Recently updated open-source projects

site-security-assessment tests websites only after an ownership gate: a matching session email domain unlocks passive reconnaissance, while a token file placed under the target domain unlocks deeper levels. The four levels cover passive checks, limited active probes, authenticated DAST, and webhook threat modeling, with per-test approval, evidence-based findings, and false-positive checks. It refuses third-party targets, denial-of-service or load tests, brute force, active automated scanners, and production-data access, and does not bypass harness denials.

Create or review Moodle questions from Claude Code or Claude Desktop, then export them as GIFT, Moodle XML, or Aiken files. The skill supports easy, standard, and challenging modes while checking self-contained stems, plausible distractors, and answer-length patterns that could make correct choices easier to guess.

Put AI To Work is a curated repository for senior managers and directors who want practical AI support without losing their voice. It organizes installable skills, standalone prompts, printable cheat sheets, and recipe-style workflows; the current featured skill audits drafts for vocabulary, structure, tone, and punctuation patterns associated with machine-written copy, then suggests a cleaner rewrite. Artifacts are refreshed quarterly and can be pinned to release tags.

Name Forge turns a product description into a shortlist of candidate names. Four strategies generate ideas in parallel, survivors are checked across GitHub, npm, PyPI, crates.io, and the open web, and the remaining names are scored for memorability, typing, pronunciation, distinctiveness, and domain potential. The report ranks ten names and expands on the top three, but it is not a trademark clearance service.

Neighbourhood Due Diligence Report creates a use-case-specific research checklist for Canadian neighbourhoods, with British Columbia as the primary focus. It adjusts priorities for families, long-term rental investors, short-term rental investors, and commercial users, then covers market data, zoning, transit, schools, safety, demographics, amenities, environmental risks, and investment signals. Each item points to a direct data source, but users outside BC must substitute equivalent local agencies.

Use this Claude Code skill when several ideas, plans, or vendors need a second opinion. It gives each option an independent advocate, then asks a fresh judge to score the matchup against a rubric and verify interpretive claims with primary sources. Prompts, responses, searches, and grades are saved for an auditable single-elimination verdict; it is not designed to produce a full ranking.

Explore an application once through Playwright MCP to generate maintainable spec files, then replay them with the Playwright CLI instead of repeating browser-driven reasoning. The toolkit adds accessibility, console, network, and regression checks, fingerprints bugs across runs, and keeps tests and reports in the repository. It does not include managed cloud execution or human triage.

Create a standup report that combines commits, the active branch, GitHub pull requests, and persistent notes into yesterday, today, and blocker sections. The full install script can auto-log Claude Code sessions through start and stop hooks, while the skills-only install omits those hooks and each /daily run reads just the current repository.

agent-saga turns long-running work with AI agents into serialized documentary fiction grounded in Git history, logs, journals, transcripts, and other configured artifacts. It can create a 20–30 chapter arc, daily entries, a consistent narrator voice, and prose in a chosen language. The skill requires a configured source set and a continuously present agent, and refuses to invent events, agents, or public surfaces that are not supported.

html-to-svg converts an HTML preview into an SVG whose glyphs are embedded as paths, preserving browser line breaks and Variable Font weight and optical-size settings in environments that cannot load the original fonts. It targets static assets such as brand banners; the first run installs Node packages including fontkit, Playwright, and SVGO.

Crafting Portfolio Essays starts with finished writing samples rather than guessing at a personal voice. It asks for essays, transcripts, or informal notes, then produces a `tone-and-soul.md` voice guide and an essay-specific specification through interview questions and one of six narrative archetypes. The skill does not scan files, query Notion, or invent quotations, and it is aimed at personal portfolio essays rather than technical documentation.

The skill turns DOCX files into normalized Markdown by accepting inserted revisions, dropping deletions and comments, repairing heading levels, cleaning tables, replacing broken image references with readable placeholders, and collapsing excess whitespace. A small cross-platform Go binary coordinates Pandoc, so no Python, Node, or Ruby runtime is required. The converter and Pandoc are downloaded lazily on first use and then cached inside the plugin directory.

Scan a codebase, dataset, research collection, or documentation project and turn it into a structured knowledge base. After you approve the proposed architecture, it generates three levels of LLM-friendly context packs, a project-specific Python compiler, and an interlinked Obsidian wiki with search and lint commands.

Use this skill to take an existing interface through a structured audit, domain study, visual direction, build, test, and iteration cycle. It includes playbooks for more than eighteen product domains and a detailed QA checklist covering responsiveness, accessibility, motion, and edge states. Installing it as a custom Skill requires a supported paid Claude plan and Sonnet or Opus 4 or later.

Session Connector keeps multi-day research, experiments, and notebook work coherent across Claude Code sessions. Its save operation snapshots progress and updates each thread, resume surfaces all active threads, and status gives a quick survey without reopening every note. State normally lives under the project’s `.claude/sessions/` directory, with an optional constrained external-drive location. It never deletes old sessions automatically.

Use this knowledge base to draft prompts for interiors, exteriors, landscapes, aerial views, and commercial architectural scenes. It also guides composition, camera choices, lighting, materials, and image preparation, with workflow references for SketchUp, Revit, ArchiCAD, Blender, and D5 Render. A glossary maps more than 150 archviz terms to useful prompt language.

theaccessible converts a PDF through theaccessible.org API into an accessible HTML rendition, a tagged PDF, and a veraPDF PDF/UA-1 conformance report. It returns download links and explains failing rules such as missing tags or alternative text instead of claiming compliance prematurely. The skill requires an API key and outbound HTTPS.

Give edge_source_skill a research question and it returns a scored source list, recommended reading order, coverage gaps, and a practical experiment. Rankings combine relevance, depth, actionability, freshness, and consequence across curated feeds and GitHub resources, with optional Telegram imports. It is designed as the source-discovery stage before separate crawling and Markdown conversion tools.