Find the open-source solution that fits.

scraper offers an article mode for clean text and metadata and a soup mode for CSS-selected fields. It respects robots.txt, handles retry and exponential backoff, writes JSONL incrementally, resumes successful URLs after interruption, and can seed work from a sitemap. The tool identifies HTML, PDF, and JSON responses and can optionally use ScraperAPI for proxying or JavaScript rendering. It is intended for auditable collection rather than unbounded crawling.

Job Trawlers Interview Prep gathers the target role, your background, interview stage, and interviewers, then researches the company and people to build a tailored preparation kit. It maps likely questions and follow-ups to STAR stories, suggests sharp questions to ask back, and runs a one-question-at-a-time mock interview with candid feedback. The downloadable skill is released under CC BY 4.0, so reuse and adaptation require keeping the required attribution.

docs-to-md crawls an in-scope product documentation site and converts each page into an OKF v0.1 Concept: a Markdown file with YAML provenance and navigation metadata. It builds per-directory listings, a glossary, change log, and bundle index, rewrites internal links to relative Markdown paths, and validates the result against the OKF specification. The crawler runs with uv and keeps images as absolute source URLs instead of downloading them, giving agents a navigable local mirror.

mastery-loop ingests slides, textbooks, PDFs, notes, or a course folder, builds a map from easier to harder material, and creates active-recall items for a daily review session. A real FSRS scheduler interleaves questions, waits for the learner’s answer, handles errors and Feynman checks, and adapts future reviews. Knowledge stays in Markdown and JSON owned by the user, while the scheduler needs Python’s standard library and readers for any binary formats.

sift builds one local full-text index across Claude Code, Codex, and Cursor session files, then returns ranked matches with snippets, timestamps, and tool filters. It can rebuild the index, list recent sessions, and run as a terminal command or an agent skill. Source logs and databases remain read-only, with no network access, telemetry, cloud dependency, or synchronization. It is useful when each coding assistant’s built-in history search is separate or too limited.

rust-coding-skill gives coding agents progressive guidance on ownership, errors, data modeling, traits, concurrency, testing, API design, unsafe code, and security tooling. The same reference set is exposed through Claude Code, Codex, Cursor, Copilot, Cline, and other agent instruction formats. Each task ends with cargo fmt, cargo clippy -D warnings, and cargo test, encouraging idiomatic code rather than code that merely compiles. It is a ruleset and verification habit, not a replacement for Rust tooling.

Construction Plan Review checks permit sets sheet by sheet across disciplines, then coordinates contradictions between sheets and compares revisions. For active jobs it tracks revised sheets, ASIs, RFIs, shop drawings, inspections, and plan-versus-field questions, returning either a structured issue log or a short action list. Regulatory points are marked for verification rather than declared compliant, and the skill is designed for plan checkers and owner representatives.

FoFo Council of Personas sends one question to several adversarial roles in parallel, has them peer-rank one another, lets a Devil’s Advocate attack the emerging consensus, and asks a Chairman to synthesize the final call. Seats can use different model lineages and an optional shared web brief, while the project offers both a command-station UI and a headless Claude skill. Running it requires Gemini or compatible model endpoints and their credentials.

FoFo SDLC separates the context that writes tests from the context that writes code, then uses a referee to grade both the implementation and the tests. Scripts enforce assertion intent, traceability, separation, and secret checks with real non-zero exit codes, so quality cannot be reduced to instructions the agent claims to follow. The plugin is stack-agnostic and sits beneath an existing specification or TDD workflow. It targets Claude Code and requires Python plus Node.

content-repurposer analyzes one Instagram Reel or TikTok with audio transcription and frame OCR, identifies its call to action, and rewrites the on-video text and caption for Instagram, TikTok, and YouTube. It can upload and schedule TikTok and YouTube through the user’s Zernio account, while Instagram remains manual by default unless a paid connection is enabled. The original file is never modified; local media tools, a Zernio account, and its key are required.

gpt-image-2-prompting-skill turns an image request into six blocks covering intent, subject, composition, text, style, and constraints. It selects from 13 templates and 29 scene recipes, with guidance for image-to-image work, series consistency, and troubleshooting, so creators can specify a repeatable visual result instead of relying on one-off prompt examples.

wporg-plugin-submit scans a WordPress plugin and builds a clean upload archive before submission to WordPress.org. Its preflight and reference maps cover common rejection points such as prefixes, permissions, sanitization and escaping, internationalization, hidden files, readme and header drift, and plugin policy rules.

reels-to-site downloads videos from TikTok, Instagram profiles or chats, or loose links, stores media in Cloudflare R2, transcribes audio with Groq Whisper, and builds a Netlify site with playable cards and transcripts. A manifest makes runs resumable. The R2 bucket must be publicly readable for playback. Groq and R2 configuration are required; Netlify credentials are needed only for deployment, and Instagram profile/chat sources additionally need a session cookie.

engineering-craft extracts implementation practices from ten exemplar codebases, covering testing, simplicity, operational robustness, extensibility, resource control, and API discipline. A practice enters its principles index only after converging across at least three unrelated projects and includes boundary conditions, so Apply and Review mode recommendations can stay calibrated instead of becoming blanket rules.

master-learning runs a separate research pass before coding, inspecting local conventions alongside official documentation, papers, standards, and GitHub examples. It returns a decision-ready Learning Brief with domain concepts, implementation patterns, risks, source quality, and open questions, while skipping trivial edits and fixes with clear local evidence.

academic-credentials-skill guides institutions through issuing, verifying, and managing academic diploma SBTs on Solana. It covers Token Extensions, Metaplex metadata, batch issuance, QR or wallet verification, revocation and compliance concerns, plus a migration path from Polygon or other EVM systems.

qld-re-compliance answers Queensland property-sales questions only from structured rule files linked to legislation, approved forms, or regulator guidance. It covers Form 6 appointments, commissions, marketing and pricing, offers, and seller disclosure, labels the authority tier, refuses when no rule applies, and explicitly is not legal advice.

repo-onboard gathers repository, manifest, entry-point, test, and CI signals, then forms an evidence-linked view of the project's purpose, stack, and current state. It persists that understanding for reuse, asks the user to confirm or correct it, and only then asks what to do, without editing the repository during onboarding.