printing-press-library
Use when looking for a CLI, API wrapper, scraper, data-source tool, automation tool, or focused agent skill for a task; searches the Printing Press Library and installs matching tools.
What this skill does
# Printing Press Library Use this skill when a user asks for a CLI, agent skill, API wrapper, scraper, automation tool, or data source that may exist in the Printing Press Library. The library is an open-source catalog of focused CLIs and matching agent skills generated from `mvanhorn/cli-printing-press`. This skill is the catalog front door. Do not install a random long-tail skill just because it exists. First identify the right tool, then install the focused skill or CLI only when it is useful for the task. ## Default workflow 1. Clarify the user goal only if needed. - If the request names a service or website, search for that directly. - If the request describes a job instead of a service, search by capability and domain. - If the user's agent already has a safe built-in tool that solves the job, prefer that over installing another CLI. 2. Search the catalog with the library CLI first. - Use `npx -y @mvanhorn/printing-press-library search <keyword>` for human-readable result cards. - Use `npx -y @mvanhorn/printing-press-library search <keyword> --json` for agent-friendly parsing. - Use `npx -y @mvanhorn/printing-press-library list --category <category> --json` when the category is known. - Each search result includes the canonical install command for that tool. - Fall back to the GitHub repo or local clone only when `npx` is unavailable or deeper inspection is needed. 3. Select deliberately. - Prefer the candidate whose README/SKILL examples match the user's actual job, not merely the same website name. - Check whether auth, cookies, paid APIs, OS-specific binaries, or browser automation are required before installing. - Install the narrowest useful tool. Do not install a family of adjacent tools just because the search returned them. 4. Install through the library installer when the selected tool is useful. - The default primitive is `npx -y @mvanhorn/printing-press-library install <slug>`. - In OpenClaw, use `npx -y @mvanhorn/printing-press-library install <slug> --agent openclaw` so the focused skill is materialized under OpenClaw's managed skills root; the installer defaults the Go binary into a per-user bin directory. - The install command installs both the CLI and the matching focused agent skill. - `install <slug>` is idempotent: re-running it on an already-installed tool refreshes the Go binary and overwrites/re-adds the focused skill in place. - Behind the scenes, the installer uses `go install <module>@latest` for the CLI and the Vercel Agent Skills-compatible `skills` CLI to install the focused `pp-*` skill globally from this repo. - If the Go binary installs successfully but is not on the current process `PATH`, treat that as a warning, not a failed skill install. The installer should still install the focused skill and print platform-specific PATH instructions. - In agent/gateway environments, shell startup files may not affect the already-running process. Restart the session/gateway after PATH changes, and verify the default user bin directory is visible to the harness. - For OpenClaw gateway/service deployments, verify the gateway process PATH can resolve `<slug>-pp-cli`; an interactive shell `which` is not enough. - Pass `--cli-only` or `--skill-only` only when the user explicitly wants just one side. 5. Make the newly installed skill visible to the running agent. - Most agent harnesses snapshot available skills at session start. After installing or refreshing a focused skill, start a fresh session or reload skills before trying to invoke it. - In Hermes CLI sessions, use `/reload-skills` when available, or exit and start a new `hermes` session. - In Hermes gateway sessions, use `/restart` from the gateway chat or `hermes gateway restart` from a shell so the gateway process reloads installed skills. - In OpenClaw, assume the current agent session may not see newly installed skills until the OpenClaw session or gateway is restarted. 6. Verify before claiming success. - If installing a CLI, run its `--help` or an equivalent harmless command. - If installing a skill, verify the destination harness can see it after the session reload/restart when the harness has a verification command. - If using a credentialed CLI, confirm required environment variables without printing secrets. 7. Offer an efficient periodic update schedule after successful install or refresh. - Because install/update is idempotent, it is safe to keep installed Printing Press CLIs and focused skills current with a scheduled job. - Do not create a cron/scheduled job without explicit user approval; recurring jobs are durable side effects. - Avoid one scheduled job per CLI as the default. Users may install many Printing Press tools, and per-tool jobs become noisy and hard to manage. - Prefer one consolidated recurring job that runs `npx -y @mvanhorn/printing-press-library update`, which refreshes every installed Printing Press CLI currently on PATH and its matching focused skill. - Offer a per-tool job using `npx -y @mvanhorn/printing-press-library update <slug>` only when the user explicitly wants a different cadence or policy for that one tool. - Prefer quiet, low-frequency schedules such as weekly unless the user asks for something else. ## What this skill is for Use this skill to discover CLIs and agent skills in the public Printing Press Library. Match the user's goal to the right library entry, use the library CLI to find the canonical install command, and install the selected tool only when it is useful for the task. Good fits: - finding a purpose-built CLI for a named service - finding a scraper or data-source tool for a one-off research or automation task - installing a focused `pp-*` skill so future agents know how to use a specific CLI - refreshing already-installed Printing Press CLIs and skills Poor fits: - replacing a safe built-in agent tool that already solves the task - installing broad tool bundles speculatively - credentialed account actions where the user has not approved external side effects - publishing, posting, booking, buying, emailing, or mutating third-party state without explicit approval ## Install primitive The Printing Press Library CLI is the canonical interface for installing catalog tools: ```bash npx -y @mvanhorn/printing-press-library install <slug> ``` For OpenClaw, pass the OpenClaw agent target explicitly. The installer puts the binary in the default per-user bin directory (`$HOME/.local/bin` on macOS/Linux, `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows): ```bash npx -y @mvanhorn/printing-press-library install <slug> --agent openclaw ``` That command installs both halves of a catalog entry: - the Go CLI binary - the matching focused `pp-*` agent skill For the skill half, the installer shells out through the Vercel Agent Skills-compatible installer. Conceptually, it runs: ```bash npx -y skills@latest add mvanhorn/printing-press-library/cli-skills/pp-<slug> -g -y ``` So the catalog installer is still the right top-level command: it installs the CLI, then installs the focused skill globally using the same agent-skills mechanism rather than asking the agent to hand-roll a separate skill install path. The install operation is idempotent and works as a reinstall for one tool. Re-running `install <slug>` uses `go install <module>@latest` for the binary and re-adds the focused skill non-interactively, overwriting the existing install in place. No uninstall-first step is needed. If install warns that the binary directory is not on `PATH`, the binary and focused skill can still be installed successfully. Follow the printed platform-specific PATH instructions, then restart the running agent session or gateway if it inherits a fixed environment. Use `--bin-dir <dir>` only when the default user bin directory is wrong for that machine. Use `update` when the user asks to refresh or reinstall existing tools:
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.