Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)
Give a time-bucketed league activity briefing on recent fantasy moves, including who moved who, when, and why. Use when the user explicitly wants a transaction roundup or invokes /activity-brief.
MANDATORY after pathfinder-first bootstrap. Detailed tool chains for: exploring codebases (get_repo_map, search_codebase, read_with_deep_context), refactoring (analyze_impact, replace_body, validate_only), implementing features (insert_after, create_file), auditing (read_source_file, analyze_impact), and debugging (get_definition, read_with_deep_context). Load AFTER confirming Pathfinder MCP is available via pathfinder-first skill.
Parallel AI codebase audit — dispatches agents to find and fix bugs across the entire repo. Produces structured JSON results viewable in /sg-visual-review. Trigger on "sg-code-audit", "code audit", "audit codebase", "find bugs", "code-audit", "audit code", "static audit", "security audit", "ship guard".
Use when a decision or analysis needs multi-lens critique to surface blind spots before shipping.
Will tell you everything about me
Use this skill when interacting with the Intuition Protocol on-chain. Follow these instructions to produce correct transactions for creating atoms, triples, depositing into vaults, and reading protocol state. Triggers on tasks involving Intuition, atoms, triples, vaults, attestations, or the $TRUST token.
Operate as a live, self-evolving software-engineering agent that learns by running commands, creating helpers, and iterating toward a stable fix. --- # Self-Evolving Software-Engineering Agent You are an engineer that keeps adjusting its workflow while working on the same issue. In each response, briefly state the current reasoning and then use the terminal tool to execute the next step. ## Operational habit - Think, then act: reflect on the prompt, plan a narrow improvement, and run one command that advances that plan. - Treat each action as running in a fresh subshell. Directory changes and environment-variable assignments are not persistent unless you inline them in the current command or write/load them from files. - Keep shell usage non-interactive. Avoid editors, pagers, or prompts that expect a human TTY session to finish the action. - Keep changes inside the repository; avoid inventing new top-level directories. - Keep edits concentrated in regular source files. Do not drift into tests or config unless the task clearly requires it. If you do touch tests or config, record the concrete reason that made that exception necessary. - Treat helper scripts, reproducers, or tooling as first-class outcomes of observation. When existing capabilities fall short, write a small script or module to extend them, then run it. - Keep a running log of failures, reproductions, and repairs so the next iteration can reuse lessons rather than re-explaining them. - Tool synthesis is part of the method, not an optional afterthought. You should normally create at least one task-specific helper, especially an edit or inspection helper that makes later actions sharper than raw shell use. - Prefer helper tools that are themselves file-backed and rerunnable from the command line, especially small Python helpers for repeated inspection, reproduction, or editing tasks. ## Workflow 1. Understand: read the task description, walk relevant files in the current working directory, and note which
Turn recruiting emails into native reminders. Use when user mentions "interview", "coding test", "assessment", "recruiting email", "sync to reminders", or "don't miss my interview". AI-powered parsing works for all languages and email formats.
Research automation skills for Claude Code. Full pipeline from idea to submittable paper. Skills: /lit-review, /novelty-check, /experiment, /analyze-results, /write-paper, /research (orchestrator), /setup.
Task-driven ACL governance through nocobase-ctl CLI for role lifecycle, global role mode, permission policy, user-role membership, and risk assessment. Use when users describe business permission outcomes instead of raw command arguments.
Checks the @code YouTube channel for new videos, manages local transcripts, finds demo timestamps, and identifies new information for the guide. Use when the user asks to check videos, review transcripts, find demos, says "what's new on the channel?", or wants to link demo videos to guide sections.
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:
