Claude Skills by majiayu000

Estimate the ROI, payback, and NPV of an investment, project, or purchase. Use when asked to calculate ROI, build a business case, justify a purchase/initiative, work out payback period, or compare options by return. Produces a computed ROI summary (net benefit, ROI %, payback, simple NPV) with the assumptions made explicit and a sensitivity note, so a business case is defensible.

Troubleshooting: REP 103/105 ground-truth checks, TF/IMU/LiDAR misalignment, use_sim_time, lifecycle states, executor deadlocks, DDS domain conflicts.

Repo Prompt CLI - proxy MCP client for AI agents to access Repo Prompt's context engineering tools via bash. Build prompts, search code, manage file selections, chat with AI, and export context without MCP configuration.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.

Generate AI images, videos, and music/audio from agents using the RunAPI CLI.

Translate Unix commands to Windows equivalents when working on Windows systems. Use when paths start with drive letters (B:\, C:\), commands fail with "not recognized" errors, or when needing to avoid Unix-specific tools like tail, head, grep, or mkdir -p. Maps common Unix commands to PowerShell and CMD alternatives.

Run rust crate release readiness.

Run rust port validation gauntlet.

Run rust search integration.

Run rust sqlite CLI architecture.

Run rust unsafe boundary audit.

Compute the core SaaS metrics — MRR/ARR, growth, NRR/GRR, churn, quick ratio, magic number — from your numbers. Use when asked to calculate SaaS metrics, MRR/ARR, net revenue retention, the quick ratio, or to build a SaaS metrics snapshot for a board/investor update. Produces a computed metrics dashboard with each value, its benchmark, and a one-line read on what it means.

Run sbh.

Executes shell scripts in a safe environment.

Stream editor for text substitution, line operations, and file transformations.

Send and receive iMessage, SMS, and RCS from application code via the Sendblue HTTP API — text, media, group messages, send styles, reactions, typing indicators, status callbacks, and inbound webhooks.

Send iMessage and SMS from the shell via the @sendblue/cli npm package — outbound sends, contact management, and account setup with no API client or webhook server required.

Use when the user wants to wire a Power Apps Wrap mobile app to an Entra ID app registration by opening the Power Apps Wrap app-registration page, pasting the resulting client ID, and updating auth.config.json.

Use when the user wants to enable offline mode for a Power Apps mobile app and create a Mobile Offline Profile in Dataverse — designs per-table row scope, relationships, columns, and sync frequency through a 3-gate approval flow.

Set up Power Automate CLI prerequisites. Use when the user is new, something isn't working, or they need help getting started.

Create or update shareable, commentable p11 documents. Use when Claude Code should author a polished proposal, brief, report, spec, plan, memo, or review draft and publish it with p11.

Shell runtime rules for mvdan/sh virtual shell in internal/runtime/virtual.go. Covers positional arguments gotcha (prepend "--"), bash strict mode (set -euo pipefail), arithmetic increment pitfalls.

POSIX shell scripting standards for Mark's workflow.

Safely start, supervise, and terminate shell processes: background jobs, PID capture, signals, traps, cleanup verification.

Modern shell prompt configuration with Powerlevel10k and Zsh Vi Mode. Use when configuring shell prompts, setting up vi/vim keybindings in zsh, customizing cursor styles per mode, adding mode indicators, optimizing prompt performance, or troubleshooting slow prompts. Covers P10k instant prompt, vi mode plugins, and cursor customization.

Audit shell scripts for correctness and common pitfalls. Use when reviewing bash/sh scripts before merging.

Audit shell scripts for correctness, portability, and common pitfalls. Triggers: shell script, bash, sh, script review, pipeline, exit code Use when: reviewing shell scripts, CI scripts, hook scripts, wrapper scripts DO NOT use when: creating new scripts - use attune:workflow-setup

This skill should be used when the user asks to "create a bash script", "write a shell script", or mentions shell scripting conventions.

Skill for reviewing shell scripts with shell-neutral behavior with best efforts.

シェルスクリプトの作成・レビュー・改善を行うスキル。POSIX準拠とShellCheck対応

Practical bash scripting guidance emphasising defensive programming, ShellCheck compliance, and simplicity. Use when writing shell scripts that need to be reliable and maintainable.

Use when writing or reviewing Bash scripts and shell snippets, especially for shebang selection, quoting, parameter expansion ("${VAR}" style), test expressions ([ ] vs [[ ]]), ShellCheck-guided fixes, and portability decisions across POSIX sh, Bash, and zsh compatibility targets.

Shell script development workflow. Use when modifying files in scripts/ directory or any *.sh files.

Scaffold a new Claude Code skill following this repo's conventions — copy a canonical template, apply the PATTERNS.md checklist, verify with lint. Use when the user runs /skill-maker, asks to create or package a new skill, or wants to turn a procedure into a slash command.

This skill should be used when the user has a vague or cross-domain request and asks "which skill should I use", "is there a skill for this", "find the right skill", or "route this to the best skill" — it matches an intent against the whole skills library and recommends the best-fit skill(s).

扫描本机 Claude Code 和 Codex 的会话日志，统计哪些 skill 有本地调用证据、哪些在本机无证据（已安装但日志无痕迹，不等于从未使用）、调用排行、月度趋势、项目分布，输出终端表格和 Markdown 报告，可导出 CSV/JSON。Use when the user asks to 统计 skill 使用, 看 skill usage, find zombie skills, 僵尸 skill, which skills are installed but never used, skill 调用排行, skill usage report, skill 使用健康度, audit personal skill arsenal, or manage which skills to keep or remove.

Create and manage argc-powered bash CLIs and Argcfile.sh task runners. Use when creating Argcfile.sh files, converting bash scripts to argc CLIs, adding argument parsing, shell completion, or task automation to projects.

Trigger when you would normally reach for pytest, gh, mypy, black, or other raw repo tooling. Redirect to `sm swab`, `sm scour`, `sm buff`, `sm sail`, `sm refit`, or `sm doctor` so remediation follows the established rails. Also trigger when filing issues about slop-mop friction — use `sm barnacle file` / `/slopmop:sm-barnacle`, never `gh issue create`.

Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning

Route coding work so GPT-5.6 Sol remains the commander and reviewer while a separate GPT-5.6 Luna Max Codex CLI session performs concrete implementation. Use when the user asks for Sol to direct, plan, supervise, or review work done by Luna Max; when native Sol-to-Luna subagent spawning is unavailable or incompatible; or when a task needs an auditable plan, bounded worker ownership, verification, and review loop.

Spawn full Claude Code peer sessions in their own terminal panes and git worktrees — real sessions, not subagents — each on a directed task with a contract brief, monitored and merged back by the spawning lead. Detects the environment and takes the strongest path — herdr first, then tmux, then a native claude background agent. Use when work must outlive or run beside the current session, needs its own worktree or its own permission settings, should stay steerable by the user in a visible pane...

Spawn full peer agent sessions in their own terminal panes and git worktrees — real sessions, not subagents — each on a directed task with a contract brief, monitored and merged back by the spawning lead. Herdr drives it; from a Codex lead the herdr socket needs an unsandboxed session, or the user runs the printed commands. Use when work must outlive or run beside the current session, needs its own worktree, or should stay steerable by the user in a visible pane. Spawns Codex or Claude Code p...

Run spec reliability implementation.

Run SSH.

Stage implementation changes for commit with precise file selection. Use when the user asks to \"stage changes\", \"stage files\", \"add files to staging\", or \"prepare changes for commit\".