Shape agent capabilities into your workflow.

linux-wayland-chinese-input-method walks Linux and GNOME Wayland users through installing fcitx5 with Rime and the rime-ice dictionary, including the `IM_MODULE` values that avoid Qt input failures. It also covers switching schemes and basic candidate-panel theming, and can be installed as a Claude skill for guided setup. The instructions target Linux desktops rather than macOS.

Use one CLI workflow for Comfy Cloud image, video, and multi-step generation tasks. It resolves S/A/B/C quality tiers, inspects model schemas to translate dimensions and flags, and includes recipes for characters, storyboards, products, thumbnails, and moodboards. Premium is the default, while budget mode downshifts quality; a Comfy API key is required.

Give it a PRD or product specification, and it chooses between a compact promise-based plan and a broader feature-grid approach before drafting P0, P1, and P2 scenarios. Each scenario pairs user-interface checks with backend assertions and accounts for multi-role permissions, making the skill useful for planning regression coverage in SaaS and other complex products.

Use renwei-zh to review Chinese product copy, reports, essays, or social posts for formulaic phrasing, promotional tone, overclaims, and dense pattern clusters. It marks numbers, dates, citations, and named sources as facts that must be preserved before producing a structural rewrite and follow-up audit. The project works as a Claude or Codex skill and as a deterministic Python CLI with JSON output; no API key is required.

Safe Debug Loop separates a difficult module cleanup into two stages: research and bug inventory without changing production code, followed by an iterative loop that handles one bug at a time. Each fix is paired with an isolated smoke test, an atomic commit, and persistent debugging notes under the project. It is intended for an already-built app or dashboard whose interconnected bugs make ad hoc fixes too risky, rather than for implementing the product’s core features.

This Claude Code skill inspects a task’s type, language, and constraints, recommends a model available through an OpenAI-compatible gateway, and asks for confirmation before invoking it through Bash. Setup stores the API key in a local permission-restricted file rather than chat history, and the workflow can reuse your own prompt files. It requires access to a compatible provider or internal gateway.

Claude MD Architect helps Claude Code create a new CLAUDE.md, extract durable context from a long session, or audit an existing file that has become bloated or contradictory. Its workflows prioritize project-specific commands, rules, and gotchas that the model cannot infer, while moving longer material behind on-demand document pointers. Each mode uses a phased process and finishes with a fresh-session self-test.

codex-council is a Claude Code plugin that sends staged context to two to six parallel OpenAI Codex sub-agents, assigns task-specific roles, and aggregates their replies. Each role keeps its own thread per project and host session, and both Claude Code and the Codex CLI must be authenticated. The plugin launches Codex with approvals and sandboxing bypassed, giving each sub-agent broad filesystem access, so it should not be used with untrusted projects or content.

Audit a CLAUDE.md with a calibrated 0–100 rubric covering specificity, coverage, brevity, currency, captured quirks, and tone fit. The skill returns the top three improvements as paste-ready snippets but does not edit the file. It handles one CLAUDE.md at a time, not AGENTS.md or nested monorepo instructions.

Provide a job-posting screenshot and resume to produce an HTML report with role analysis, resume-to-JD fit and gaps, company and product research, competitor comparison, 13 tailored interview questions with answer structures, and thoughtful questions to ask. It relies on web search and public sources, so important facts should be verified before use.

AlphaDesk feeds Claude a brokerage screenshot, CSV export, or MCP account view and produces a structured report covering holdings, market context, research, flows, risk, and P0/P1/P2 actions. It supports quick, standard, and deep modes, while leaving real orders to the user.

Use this Claude Code skill to formalize requirements, check compliance and compatibility, research current price bands, calculate total ownership cost, and compare vendor risk before buying. It scales the decision method to the importance of the purchase, supports both consumer and business procurement, and produces a cited memo with post-purchase steps for inspection, warranty, maintenance, and eventual resale or retirement.

Mand! teaches a Claude Code agent to answer fully first, then shorten its reply whenever the user says “korter,” “shorter,” “again,” or a similar cue. Repeated turns strip the response down to one word, and the skill can be installed locally or as a plugin.

Ask Claude, Cursor, Windsurf, ChatGPT, n8n, or any HTTP client whether a domain is available across more than 50 TLDs and where registration is cheapest. DigMyName verifies results through several sources and returns an unknown state instead of treating uncertainty as a taken domain. The public endpoint requires no API key, but per-minute and daily fair-use limits apply.

Load this skill when drafting or editing Chinese prose to catch empty openings, report jargon, faux profundity, canned business language, and mechanical structures. Its rules favor concrete scenes, actions, objects, and limits while preserving the original facts, genre, terminology, emotion, and authorial judgment. It is not an AI detector, banned-word list, paraphrasing service, or automatic shortening tool.

Claude Autopilot for Obsidian makes Claude read relevant notes before editing code, update the vault alongside the change, archive sessions, cross-link related work, and optionally sync through git. The pure-Python toolkit runs on macOS, Linux, and Windows; archives stay local and are secret-redacted by default, while pushing them requires explicit opt-in.

Give Codex or Claude a file, diff, pull request, or repository, and the skill produces a severity-ranked security review with an attack-surface map, CWE and OWASP labels, file locations, assumptions, validation questions, and patches in the original language. Results can be formatted as Markdown, SARIF, GitHub issues, JIRA tickets, or executive summaries. It is defensive only and does not replace a professional penetration test.

paypay-securities is a read-only CLI and agent skill for PayPay Securities accounts. It shows assets, cash, funds, US stocks, and trade history, measures stated fees and FX spread, and produces per-symbol summaries and review reports. Multiple accounts, Lark output, and separate session caches are supported.