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

seocompass-skill brings SEO, GEO, and AEO workflows into Claude. It can find quick wins from Google Search Console, compare whether AI search engines recommend you or competitors, find backlink prospects and draft outreach, and run a hosted URL audit with a free SEOcompass key. Bring your own keys or use the hosted option; this DIY skill does not provide the app’s ongoing tracking and automation.

presentation-evaluator scores a talk or keynote using Louise Beale’s framework for speaking powerfully in the age of AI. It checks audience fit, the opening hook, message focus, one clear intent, spoken language, and vivid examples, then asks what should be left out. The result is a one-shot evaluation for sharpening the human layer of a presentation, not a rehearsal loop or slide generator.

solana-incident-response-skill structures a live Solana security response around detection, containment, investigation, fund tracing, and the remaining response tracks. It prioritizes reversible, authority-gated actions such as pausing systems, rotating authorities, locking multisigs, and invalidating pre-signed transactions. Investigators can replay an exploit on a Surfpool mainnet fork to separate a code bug from key compromise. It provides operational support, not legal advice or a guarantee of recovery, and named human authority must approve fund-moving or program-changing actions.

Hyperloop asks you to define the destination and verification criteria, then loops through planning, building, checking, review, and repair until the criteria pass. It scans the project to recognize its stack and can account for common frontend, backend, database, hosting, and auth setups. You still own the acceptance checks and final review; the skill automates the loop rather than promising correctness by itself.

dev-forge stores bug descriptions, root causes, impact, solutions, and lessons as plain Markdown and YAML on your disk. Log a problem with Git context, search past causes before repeating the work, resolve it with the fix commit and time spent, then forge lessons, reports, or resume bullets from the same records. Optional auto-capture can run silently, but it is off by default and does not require a hosted account.

zip-code-research takes a service radius, combines it with US Census ACS data and ZIP boundary shapes, and produces Include, Test, and Exclude targeting lists plus an interactive map. It is aimed at home-services financing teams that want to choose markets more deliberately and reduce credit denials. The scoring rationale can be adapted by vertical, while the underlying script uses only Python’s standard library.

design-room evaluates a website through seven codified lenses, covering first impression, conversion usability, decision psychology, positioning, technical accuracy, and feasibility or boldness. In grounded mode Claude assembles source-backed options while you decide; a weekly modernity pulse and anti-slop gate challenge stale or generic output. Each decision is appended to a dated, hash-chained decisions.md record so later sessions can see what changed and why.

Go Lean SDD sizes planning to the change: minor work stays in conversation, while larger features earn durable artifacts. Every change includes colocated tests plus a mutation-style discrimination check that proves the test can fail, and the agent searches the project, dependencies, standard library, framework, and platform before adding new code. It keeps durable context in one AGENTS.md instead of a stale scaffolding tree.

chalktalk teaches an AI coding agent to turn a math topic into an end-to-end animated explainer with scene design, rendering, and frame checks. It uses Pango text and Unicode for equations, avoiding a large TeX installation and its common rendering traps. Setup scripts prepare the Python environment, animation engine, Cairo, Pango, and FFmpeg on macOS or Linux; the result is a rendered video rather than an editable lesson deck.

skill-planok packages the PlanOK CRM REST API documentation in Spanish and English for Claude Code and other Agent Skills runtimes. It covers endpoints, authentication, parameters, schemas, and examples across the CRM modules, and includes a local CLI for keyword searches. The skill explicitly refuses to invent an endpoint or field when the documentation does not declare it.

hekouwang-channel-analyst reuses your Chrome login session to pull your own Xiaohongshu creator-backend data into CSV time series. It analyzes the view-to-profile-to-follow funnel, out-of-pool diagnosis, note rankings, trends, and follower-target levers, then builds a self-hosted ECharts HTML report with one priority action and one explicit “do not do.” Historical recommendations are compared with later results; it does not inflate metrics or promise follower numbers.

debrief is a conversational learning ritual, not a document generator. It narrows the session to a few ideas, asks you to reconstruct each one in your own words one question at a time, reveals and corrects gaps only after the attempt, and distills a transferable principle with an optional durable note. It deliberately stays out of mechanical tasks, mid-task flow, and ordinary status recaps.

codex-image-gen drives an interactive Codex pane through tmux, requires an explicit absolute save path, waits for the file, and verifies the image and target aspect ratio with ffprobe or PIL. If the expected file is missing, its helper searches the Codex generated-images cache and can recover base64 data from the newest session rollout JSONL. It is a reliability wrapper around an interactive workflow, not a standalone image model.

trip-planner builds an itinerary around geography, dates, and logistics before filling it with attractions. It red-teams the plan for long transfers, closures, holiday traffic, weather, vehicle capacity, and other failure modes, then verifies places against the actual travel dates. The output is a clean group-friendly PDF with route context, book-now warnings, and Google Maps links that open when a traveler taps each stop.

launch-doctor-kr scans a Korean Android app before Google Play submission, with checks for missing Maps keys, outdated targetSdk, release debuggable flags, Capacitor Hangul input issues, location-service reporting, AI-content labeling, and privacy-policy gaps. Findings include a file location, a suggested fix, and a supporting link. It is aimed at small teams using Capacitor, React Native, or Flutter.

visualizing-data helps an agent choose a chart from a message-first framework and a catalog of more than 24 chart types. It covers decision trees, annotations, operational dashboard patterns, perception principles, colorblind-safe color systems, performance, and HTML or document output. The emphasis is on making the intended message legible and accessible, not merely decorating a dataset.

genai-prompt-optimizer finds every LLM call in a GenAI app, pins one model per run, and derives adversarial cases from the app’s prompts and JSON schemas. It first records the expensive model as an oracle, then iterates on the cheaper student’s prompt and re-verifies each cohort with deterministic checks, semantic comparison, and limited judge review. The result reports measured token cost and projected savings; it asks for consent before the token-heavy run.

schedule-reminder is a persistent, queryable store for todos, events, deadlines, and progress rather than a calendar UI. Its state machine covers pending, doing, done, blocked, and cancelled; a local Discord relay dispatches due reminders, while other skills can use the stable JSON CLI. It also handles idempotent ticks, missed-fire catch-up, retries, and concurrent read/write checks without becoming a cloud service.