Use when attacking Active Directory environments, hunting Kerberoastable accounts, AS-REP roasting, DCSync, Pass-the-Hash, Pass-the-Ticket, BloodHound path analysis, LDAP enumeration, GPO abuse, ACL abuse, or full AD domain compromise chains. Also use when the user says "attack AD", "domain compromise", "Kerberoast", "DCSync", "BloodHound", or "lateral movement".
用于创建架构类 Issue（RFC 风格）。当用户需要明确模块边界、核心设计和落地路线时使用。
Run a regression-tests-first cleanup/refactor workflow to reduce slop
Two-mode planner — produces plan.md from CONTEXT.md (Planning), then decomposes approved plan into task JSON files phase-at-a-time (Decomposition)
Fight as Neo from The Matrix. Use when the user describes combat scenarios, attacks, fights, or battles against Agent Smith. Handles martial arts (punches, kicks), firearms (bullets, guns), and sword combat using MCP tools that return text art.
Cross-plugin data model for claim verification — defines ClaimRecord, DeviationRecord, and ResolutionRecord schemas, status transitions, deviation types, severity levels, and workspace layout. Use this skill whenever you need to understand claim data structures, create or validate claim records, check what fields a ClaimRecord has, understand deviation types or severity levels, or work with the cogni-claims directory layout. Any plugin that submits or consumes claims should consult this skill for the contract.
Use this skill for adversarial AI testing — red-teaming, guardrail verification, bias detection, prompt injection testing, and compliance auditing of any application with an AI component. Triggers
Audit a PR's structural choices against architecture-priming, the repo's own architecture.md, and any nested boundary configs. Use when the user says "audit this PR's architecture", "check the boundaries", "is this PR clean structurally", "post-merge review of #N", "do a structural review", "what's the boundary impact of this PR", or asks to fact-check the lift / extract / share decisions on a refactor PR. Output is an audit doc at `docs/audits/<YYYY-MM-DD>-<topic>.md` (or — until the first audit lands — a `docs/audits/.gitkeep` + the new file). NEVER edit source while running this — produce a findings doc + a per-finding plan first.
Install the DeepVista CLI. Load when the `deepvista` binary is missing from PATH (hooks/commands return "command not found" or silently no-op), when the user asks how to install DeepVista, or when `deepvista auth login` hasn't been run yet. Ships with the DeepVista Claude Code plugin so the install path stays discoverable even before the CLI is present. --- # Install the DeepVista CLI The DeepVista Claude Code plugin requires the `deepvista` CLI to be installed separately. Without it, the plugin's `SessionStart` hook exits silently and no catalog skills sync. ## Install ```bash uv tool install 'deepvista-cli[ui]' # preferred # or pip install 'deepvista-cli[ui]' ``` The `[ui]` extra adds the optional terminal UI (`deepvista ui`). Omit the suffix for a CLI-only install. ## Authenticate ```bash deepvista auth login # opens a browser for OAuth deepvista auth status # verify ``` ## Trigger a first sync Once the CLI is installed and authenticated, force the plugin's catalog
Use Chirp when you need local, offline text-to-speech with optional voice cloning. Chirp provides a small native server that can create WAV files from text using Qwen3-TTS.
Flip the snap spec default version. Updates all files that reference the current version — constants, docs config, SKILL.md files, template, and llms.txt.
This skill should be used when conducting architecture review with area/performance/power tradeoff analysis. Saves review reports to reviews/ directory.
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:
