Cloudflared Tunnel
openbooklet.com/s/cloudflared-tunnelopenbooklet.com/s/cloudflared-tunnel@1.0.0GET /api/v1/skills/cloudflared-tunnelCreate a named Cloudflare tunnel, write multi-ingress config, route DNS, and optionally start it. Supports multiple hostname:port pairs for routing several services through one tunnel.
Rank open issues by PM criteria, update pinned backlog tracking issue. Queries all open GitHub issues, scores them on strategic value, community signal, feasibility, dependencies, age, and staleness, then maintains a curated "Top 10 Feature Backlog" as a pinned GitHub issue. TRIGGER when: heartbeat (daily 08:00 UTC), or when asked to rank the backlog, prioritize issues, or run backlog ranking.
Monitor the GitHub Actions CI pipeline for the current branch. A feature is not done until CI passes.
Validate content quality before publishing. Checks frontmatter, conciseness, structure, links, code blocks, length, and visual rendering via agent-browser. TRIGGER when: before committing docs/content/** or workspace/wiki/pages/**, after /wiki-ingest, "check content quality", "content gate".
Tear down the next-postgres-shadcn sandbox: stop containers, remove volumes, and optionally prune the Docker image. Reads .openharness/config.json for compose overlays so all services are cleaned up. TRIGGER when: asked to tear down, destroy, clean up, stop, or remove the sandbox.
Score workspace files for conciseness using filler-word density. Measures prohibited-pattern density (articles, filler, hedging) in compressed files. Reports PASS/FAIL per file. TRIGGER when: after /compress, "score conciseness", "eval files", "check compression quality", or periodically via heartbeat.
Provision or rebuild the next-postgres-shadcn sandbox. Reads .openharness/config.json for compose overlays, builds the image, starts all services, waits for startup, and runs test:setup to validate. TRIGGER when: provisioning, rebuilding, or when asked to set up the sandbox.
Repair the sandbox stack: detect environment (container vs host), run test:setup, auto-remediate failures, and re-verify. Works both inside the container (direct) and from the host (via docker exec). TRIGGER when: after container restart, after rebuild, when something seems broken, when asked to check setup, repair, diagnose issues, or verify the stack.
Score all skills for staleness using 5 dimensions (freshness, usage, integrity, format, dependencies). Reports CURRENT/STALE/BROKEN/DELETE verdicts with specific recommendations. TRIGGER when: asked to audit skills, check skill health, "are my skills stale", "skill lint", or periodically via heartbeat.
Spawn 5 domain experts to propose roadmap items, then an AI council drafts a roadmap, a Strategic Critic challenges it, and the council finalizes with revisions. Updates the pinned roadmap issue and /roadmap page data. TRIGGER when: asked to build roadmap, prioritize features, strategic proposal, "what should we build next", or rank product priorities.
Template for building a strategy review skill that measures decision quality over time. CUSTOMIZE this template for your agent's domain. Tracks whether the agent's approach is improving by comparing predictions against actual outcomes. TRIGGER when: periodic review (weekly/monthly), when user asks about performance trends, or when evaluating whether to change approach.
Auto-indexed from ryaneggz/open-harness
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.