Your next session starts cold. No memory of what you built, what broke, what you decided. Every signal you write is a gift to that future session. The richer the signal, the less time re-learning.
Before finalizing any public-facing design, document, or feature — identify the audience, what they search for, and what they need most urgently. Use when creating README sections, naming repos, writing descriptions, or designing user-facing interfaces.
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate", "stress test this idea", "poke holes in my plan", "help me decide between X and Y", "what are the second-order effects", "I'm stuck on a decision", names any specific model (SWOT, first principles, inversion, pre-mortem, etc.), or asks for structured reasoning on any ambiguous, high-stakes, or complex problem. Also trigger when the user seems uncertain, is rationalizing, or is asking "am I thinking about this right?" Even casual phrases like "what do you think about..." on non-trivial topics should trigger this skill. --- # Thinking Partner A deterministic thinking partner that challenges assumptions and applies mental models to help users think better and clearer. Not a lecture — a sparring session. ## Core Philosophy Good thinking is an active achievement, not a default state. The goal is not to tell the user what to think, but to sharpen *how* they think by: 1. **Challenging assumptions** — Surface hidden beliefs the user is treating as facts 2. **Applying mental models** — Select and deploy the right thinking frameworks for the situation 3. **Detecting orientation capture** — Notice when thinking serves comfort instead of truth 4. **Maintaining productive tension** — Hold complexity open long enough to find real insight You are not a yes-machine. You are not an interrogator. You are a thinking partner: respectful, direct, genuinely curious, and willing to push back. ## When This Triggers - "Help me think through X" - "Challenge my thinking / assumptions" - "What am I missing?" - "Apply [any model name] to this" - "Play devil's advocate" - "Stress test this idea / plan" - "Help me decide between X and Y" - "What are the second-order effects?" - "Am I thin
**sgrep** is a semantic and hybrid code search tool that understands what you mean, not just what you type.
Reads recent session context, infers what you were working on, and proposes the specific next action. Use when resuming after a break, or say "act" / "what should we do next" / "pick up where we left off". Executes immediately on confirmation.
Adaptive memory system that makes any LLM output better over time. Learns what works (strategies) and what fails (antibodies) from every scan. Injects winning patterns before generation, catches errors after. Hot/Cold tiered memory with multi-domain support.
Use this skill when the user reports a bug, error, crash, unexpected behaviour, or performance problem in their application, or asks to "investigate", "debug", "check logs", "look at errors", "what happened", "why is X failing", or "trace a request". Also activates when the user pastes an error message or stack trace and asks for help. Also use when the user asks "what is my app doing?", "show me what happened when I ran X", "trace this flow", "is my service receiving logs?", "I'm testing this endpoint — what do I see?", or any exploratory runtime question. Also use when the user wants to set up, configure, or verify logging/OTLP instrumentation in their application. Requires Loggles MCP tools to be connected.
PRP (Product Requirement Prompt) methodology for writing PRDs. Reference for best practices in structuring requirements documents for coding agents. --- # PRP Methodology — Quick Reference The PRP (Product Requirement Prompt) framework is a structured process for creating PRDs that coding agents can execute in a single pass. ## Core Principle A PRD must contain ALL context needed for implementation. If a fresh Claude session with only the PRD can't build the feature correctly, the PRD is incomplete. ## The 3-Step Process 1. **Write initial description** — Brain dump what you want: feature, tech stack, constraints, integrations, examples, documentation references 2. **Generate the PRD** — Research the codebase + web, interview the user, produce a structured document following the base template 3. **Execute the PRD** — Clear context, start fresh, implement from the PRD alone ## What Makes a Good PRD **DO:** - Reference specific files and code patterns from the codebase - Write testable validation criteria ("returns 401 on invalid token") - Include explicit non-goals to prevent scope creep - List anti-patterns specific to the project - Order implementation steps by dependency (what must exist before what) - Include migration strategy for existing data/behavior **DON'T:** - Use vague validation criteria ("works well", "is performant") - Leave technical design abstract ("use appropriate data structures") - Assume the implementing agent knows project conventions — spell them out - Skip the non-goals section — agents will over-build without boundaries - Write steps that can't be verified independently ## Interview Technique The most valuable part of PRD generation is the interview. Goal: reduce assumptions to near zero. - Ask at least 8-10 questions before writing - Batch questions in groups of 3-4 - Provide recommended answers based on codebase research - Cover: scope, users, technical constraints, data model, compatibility, edge cases, testing, anti-patterns - Final ques
[What this skill does and when to use it]
Use this skill to validate and refine brand messaging, positioning, and taglines using real audience insight. Triggers include: requests to test brand positioning, validate taglines or slogans, understand brand perception, refine mission statements, test brand voice, or differentiate from competitors. Uses OriginalVoices Digital Twins (ask_twins) to understand how target audiences interpret brand messaging, what resonates emotionally, what creates confusion, and what drives brand affinity — ensuring brand statements connect with real people, not just internal stakeholders.
Multi-agent coordination through files. Memory, threads, progress, handoffs. Use when asked to "save progress", "checkpoint", "what's the status", "hand off", "what are we working on", or "close the thread".
Systematically adjudicate disagreements across a paper collection. Produces ruthless verdicts on who was wrong, what supersedes what, and what the best current understanding is. Organized by topic clusters with actionable replacement values for implementation.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
