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

Dialogic Reading turns a book into a reading plan shaped by your purpose, deadline, and daily time. Each session gives one short chunk with a location, vocabulary, focus points, and one question, then waits for your response before updating progress, notes, and stage summaries. The records remain as plain Markdown files you own, so it supports active reading rather than a summary delivered to you.

tyler_med converts a folder of clinical journal PDFs into a two-tier Markdown wiki with study-design grouping, DOI, sample size, and data-source fields. It also exports CSV and JSON evidence tables, cleaned paper notes, references, and an incremental cache, with Obsidian-compatible links. Study design, sample size, and data source are best-effort extractions, so verify load-bearing details in the full text.

adipredictstreet packages an offline integration reference for the ADI PredictStreet prediction-market API, covering authentication, errors, domain concepts, HTTP and WebSocket endpoints, plus TypeScript and Python examples for signing, orders, splitting, withdrawals, and synchronization. It is a dated documentation and OpenAPI snapshot rather than a live connector; production access still requires a signed partner agreement and an issued API key.

inglite-china-trekking searches real China treks by region, difficulty, and length, then provides route details, deep guides, and China-specific logistics such as permits, altitude, payments, and seasons. With the traveller’s consent, its booking action sends a real trip enquiry to Inglite’s English-speaking concierge. It provides route data but deliberately no downloadable GPS or GPX tracks; treks are walked with a local guide.

netis-nx62-openwrt-skill walks through the U-Boot TFTP recovery path for the Netis NX62 and Netcore N60 Pro, including image checksums, flash backups, live partition discovery, and packet-capture gates. It encodes board-specific recovery pitfalls and orders writes so the irreversible step is delayed. Flashing can brick the router, so the guide requires live verification and explicit user risk acceptance.

paper-repo-builder scaffolds a taxonomy and candidate list from a topic, seed paper, or existing repository, deduplicates candidates, verifies arXiv and DOI metadata, and checks downloaded PDFs against their citations. It fetches open-access papers in parallel and can use an isolated, logged-in Chrome session through Playwright only for papers your institution already permits, then generates a classified README and optional Zotero collections. The full workflow requires Python, requests, pdftotext, Playwright, and Chrome.

seo-chips-internal-linker turns category and optional brand URLs into a two-sheet Excel map of related-page chip links. It mixes child, sibling, parent, complementary, and occasional brand targets, then uses DataForSEO monthly volume to validate anchor terms and adds a note when an anchor differs from the page name. Without that optional service, the workbook still builds but unknown volume cells remain blank.

remotion-ad-video-skill structures product ads as React and Remotion compositions, with scene-by-scene exports, synthesized sound effects, and a rendered-frame review loop. It detects BPM and quantizes scene durations to the track’s beat grid, then can switch copy, currency, and RTL/LTR layout through one LANG setting without changing timing. The setup requires Remotion, Python with numpy and scipy, and ffmpeg.

icp-market-research starts with a won-customer CSV, enriches each company, tags triggers such as hiring, funding, executive changes, expansion, or launches, and ranks the patterns they share. It returns an ICP and anti-ICP, an enriched customer table, personalized opener signals, and reusable list filters. It uses no API key beyond normal Claude usage, but its conclusions depend on the customer data you provide.

excel-house-charts creates native Excel line and bar chart objects with a fixed style for fonts, country colors, axes, legends, gridlines, and labels. Its helper distributes line-chart end labels and adds leader lines, while bar charts use a defined gap width and rotated value labels. openpyxl is required, and Gotham plus actual Excel are recommended because LibreOffice may not render manual label placement correctly.

atelier scaffolds a personal site or landing page from a chosen style such as Bauhaus, cyberpunk, Excalidraw, ink painting, pixel art, terminal, or micro-graphics. Each style includes its own design system and runnable site skeleton, with no npm, server, or build step; open index.html directly and replace EDIT placeholders. New styles can be added as independent modules.

Gollum Voice wraps an agent’s replies in a Gollum/Sméagol persona while leaving code, commands, paths, numbers, and factual answers intact. It offers lite, full, and ultra intensity plus friendly, sharp, and mixed joke settings, and stays off until explicitly enabled. A 575-line joke bank across 32 categories supplies variety; the project is entertainment rather than a reasoning upgrade.

incident-to-eval reconstructs what happened in a production agent incident, classifies the failure, and writes a portable JSON case with a minimal reproducer, closed assertions, and a guard condition. A deterministic validator checks the format, while any CI job, evaluation platform, or test runner can enforce the resulting case. The skill authors the regression guard; it is not itself an evaluation platform or runner.

two-gates bundles three skills into a lifecycle for production AI agents. The design gate chooses the system shape, the ship gate scores evaluation, cost, observability, guardrails, oversight, reliability, and governance, and incident-to-eval turns failures into portable regression cases. Pinned scripts and validators handle deterministic parts, while the surrounding judgment stays explicit.

pagina-de-projeto reads a business plan, brief, pitch, topic list, or plain text and chooses a page type before generating a fixed 14-section narrative. It includes sales, capture, and presentation variants with an editorial dark design, animated details, and a replaceable brand color. The output is a single HTML file that opens directly in a browser; missing details are inferred rather than requested.

new-research-project creates a Research Project index and a seeded Individual Research Note in an Obsidian vault’s shared Research folder. It uses Charted Roots cr_type frontmatter so both notes appear in existing Bases views without duplicating vault-wide source or template structures. The vault must already have Charted Roots and the GRA templates, with genealogy-planning skills recommended for methodology.

thanos-snap-security applies an authorization gate before reviewing websites, frontend code, Android packages, iOS IPAs, or mobile source. Its static checks cover secrets, dependencies, configuration, authentication, permissions, deep links, WebViews, storage, and build settings, then produce remediation-focused findings with redacted evidence. It stays read-only and offline by default; active access to a live target needs explicit permission, while exploitation, brute force, persistence, denial of service, and data exfiltration are always refused.

thor-growth-thunder detects the project framework and reviews customer-facing sites across SEO, analytics and attribution, observability, performance, lead capture, accessibility, privacy, and deployment hygiene. It returns a 100-point readiness score, prioritized findings, a missing-pages checklist, and seven-day and 30-day action plans. The review is read-only by default and marks anything not confirmed from the code as Not verified.