kyzooghost
16 verified skills
unit-test
Guidelines for writing and reviewing unit tests. Covers AAA pattern, test naming, determinism, mocking strategies, and reviewer responsibilities. Use when creating or updating *.test.* files, reviewing test PRs, or refactoring tests to improve clarity and coverage.
development
sync-command
Sync a command from this repo into local agent surfaces. Use when the user asks to make a repo command available locally, sync a local command for Claude, Agents, or Codex, update command symlinks, or expose a command to Codex as a skill.
development
developing-smart-contracts
Solidity smart contract development guidelines. Covers NatSpec documentation, naming conventions, file layout, and code style. Use when writing, reviewing, or refactoring Solidity contracts, or when the user asks about Solidity best practices, contract structure, or NatSpec.
development
audit-code-health
Scans codebases for security vulnerabilities, bugs, and code health issues. Creates structured work items for remediation. Triggers on "audit", "code review", "security scan", "find bugs", "tech debt", or "assess code quality".
development
create-pr
Use when the user asks to create, update, draft, or generate a GitHub pull request, including /create-pr behavior or equivalent workflow.
tools
grill-plan
Use when the user asks to grill, interrogate, pressure-test, or relentlessly interview them about a plan until requirements, tradeoffs, dependencies, and implementation decisions are clear.
testing
sync-skill
Sync a skill from this repo into the local machine's skill directories. Use when the user asks to make a repo skill available locally, sync a local skill for Claude, Agents, or Codex, update local skill symlinks, or follow the .claude/skills source link pattern with .agents/skills and .codex/skills symlinks.
development
perf-review
Use when drafting a periodic performance review (annual review, mid-year, promo packet, peer feedback) from monthly win reports and supporting sources, where the goal is prose-form answers grounded in verifiable evidence.
development
llm-wiki
Build and maintain a personal knowledge wiki using LLMs. Bootstraps a portable markdown wiki for a subject area, ingests sources into it, answers queries against it, and health-checks it. Triggers on "/wiki-init", "/wiki-ingest", "/wiki-query", "/wiki-lint", or natural-language phrases like "set up a wiki for X", "ingest this source into my wiki", "query my wiki", "health-check my wiki", "lint my wiki". Use when the user wants a persistent, compounding knowledge base that the LLM maintains over time, rather than one-shot RAG against raw sources.
development
discover-repo
Generate a comprehensive AGENTS.md index for a repository with a CLAUDE.md symlink. Dispatches parallel subagents to study directory structure, core code, docs, tests, and config, then synthesizes findings into a structured guide for future Claude sessions. Triggers on "/discover-repo", "discover this repo", "generate a CLAUDE.md", "index this codebase", or "study this repo". Use when onboarding to a new codebase or creating documentation for AI-assisted development.
development
win-report
Discover and synthesize engineering wins from GitHub PRs/issues, Confluence, Jira, Notion, and Slack over a configurable time range. Uses exhaustive two-phase subagent architecture to paginate all sources and read all artifacts in full before synthesizing. Produces a structured markdown report of top wins with evidence, impact, and ownership. Use when the user says "/win-report", "summarize my wins", "what did I ship last month", "monthly wins report", "generate wins for performance review", or asks for a summary of their recent engineering contributions.
data-ai
install-local-skill
Install or refresh a skill from this repo into the local machine's skill directories. Use when the user asks to make a repo skill available locally, install a local skill for Claude, Agents, or Codex, update local skill symlinks, or follow the .claude/skills source link pattern with .agents/skills and .codex/skills symlinks.
development
usage-insights
Generate a usage insights report analyzing coding assistant session history. Parses session JSONL logs, extracts metadata (tools used, languages, git activity, friction points), and produces a structured markdown analysis with actionable suggestions. Works with any assistant that stores sessions as JSONL. Use when the user says "/usage-insights", "analyze my sessions", "usage report", "how am I using this", "session insights", or asks to review their coding assistant usage patterns.
tools
handover
Prepare a structured handover document from the current session for a fresh Claude session to continue the work. Use when the user says "/handover", "prepare a handover", "write a handover", "session summary for next time", or when wrapping up a complex debugging/implementation session that will be continued later. Captures problem context, locked decisions, dead ends, running state, key files/commands, artifacts, open questions, and next steps so zero context is lost between sessions.
development
peer-review
Generate evidence-backed draft peer review answers for annual performance reviews. Sources from GitHub PRs/issues, Confluence, Jira, Notion, and Slack over the last year, plus user-pasted DM snippets from any messaging platform. Uses exhaustive two-phase subagent architecture to discover all artifacts, read them in full, then synthesize into human-sounding answers mapped 1:1 to the review form questions. Use when the user says "/peer-review", "write a peer review", "help me with performance review feedback", "peer feedback for [name]", or asks to write review answers for a colleague.
documentation
perf-review
Use when drafting a periodic performance review (annual review, mid-year, promo packet, peer feedback) from monthly win reports and supporting sources, where the goal is prose-form answers grounded in verifiable evidence.
development