Start with the job, then find an open-source answer

env-paper-writing collects six Claude skills for environmental science and engineering papers: section drafting, abstracts, figure captions, cover letters, reviewer responses, and data-availability statements. It preserves LaTeX commands, uses domain terminology and units, and avoids inventing missing data; authors remain responsible for accuracy and disclosure.

redesigner captures a website with Playwright or a native app with Maestro, then creates a navigable mock, design analysis, UX findings, and a React-based redesign with Tailwind and Framer Motion. It can export HTML, Figma, and Pencil artifacts after approval. Logins are manual, and capture stays read-only.

repo-summarizer analyzes a repository's structure, dependencies, modules, data flow, configuration, and tests, then writes an Obsidian-ready architecture document plus a one-page quick reference. It works across frontend, backend, monorepo, full-stack, and mobile projects, and is invoked with /summarize.

City Food Guide builds a static bilingual restaurant site from one JSON file and a set of photos. Visitors can filter and search venues, mark visits, browse a map, and generate share cards, while creators can export a PDF and map data or offer email-gated downloads. The result has no backend and can be deployed to common static hosts.

intune-conflict-detector reads an offline Microsoft Graph export, normalizes settings across policy types, and intersects assignments before reporting conflicts or duplicate values. It catches custom OMA-URI and cross-type issues that the Intune view can miss. The analyzer is read-only, uses only the Python standard library, and does not contact a tenant.

intune-drift-sentry compares two exported Intune snapshots by canonical setting identity, classifies changes by risk, and writes one reverse step for each change. It can emit a receipt that checks whether the rollback covers the diff, but remains offline and read-only; applying Graph-level actions is a separate human-approved step.

netguard-config validates a proposed Cisco IOS-style configuration without contacting a device. It checks addressing math, duplicate IPs, routes, dangerous access and management lines, then produces an ordered rollback. The tool is a heuristic linter rather than a full IOS parser or simulator, so lab validation and human approval still matter.

import-sentinel resolves Python and JavaScript/TypeScript imports against the standard library, dependency manifests, and local modules. It flags missing packages, one-edit typosquats of popular names, and real dependencies that are not declared. The offline standard-library tool can scan a project or diff as a pre-commit gate, with heuristics clearly separated from package-index checks.

blast-radius reads a unified diff and reports its scope, severity, and high-reach signals, including committed secrets, authentication changes, deleted tests, deployment files, migrations, and dependency manifests. It can fail a pre-merge gate at a chosen threshold, but the score is a review signal rather than a correctness verdict.

discord-history-export uses a headed Playwright browser for a user login, captures the target server details, exports visible channels and threads, and reorganizes the result into category-based HTML plus parallel JSON. It is a one-shot archive, not sync or monitoring. Automating a user account can conflict with Discord's ToS, and the skill advises changing the password afterward.

offboarding-auditor examines a departing engineer's code and documentation for knowledge silos, account bindings, unfinished work, dependencies, and test coverage. It scores how independently a new owner could take over, then produces a severity-ranked report and assignable fixes to complete before departure. The focus is inheritability, not code style.

EasyEDA Pro Claude Skill adds a netlist-first discipline on top of the official API, MCP servers, or computer-use editing. After each change it checks pin-to-net connectivity in the exported text, catching floating wires, silent net merges, and part-swap pin remaps. EasyEDA Pro and an editing channel are required.

tech-audit routes a codebase review into quick, security, release, deep, or full modes across a 13-dimension framework. Stack-aware extensions cover PHP/Laravel, Python/FastAPI, TypeScript/Node, shell, and Docker, while calibrated severity keeps real blockers separate from minor findings. It suits PR checks, release gates, and deeper technical reviews.

China Report Navigator turns a Chinese equity or industry research question into a searchable report pack. It organizes broker coverage, target prices, ratings, valuation, forecasts, and operating metrics while separating official facts from analyst views and agent inference. Outputs include CSV matrices and editable memos; blocked PDFs remain as manual links rather than being fetched by bypassing access controls.

outreach-stack guides outbound writing through four skills: cold email, LinkedIn messages, follow-ups, and recipient research. It asks forcing questions before drafting, respects each channel's length and CTA limits, and produces variants with different strategic outcomes instead of cosmetic rewrites. A shared linter removes common bot-like phrasing; Bun is optional for local voice memory and linting.

Socratic Mirror creates one interactive HTML lesson for a concept. Two unrelated parables introduce the shared mechanism, followed by staged multiple-choice questions on comprehension, misconceptions, analogy, recall, and transfer; each first answer locks and receives immediate feedback. Pages work offline without dependencies, but the method intentionally uses recognition questions rather than free-text explanations.

travelguide-composer parses Markdown, DOCX, XLSX, or PDF itineraries, catalogs missing structural details, and delegates prose for each gap to the companion travelguide-copywriter skill. It then compiles a roadbook or interactive guide with photos, maps, and climate information in one of six styles. The companion skill and Node/Python dependencies are required.

Watson turns a brief field observation into three distinct takes: Service Design, Business Model, and Trend. Each lens adds one Socratic question, with an optional deepen mode for a fuller analysis. Saving is opt-in and writes a structured Markdown note only after the user asks, so the default experience remains chat-only.