dotfiles

Token-efficient man page reading. Load when looking up CLI tool docs, flags, options, usage examples, config formats. Do NOT use bash to run `man` directly without loading this skill first.

Load when user asks to create, update, edit, or refactor any OpenCode (OC) artefact: skills, agents, commands, tools, plugins, or snippets — including modifying an existing one. Triggers examples: "create skill to …", "draft a command to …", "add Y to OC cmd Z", "edit the W agent", "write a plugin to …", "create a tool for …", "update crafter skill". Guides user through discovery, drafting, and iterative refinement.

Methodology for drafting technical design specs. Load when asked to write, draft, or refine a spec, design doc, architecture note, RFC, or similar document for a system, API, protocol, or subsystem.

Load ONLY when user explicitly invokes /reflect-friction or directly asks to review session friction (e.g. "review friction", "what went wrong", "where did you push back"). Do NOT auto-load speculatively.

General script writing guidelines: structure, naming, error handling, and organization. Language-agnostic. Auto-load when writing or reviewing any script. Language-specific skills (write-script-bash, write-script-bats) build on top of this.

Load whenever new files or directories are created in a git repo — via write, bash, or any other tool. Ensures `git_track_new_file` is called so new files are git-tracked for the user.

Bash script writing guidelines: shebang, strict mode, bash idioms, and full boilerplate. Auto-load when writing or reviewing bash scripts. Loads write-script-generic for language-agnostic rules.

Rules for drafting a new write-script-<lang> skill. Load when creating or updating any write-script-* language-specific skill.

Post-iteration reflection for script writing sessions. Load after a script has been written or iterated and the user signals it is done.

Bats test file writing guidelines: file structure, test naming, setup conventions, and helpers. Auto-load when writing or reviewing .bats test files.

Nushell script writing guidelines: idioms, types, entry point, error handling. Auto-load when writing or reviewing Nushell (.nu) scripts.

Testing phase instructions for OpenCode artefact review: generate test cases, narrate dry-runs, iterate on failures. Invoked by opencode-reviewer agent. Not for direct use.

Pattern for writing structured files incrementally: skeleton first, then fill each section/function via targeted edits. Improves reviewability and avoids large opaque writes. Load when writing or rewriting any structured file with identifiable sections: spec, design doc, README, config, code module, skill/agent/command artefact, etc. Applies regardless of file length — structure is the trigger, not line count.

Load when the agent hits an environment/runtime hard error: command/module not found/installed, version/runtime mismatch, permission denied, auth/credentials failure, unreachable network/API, or a test suite broken independently of agent changes. (and close variants) Also load when a user-specified resource (path, repo, URL, named config, etc.) does not exist or is inaccessible — do NOT silently substitute or work around it. Do NOT auto attempt manual correction/workaround.

Load when the agent cannot proceed without a human decision or a strategy change. Track consecutive identical failures — load this skill at the third. Also load when the task requires a library that is not yet in the project.

Style reference for writing prose in bew's personal voice. Can be used for any written communication: PR descriptions, issue comments, community posts, emails, chat messages. Load when asked to write new prose or review a draft for style conformance in bew's voice.

Convention for inline callout markers in prose and artefact files. Reference-only — not auto-loaded. Load explicitly when writing or reviewing documents that follow bew's personal notes style.

Compressed code review comments. Cuts noise from feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. When the context is already using caveman mode, and user requests a review, ask user whether this skill should be used.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.