Find the best CLAUDE.md, AGENTS.md and Claude skills

GeiserXSkill

refine-loop

GeiserX/agent-skills/skills/refine-loop/SKILL.md

Use when the user asks to refine, polish, or keep improving a repo and no specific tasks remain.

GeiserXSkill

research

GeiserX/agent-skills/skills/research/SKILL.md

Researches a question with independent parallel specialists that gather evidence from the code, its history, and primary sources, then synthesizes a ranked, cited answer. Use when invoked explicitly for research before a decision.

Often used withdaily-arxiv·Problem-Solving Techniques·setup-ts-deep-modules

GeiserXSkill

review-code

GeiserX/agent-skills/skills/review-code/SKILL.md

Audits a whole codebase in bounded waves of independent parallel auditors, publishes every verified finding ranked by severity, and applies only safe, in-scope repairs. Use when invoked explicitly for a codebase health review.

GeiserXSkill

review-pr

GeiserX/agent-skills/skills/review-pr/SKILL.md

Review one or more pull requests as a single Workflow run (three lenses, one fixer, one adversarial verifier), comment the plan on each PR, push the fixes, then merge or close. Use when asked to review, fix up or merge a PR, or on "review-pr".

GeiserXSkill

revive

GeiserX/agent-skills/skills/revive/SKILL.md

Bring cut-off work back exactly where it stopped after a usage limit, a crash, a restart or a compaction, without doing anything twice. Use when a session resumes after a limit or crash, when agents or background tasks died mid-work, or when asked to continue, resume or revive.

GeiserXSkill

sergio-loop

GeiserX/agent-skills/skills/sergio-loop/SKILL.md

Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal, with optional lease-backed coordination across sessions. Use only when the user explicitly invokes sergio-loop.

GeiserXSkill

submit-awesome

GeiserX/agent-skills/skills/submit-awesome/SKILL.md

Get an open-source repository listed in third-party awesome lists, one pull request per list, by each list's own rules. Use when asked to submit a repo to awesome lists or to continue an awesome-list sweep.

GeiserXSkill

verified-reply

GeiserX/agent-skills/skills/verified-reply/SKILL.md

Draft a reply the user will send as themselves, with every factual claim checked against a live source first and posted only after they approve the exact text. Use when asked to answer a message, reply to a thread, PR or ticket comment, or check a reply the user wrote.

GeiserXCLAUDE.md

atlassian-browser-mcp

GeiserX/atlassian-browser-mcp/CLAUDE.md

MCP server wrapping upstream mcp-atlassian with browser-cookie authentication via Playwright. Designed for Atlassian Server/Data Center instances behind corporate SSO where API tokens are not available. Authentication and serving are deliberately…

GeiserXCLAUDE.md

pumperly-mcp

GeiserX/pumperly-mcp/CLAUDE.md

Generated by LynxPrompt CLI This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands. Architecture in one line: issues live in a…

GeiserXAGENTS.md

biblical-atlas-mcp

GeiserX/biblical-atlas-mcp/AGENTS.md

biblical-atlas-mcp is a Go MCP server for the biblical-atlas Bible atlas. It downloads the atlas's public data file (https://biblical-atlas.geiser.cloud/data.json), indexes it in memory and answers ten read-only tools. The design is in docs/design/DESIGN.md; read it before changing behaviour. User docs are in docs/. This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands. Architecture in one line: issues live in

GeiserXCLAUDE.md

biblical-atlas-mcp

GeiserX/biblical-atlas-mcp/CLAUDE.md

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands. Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns. The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions. This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and…

GeiserXCLAUDE.md

homebrew-lynxprompt

GeiserX/homebrew-lynxprompt/CLAUDE.md

Homebrew tap for LynxPrompt. AI configuration blueprint manager for AGENTS.md and CLAUDE.md files. Standard Homebrew tap with formula definitions in Formula/. Generated by LynxPrompt CLI This project uses bd (beads)…

GeiserXCLAUDE.md

lynxprompt-mcp

GeiserX/lynxprompt-mcp/CLAUDE.md

Generated by LynxPrompt CLI This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands. Architecture in one line: issues live in a…

GeiserXCLAUDE.md

lynxprompt-vscode

GeiserX/lynxprompt-vscode/CLAUDE.md

Press F5 in VS Code to launch the Extension Development Host. The extension reads these VS Code settings: Generated by LynxPrompt CLI This project uses bd (beads) for issue tracking

GeiserXCLAUDE.md

unsent

GeiserX/unsent/CLAUDE.md

unsent is AutoRecover for AI agent prompts: a Go wrapper that runs an agent CLI in a pseudo-terminal and keeps the text in its input box saved on disk.

GeiserXSkill

unsent-context

GeiserX/unsent/skills/unsent-context/SKILL.md

Use when the user asks why they answered something, wants the context of their sent prompts filled, or asks to run the gloss pass; also on a schedule. Fills each Claude Code message in unsent's sent log that replies to the agent with a one-line gloss of what was asked and what was chosen, and marks the replies unsent's own rule missed.

GeiserXCLAUDE.md

lynxprompt-action

GeiserX/lynxprompt-action/CLAUDE.md

The compiled output in dist/ is committed to the repo (required for GitHub Actions). Test locally with act or by referencing a branch in a workflow: Generated by LynxPrompt CLI

GeiserXAGENTS.md

vpn-bypass-mcp

GeiserX/vpn-bypass-mcp/AGENTS.md

MCP server (Go, stdio only, macOS only) for VPN Bypass. Each tool sends one request to the app's control socket and returns the app's result object unchanged. The app owns the contract. Its source of truth is in the VPN-Bypass repo: Sources/VPNBypassCore/CommandRouter.swift (Custom-mode verbs: status, mode, default, route.*, rule.*), ClassicControl.swift (the 4.9.0 domain.*, service.*, routes.*, refresh, dns.refresh and logs verbs; both hold their arguments and error codes), ControlSocketServer.swift (framing: one JSON line each way, 64 KiB per request line, 30…