" / "agent health", or wants to know what junk has piled up in their Claude…
Skill Claude CodeCodex
End-to-end Luma event launch: research comparable events in the target city, draft copy that doesn't read like AI slop, create a Private draft via the admin API, fix the startat / duration / capacity traps, and polish theme, font, and cover. Use this whenever the user wants to publish, edit, or shape an event for…
YankielDBC2/saas-cybersecurity
Skill Codex
Audit and safely harden authorized SaaS web applications across frameworks and hosting providers. Use for OWASP-aligned reviews, runtime browser checks, HTTP headers, XSS/CSRF, access control, secrets, payments, uploads, privacy, abuse controls, supply-chain risk, link injection, or security remediation; do not use…
Exponential-View-co/autoresearch-skill
Skill Claude CodeCodex
Autonomous iterative improvement loop for any writing or thinking task — thesis frames, book titles, essay angles, product positioning, strategy arguments. Give a problem statement, the agent auto-designs the oracle (scoring dimensions + judge panel), shows it for approval, then iterates one change at a time until…
Skill Claude CodeCodex
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Skill Claude CodeCodex
Generate and edit diagrams with the mcp-diagram-generator MCP server. Use this skill for new diagrams, existing .drawio/.mmd/.excalidraw edits, network topology, architecture, flowchart, swimlane, sequence, class, ER, and Excalidraw whiteboard work. Always use this skill when the user asks to draw, generate, revise…
Skill Claude CodeCodex
Adversarial specification writer. Takes a brief (from grill-me or user) and produces a structured spec.md with YAML frontmatter, requirements, acceptance criteria, and target files. Git-aware pipeline: each run on its own branch, squash-merge on approval.
adarshnagrikar14/resume-any-chat
Skill Codex needs its repo
Use when the user wants to inspect, search, normalize, resume, hand off, or optionally import local Codex, Claude, or Antigravity CLI conversation history. This skill provides a local viewer, provider-specific parsers, native resume commands, a Codex handoff flow, and an explicit experimental Codex-history import path.
makisekurisu0827/context-compactor
Skill Claude CodeCodex
Keep long Claude Code sessions coherent by rolling old conversation into a single, constantly-updated summary so the context window stops overflowing and the assistant stops giving degraded or off-topic answers. Use this skill whenever a coding or development session has been running long, whenever the conversation…
Skill Codex
Lead free-form implementation work through bounded delegation: define the exact outcome, launch the smallest useful executor team, integrate the result, and prove completion. Use when the user asks Work to build, fix, implement, refactor, or change something without selecting a focused Work skill.
Skill Claude Code
Analyze the fonts in fonts/ and set up this repo for proofing. Runs the containerized fontTools introspection, writes a human-readable font summary into CLAUDE.md (and machine-precise data into fontinfo.json), then interviews the user about the proof they want — page size, orientation, colors, header/footer, margins…
Skill Claude CodeCodex
After a batch of 2+ user-facing UI changes, produce a before/after verification report to sign off each change while reviewing locally. Invoke on request ('before/after report', 'verification table', 'screenshot diff') or proactively when a finished change set touches ≥2 distinct UI surfaces/behaviors. Captures…
adityasasidhar/claude-code-in-100-lines
Skill Claude CodeCodex
Use when asked to review code, a diff, or a PR for correctness bugs and quality issues.
Skill Claude CodeCodex
Reveal consequential blind spots after answering. Use proactively for exploration, research, product thinking, architecture, planning, creative work, and decisions, or when the user asks what they missed, what to ask next, or to challenge an idea. Skip routine execution unless a hidden issue could materially change…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: