shortcuts
User📁 tmux, ghostty, fish, nvim, claude code, aerospace
Categories
Indexed Skills (32)
branch-auditor-pgpemu
Audit a feature branch against origin/main to highlight changes, verify test coverage, and detect potential bugs. Use this skill whenever you need to: - Understand what changed in a branch compared to main - Verify all changes have corresponding unit tests - Detect potential bugs or regressions - Assess merge risk and readiness - Review code quality, formatting, and architecture - Get actionable recommendations for test coverage gaps This is pgpemu-specific: It understands the ESP32-C3 firmware architecture, the comprehensive test suite (252 assertions across 8 test modules), and code review standards from AGENTS.md. The auditor scans the entire codebase—no specificity needed, the unit tests handle verification.
explain
Explain any topic as one terse note in the user's Obsidian vault - from zero knowledge to the subject itself.
self-review
Summarize what the user shipped on GitHub over a time range, as one Obsidian note with one subsection per system. Use whenever the user asks what they accomplished or shipped over a period - "what did I do since last november", "self review", "write my perf review", "recap my last quarter" - including when they never say "self review" or name a repository.
documentation
Creates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose between Diátaxis documentation types, or improve existing documentation structure. Trigger terms include: documentation structure, Diátaxis, tutorials vs how-to guides, organize docs, user guide, reference docs, technical writing.
radin-plan
Write a step-by-step implementation plan for one backlog entry, without touching code. Scope is one task (a title/keyword), not the whole backlog. Use for /radin-plan, "plan this backlog entry", "write a plan for X before we execute it". radin-execute delegates here for any entry too complex to implement directly.
radin-review
Review a scope (commit, PR, directory, or a range like "since yesterday") on two axes — Standards (does the code follow this repo's rubrics?) and Spec (does it do what the originating backlog entry asked for?) — triage the findings with the user, and log the ones they keep as backlog entries. Use for /radin-review, "review and log to backlog", "audit this commit/PR/directory and file backlog entries".
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record or any request to save something from this session for later (a bug, follow-up, idea, or finding). Triggers even on vague asks ("add the findings"): scan the whole session, not just the literal text.
radin-setup-hooks
Wire codebase-memory-mcp into this repo when install.sh could not do it globally. Use for "set up hooks", "wire up codebase-memory-mcp", "enable the knowledge graph here", or when the graph's MCP tools are missing in a project.
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.
radin-stats
Show stats/gain output from every companion tool that ships one, side by side. Use for /radin-stats, "show me all my stats", "aggregate my tool gains", "what savings am I getting from these tools".
new-rules-of-context-engineering-claude-5
Audit and rewrite agentic context files (CLAUDE.md, AGENTS.md, SKILL.md files, agent instruction docs) to follow Anthropic's Claude 5 context engineering rules — replace rigid rules with judgment-enabling guidance, remove redundant constraints, deduplicate across files, and apply progressive disclosure. Use whenever the user wants to modernize, audit, slim down, "unhobble", or right-size CLAUDE.md files, skills, system prompts, or a docs/ directory of agent instructions — even if they just say "clean up my agent files", "my CLAUDE.md is bloated", or "apply the new context engineering rules".
non-technical-reporting-summary
Summarize a PR or branch into a concise, non-technical notebook entry with "What we did" and "Expected outcome" sections. Aimed at engineering managers and executives. Use when the user wants a PR summary, branch summary, notebook entry, exec summary, or non-technical report.
openscad
Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and export STL files for 3D printing platforms like MakerWorld.
radin-update
Refresh radin's agents/skills in ~/.claude/ by re-running install.sh (latest release or main), overwriting what's there. Use for "update radin", "pull the latest radin", "reinstall radin", /radin-update.
release-candidate
Audit the main branch to determine if the repository is ready for a new release. Runs build/lint/test checks, audits documentation consistency against changes since the last release, and logs every failure via radin-record to radin's BACKLOG.md. Returns a clear go/no-go verdict. Use this skill whenever the user wants to: - Check if the codebase is release-ready - Run a pre-release audit or checklist - Validate that docs are in sync with code changes - Get a release go/no-go verdict before tagging - Run "release checks", "pre-release audit", "is this ready to ship?"
release-notes
Generate user-facing release notes from tickets, PRDs, git logs, or internal changelogs. Use when writing release notes, creating a changelog, announcing a product update, or summarizing what shipped.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
no-ai-slop
Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.
radin-plan
Write a step-by-step implementation plan for one backlog entry, without touching code. Scope is one task (a title/keyword), not the whole backlog. Use for /radin-plan, "plan this backlog entry", "write a plan for X before we execute it". radin-execute delegates here for any entry too complex to implement directly.
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks ("add the findings"): scan the whole session, not just the literal text.
radin-review
Review a scope (commit, PR, directory, or a range like "since yesterday") on two axes — Standards (does the code follow this repo's rubrics?) and Spec (does it do what the originating backlog entry asked for?) — triage the findings with the user, and log the ones they keep as backlog entries. Use for /radin-review, "review and log to backlog", "audit this commit/PR/directory and file backlog entries".
radin-setup-hooks
Wire codebase-memory-mcp into this repo when install.sh could not do it globally. Use for "set up hooks", "wire up codebase-memory-mcp", "enable the knowledge graph here", or when the graph's MCP tools are missing in a project.
radin-implement
Work through a project's whole backlog with no planning pass: prioritize every task, implement each straight from its entry via a sub-agent, commit after each. Use when the user wants the backlog implemented directly ("skip planning", "just implement the backlog"). A task that already has a /radin-plan plan still follows it.
radin-doctor
Check that radin's own install under ~/.claude is complete and its companion tools are reachable. Use for /radin-doctor or any request to verify or diagnose the radin install.
radin-uninstall
Remove everything install.sh copied into ~/.claude -- radin's skills and lib scripts. Use for /radin-uninstall or any request to remove radin from this machine.
radin-show
Print the current project's backlog to the terminal. Use for /radin-show, "show me the backlog", "what's in the backlog".
radin-stats
Show stats/gain output from every companion tool that ships one, side by side. Use for /radin-stats, "show me all my stats", "aggregate my tool gains", "what savings am I getting from these tools".
radin-doctor
Check that radin's own install under ~/.claude is complete and its companion tools are reachable. Use for /radin-doctor, "check my radin install", "is radin installed correctly", "radin doctor", "verify radin install".
radin-show
Print the current project's backlog to the terminal. Use for /radin-show, "show me the backlog", "what's in the backlog".
radin-uninstall
Remove everything install.sh copied into ~/.claude -- radin's skills and lib scripts. Use for /radin-uninstall, "uninstall radin", "remove radin", "tear down radin", "get rid of radin".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.