GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
test-discipline
Update tests when changing APIs — no exceptions
sales-analysis
Turn the RAW weekly sales rows and catalog facts from the Sales & Performance MCP into merchandising analytics by running the bundled sales_analysis.py script. Use first in an end-of-quarter markdown review, when a manager wants top sellers and slow-moving / dead stock over a period. The MCP returns raw data only, so the script derives velocity, weeks-of-cover, and margin, then prints the top sellers and slow movers as structured JSON. It renders NO charts (the merch-report-html skill owns all visuals) and does NOT decide discounts (hand the slow movers to markdown-optimizer).
squad-conventions
Core conventions and patterns used in the Squad codebase
prorated-refund-calculator
Calculate the exact prorated refund when a customer cancels a BlastPass membership, and the net settlement when a defective unit is traded up to a pricier model. Use after the Store Policy Agent confirms the refund rule and the Membership MCP has returned the membership details. The skill runs a bundled Python script so the arithmetic is exact.
points-reconciliation
Reconcile a customer's BlastPoints loyalty balance after a complex visit (purchases, returns, promo multipliers, expiry) and convert the net balance to store credit. Use when an associate asks about a member's points, or after a return that should claw back previously earned points. The skill runs a bundled Python script that applies the base earn rate, promo multipliers, tier bonus, clawbacks, and expiry, then prints a points ledger and the redeemable store-credit value.
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
merch-report-html
Generate the shareable end-of-quarter markdown review as a single self-contained interactive HTML report by running the bundled merch_report.py script. Use as the final step once the analysis and policy-bound markdown recommendations are decided. The script renders top sellers, slow movers, and the markdown recommendations into one BlastBox Omega themed HTML file with inline SVG charts, sortable tables, and a clearance toggle - no internet, no external assets. Hand the file to the manager to download and open in any browser.
secret-handling
Never read .env files or write secrets to .squad/ committed files
membership-card-png
Generate a digital BlastPass membership card as a PNG image by running the bundled card_png.py script. Use when a member self-serves a lost/stolen/damaged card replacement, or any time a card needs to be shown on screen (vs. printed). The skill takes the member details returned by the Membership MCP (get_membership) plus the new_card_serial returned by reissue_card and passes them as command-line flags to a bundled Python (matplotlib) script that renders a CR80-sized membership card to a real PNG. It only renders the card from already-retrieved values — it never looks anything up or invents data.
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
membership-card-pdf
Generate a printable BlastPass membership card as a PDF. Use when an associate or member asks to print, reprint, or replace a BlastPass membership card. The skill takes the member details returned by the Membership MCP (get_membership) and generates and runs a short Python (reportlab) snippet that renders a CR80-sized membership card to a real PDF file. It only renders the card from already-retrieved values — it never looks anything up or invents data.
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
markdown-optimizer
Recommend a discount percentage and new price for each slow-moving product by running the bundled markdown_optimizer.py script, respecting pricing guardrails that come from the Store Policy Agent (never hardcode them). Use after sales-analysis-chart has identified the slow movers and after fetching the markdown guardrails via the Store Policy Agent's get_markdown_policy. The script applies the max-discount cap and margin floor, computes each new price and margin, flags items that cannot be meaningfully promoted within the floor for clearance instead, and renders a recommended-discount chart.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
bundle-settlement-calculator
Calculate the exact settlement when a customer returns a multi-item BlastBox Omega bundle (console, accessories, games) and optionally cancels a BlastPass membership in the same visit. Use after the Store Policy Agent (Policy RAG MCP) has confirmed which lines are returnable and the restocking/store-credit rules, and after any membership proration refund has been computed. The skill writes and runs a short Python snippet that applies restocking fees, the store-credit goodwill bonus, tax, and the membership refund, then prints an itemized settlement for the slip.
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
distance-calculator
Calculate the great-circle distance between two locations. Use when the user wants to know how far apart two cities, towns, or places are. The skill asks for two locations, looks up their geographic coordinates via web search, then computes the distance with a Python script.