Recently updated open-source projects

Begin a focus block by defining the task, duration, finish line, and current energy, then optionally enable Do Not Disturb, close distracting apps, and start music. The skill keeps the goal visible without conversational interruptions and records the outcome, next step, and reflection in Markdown for later weekly or monthly review.

Founder Mode turns a set of founder-led operating ideas into 12 Claude Code commands for audits, org health, hiring, delegation, reviews, and decision checks. Each command produces a scored diagnosis, pressure-test questions, and concrete next steps, helping founders decide where deeper involvement is useful and where delegation remains appropriate rather than treating one management style as universally correct.

Use this Claude Code skill to turn a brand brief or an existing site into a detailed website design system covering typography, color, spacing, motion, and optional WebGL direction. Its hub-and-spoke knowledge base loads only the guidance needed for the task and produces four deliverables: a design specification, DTCG tokens, a motion specification, and an implementation plan. Building the site remains a separate stage.

contest-idea-forge helps contest participants turn one contest link into feasible, research-backed project ideas. It gathers and deduplicates papers, checks prior art, technical soundness, citation validity, and team or demo constraints, then has Claude generate, challenge, and rank candidate ideas while deterministic Python handles fetching, paper search, and rendering.

survey-linter checks survey questions for leading wording, double-barreled items, presuppositions, absolutes, vague quantities, recall burden, unbalanced scales, missing options, priming, and fatigue. Its rule engine is deterministic and points each finding to exact wording, with a score whose arithmetic can be reproduced without trusting a hidden model. English and Simplified Chinese are supported, along with text, Markdown, CSV, and common form JSON formats. It runs locally, offline, in a browser, CI, or as a Claude skill.

pmcontext structures Claude Code work into Quick, Standard, and Full workflows with explicit approval gates before implementation advances. It stores decisions, risks, session receipts, and execution state in the user’s own Supabase project so work can resume across projects and machines. Standard and Full workflows depend on the superpowers plugin; context7 MCP is additionally required when a plan touches external libraries.

safe-push-skill helps developers catch secret leaks and repository-hygiene problems before git push. It checks staged files, sensitive content, README freshness, and environment-example parity, then returns pass, warning, or block and stops high-risk pushes.

servicetitan-forms-skill helps Claude build, fix, and refactor ServiceTitan Form 2.0 JSON. It covers the envelope and IsForm20 flag, conditional visibility and micro-rule splitting, common import validation failures, fieldType pitfalls, preview errors, and plain-English-to-JSON form generation. The repository says its patterns were checked against live tenant exports and that the skill ships only Markdown, without scripts or network calls.

Give the skill a company, role, interview date, and your experience, and it generates a tailored standalone HTML preparation app with talking points, question banks, flashcards, a simulation timer, readiness tracking, and browser speech features. The file opens in Chrome without a build step, although speech recognition may require serving it locally when the `file://` protocol is restricted. Web research is optional enrichment.

Meeting Intel Brief takes a person's name, company, and meeting type, then coordinates parallel research on the organization, attendee, and surrounding context. It produces a standalone HTML brief with company facts, personal background, likely goals, conversation openers, questions, and watch-outs for sales, interviews, investing, or partnerships. Current intelligence requires working web-search or MCP tools.

Run Honest Oracle before submitting a pull request to compare claims in the description and commit messages with the actual diff. It extracts statements about testing, performance, parity, and coverage, then runs cheap, safe checks when possible or names the evidence still required. The skill reviews the honesty of the claims rather than code quality and can rewrite the description to match what is provable.

CLAII is a command-line-first coding agent built around a tool loop restricted to a configured working directory. It can inspect and change files, run Python, and keep calling tools until a task finishes. Local knowledge-base references and optional lightweight memory make it a compact core for studying or extending agent behavior.

install-tags-10dobro creates a shared gtm-loader.js and inserts the Google Tag Manager script plus noscript fallback into every HTML page in a directory. Re-running it avoids duplicate tags, each changed page receives a backup, and dry-run plus loader-path options help control the edit. The tool installs the container; GA4 and Meta Pixel tags are configured in the GTM interface afterward. A folder of HTML files and a GTM ID are the minimum requirements.

consumer-dispute-assistant organizes messy refund, subscription, and billing problems into a usable case summary, merchant request, payment-dispute statement, complaint draft, and follow-up log. It helps users preserve a factual timeline and escalate gradually instead of producing only a generic complaint letter. The skill is not legal advice, does not invent evidence, and leaves every external submission under the user's control.

macos-llm-agents is a personal macOS collection for scheduled finance news, neuroscience reading, investment-bank AI viewpoints, daily vault briefs, Apple Notes synchronization, and paper reading. launchd runs the jobs, while a small governance layer injects only the required secrets, centralizes Obsidian paths, reconciles indexes, and catches up missed slots. The repository keeps private values in local templates and requires the user to configure service keys, a vault, and macOS permissions where needed.

Zero Docs mirrors Rocicorp Zero documentation into version-pinned, grep-friendly Markdown so Claude Code can answer ZQL, schema, mutator, permission, and zero-cache questions without a network round trip. A sync script refreshes the local files and records the upstream commit, with a weekly action for updates. It is an unofficial community mirror and needs maintenance when the source changes.

smart-contract-audit reviews Solidity, Vyper, Solana, and CosmWasm code from an attacker’s perspective. It builds a system model and invariants, runs available analyzers, performs manual function-by-function review, and writes severity-rated findings with concrete exploit paths and remediation. The methodology also examines privileged roles, upgrades, oracles, cross-chain messages, and live deployment state before producing a GO, conditional GO, or NO-GO verdict. Coverage of other virtual machines is general and partial, and a clean report is not a guarantee of safety.

Job Search Ops coordinates a five-phase job search: document intake, a structured career-profile interview, a master CV, per-posting fit and tailored PDF documents, then interview coaching with a printable cheatsheet. It keeps applications consistent through a database record, scores capability and preference separately, and preserves honest gap wording. It never fabricates experience, auto-applies, scrapes job boards, or sends applications.