Shape agent capabilities into your workflow.

stock-research-skill offers Chinese and English variants for multi-source equity research in Cursor and Claude Code. The playbooks combine Schwab market signals, SEC filings, Polygon news, and ClickHouse data for shakeout-with-news and insider-alert analyses, with health checks and version gates before use. The repository is documentation-only; connected MCP servers own the actual API traffic.

java-springboot-code-review examines Java and Spring Boot code beyond style and syntax. It traces transaction and AOP proxy pitfalls, JPA query and locking problems, race conditions, idempotency, IDOR, payment and inventory logic, API contract issues, and data exposure. Each review organizes critical issues, ripple effects, warnings, suggestions, and a pre-merge checklist for engineers working on high-impact services.

agentic-email-skill selects email templates by prospect or client stage and drafts individual messages or multi-email sequences for outreach, sales, follow-up, delivery, retention, referrals, and win-back. A Python renderer can produce branded Markdown and PDF outputs. The drafts require verified recipient, offer, proof, and timing details before use, and the examples explicitly avoid fabricated metrics or client names.

agentic-invoice-skill selects and drafts invoices, pro formas, deposits, milestone bills, change orders, retainers, credits, refunds, receipts, and closeout documents from contract and billing facts. Its Python tools render branded Markdown and PDFs, while placeholders remain visible until client, tax, payment, and accounting details are verified. It is suited to agentic development engagements with milestone-based billing.

riff connects Claude Code with OpenAI’s Codex CLI as a peer collaborator rather than a subordinate tool. Its delegate, consult, and roundtable modes can use Codex MCP or `codex exec`, while a trace contract records context, constraints, execution, and acceptance criteria for non-trivial calls. Codex CLI is required; the MCP server is recommended for cleaner multi-turn exchanges.

agentic-case-study-skill turns verified delivery outcomes into client interviews, anonymized or named case studies, testimonials, technical notes, sales one-pagers, website stories, and other proof assets. It selects formats by evidence, approval status, and channel, then can render branded Markdown and PDFs. Sensitive details and attribution stay bounded, and placeholders must be replaced with client-approved facts before external use.

agentic-customer-success-skill selects and drafts account profiles, contact maps, follow-up trackers, health scorecards, QBRs, renewal reviews, expansion briefs, recovery plans, and offboarding checklists. It keeps account work tied to verified facts, clear ownership, and next steps, while warning against wrong-contact messages, invented sentiment, and unsupported renewal assumptions. Python tools can render the artifacts as branded PDFs.

agentic-delivery-skill supports approved-scope execution from kickoff through evaluation, launch, support, handoff, and closeout. It selects templates for project plans, milestones, decisions, risks, change requests, acceptance packets, monitoring, runbooks, and escalation, then keeps outputs aligned with the engagement’s scope and approval gates. It can feed verified delivery facts back into proposal, contract, invoice, and email workflows, and is designed for bounded agentic pilots rather than open-ended delivery.

agentic-discovery-skill structures early work for agentic development through intake questionnaires, discovery scripts, interviews, workflow maps, readiness checks, risk reviews, success criteria, evaluation worksheets, and proposal handoff briefs. It focuses on bounded scope, approvals, logging, monitoring, documentation, and support, helping a team clarify unknowns before a proposal is written. Python tools can render the selected artifact as a branded PDF.

agentic-proposal-skill turns verified discovery into buyer-facing one-page pilots, proposals, SOWs, roadmaps, evaluation plans, risk and control plans, change orders, and approval summaries. It chooses the document by buyer stage and decision need, while keeping scope, assumptions, risks, acceptance criteria, and approval gates visible. Templates remain drafts until pricing, timeline, and other client facts are verified.

agentic-security-review-skill creates bounded review artifacts for permissions, data exposure, credentials, tools, retrieval sources, external actions, launch blockers, rollback, and incidents. It selects checklists and memos by the change or launch event, then keeps controls, logs, approvals, and escalation paths explicit. The output is a practical review draft, not a substitute for the technical or client signoff needed for a real launch.

agentic-envelope-skill creates printable CompleteTech-branded #10 envelope PDFs from recipient and artifact facts. It can add a logo, return address, recipient block, attention line, postage box, attachment manifest, and delivery-readiness notes, with default or per-recipient overrides. Missing address or approval information leaves the package blocked rather than ready for handoff.

did-it-actually decomposes a user request into falsifiable acceptance criteria, records implementation claims, and audits the result with deterministic checks plus a fresh-context critic. Missing or unsupported claims trigger a fix-and-re-audit loop capped at three iterations, with a mechanically grounded VERIFIED or NOT VERIFIED verdict. It checks request fidelity rather than serving as a code reviewer, security scanner, or test framework.

Use this Claude Code skill to review a Git diff or selected files through OpenRouter. Findings must include matching verbatim quotes, and confirmed fixes can be applied directly. It chooses usable free models from the catalog, falls back to a low-cost model when needed, and requires an OpenRouter API key.

Render Word, PowerPoint, or PDF pages and audit them with a structured visual rubric covering layout, typography, color, content, and coherence. The skill reports findings rather than proposing fixes; scanned PDFs can be checked for layout but are not OCR-checked, and Office rendering needs LibreOffice plus an Anthropic API key for the visual audit.

Audit a LaTeX paper before submission for anonymity, reference hygiene, required sections, and page limits measured from a real PDF compile. A reviewer-style checklist also flags issues such as missing model versioning or mismatched ablations. Venue rules arrive through overlay skills; this is an audit toolkit, not a drafting assistant.

Use this Claude skill while building or auditing a WordPress plugin for the wp.org directory. It focuses on security, REST permission callbacks, remote assets, text domains, privacy, and bundled-library collisions, with references loaded as needed. It intentionally skips themes, standalone PHP, and pure frontend work.

Ask Claude Code to render architecture, dependency, file-tree, sequence, state-machine, flowchart, data-flow, or ER diagrams on a live Excalidraw canvas. Dependency maps and directory trees can be generated deterministically from project files; other diagrams use model composition, and the setup requires the canvas server plus PyYAML for dependency maps.