tumf
@tumf
Public Skills
fermi-estimation
by tumf
Solve user questions with defensible Fermi estimates using explicit assumptions, source-backed inputs, uncertainty ranges, and sensitivity analysis. Use when exact data is unavailable or too slow to collect but the user still needs a quantitative answer for counts, market size, demand, costs, revenue, capacity, timing, or operational scale. Autonomously gather accessible evidence, prefer current primary sources, and drive to a conclusion without asking for approval.
jp-grants
by tumf
Collect and answer questions about Japanese subsidies/grants (補助金・助成金) with up-to-date sources. Use when a user asks: which programs they qualify for, eligibility, deadlines, required documents, application steps, or where to find official calls for proposals (e.g. J-Grants, METI/SME Agency, MHLW, prefectures/municipalities). Includes workflows and scripts for web search + structured extraction with citations.
greats-soul-archive-contributor
by tumf
"Contribute new profiles to tumf/greats-soul-archive. Use when user says they want to add/post/submit a new person/character profile, open a PR, scaffold IDENTITY.md/SOUL.md/sources.md, add meta.yml (category/tags), run scripts/build_index.py, or follow the repo contribution rules."
oss-publish
by tumf
Open source publication and release hygiene for repositories and CLIs (language-agnostic): choose and add LICENSE, prepare README/CONTRIBUTING/SECURITY/CODE_OF_CONDUCT, standardize versioning/tags/releases and release notes, set up CI matrices, quality gates (pre-commit/pre-push), and safe-by-default automation/bootstrapping. Use when preparing a project to be published publicly (GitHub/GitLab), cutting a release, or standardizing repo tooling across languages.
rust-cli
by tumf
General guidance for building Rust CLI programs (clap/anyhow/tracing/serde_json), with agent-friendly patterns: JSON output mode, stdout/stderr separation, predictable exit codes, integration testing, and a cargo-release based release workflow.
product-improvement-proposal
by tumf
Propose concrete, high-leverage product/UX improvements to increase a software project's appeal and retention. Use when asked to generate product improvement proposals, UX ideas, onboarding/doc improvements, packaging/pricing positioning suggestions grounded in repo evidence, and prioritized MVP plans (ideation only; no implementation).
openclaw-agent-creator
by tumf
Create and maintain OpenClaw agent workspaces using the "Memory as Documentation" layout. Use when you need to: (1) create a new OpenClaw workspace/profile, (2) generate bootstrap files (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, MEMORY.md, memory/YYYY-MM-DD.md), (3) keep instructions/persona/memory separated and token-lean, or (4) set up a safe git backup of an OpenClaw workspace without committing secrets.
gogcli
by tumf
Fast, script-friendly CLI for Google Workspace and Gmail. Use when you need to automate or interact with Gmail (search/send/manage emails), Google Calendar (create/manage events), Google Drive (upload/download/organize files), Google Sheets/Docs/Slides (read/write/export), Contacts, Tasks, Chat, Classroom, Groups, or Keep. Supports JSON output, multiple accounts, batch operations, and least-privilege authentication. Ideal for email automation, calendar management, file operations, data extraction, workspace administration, and integration with Google services.
clawdbot-config
by tumf
Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing.
firecrawl
by tumf
Comprehensive web scraping, crawling, and data extraction toolkit powered by Firecrawl API. Provides scripts for single-page scraping (scrape.py), web search (search.py), URL discovery (map.py), multi-page crawling (crawl.py), structured data extraction (extract.py), and autonomous data gathering (agent.py). Use when you need to: (1) extract content from web pages, (2) search and scrape the web, (3) discover URLs on websites, (4) crawl multiple pages, (5) extract structured data with JSON schemas, or (6) autonomously gather data from anywhere on the web. Requires FIRECRAWL_API_KEY environment variable.
slack-rs
by tumf
Slack Web API automation via the slack-rs CLI (Rust). Use when you need to authenticate to Slack via OAuth (PKCE), manage multiple workspace profiles, call arbitrary Slack Web API methods (e.g. chat.postMessage, conversations.list, users.info), and run safe scripted Slack operations from the terminal. Includes tunnel-assisted remote login (see auth login --help), encrypted profile export/import, and a write-safety guard via SLACKCLI_ALLOW_WRITE. Credentials are stored in file-based storage under ~/.config/slack-rs/.
agentic-cli-design
by tumf
Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.
opencode-command-creator
by tumf
Create custom OpenCode commands with proper structure and configuration
opencode-agent-creator
by tumf
Create specialized OpenCode agents with proper configuration for primary agents and subagents