个人作者
Randy Wilson
Full-stack engineer building AI agents, RAG pipelines, and knowledge graphs. TypeScript · Node.js · Vercel AI SDK · 8+ years shipping production systems.
- Skills
- 22
- 仓库
- 1
- 职业覆盖
- 3
- 场景覆盖
- 6
- Stars
- ★ 1
Randy Wilson 的 Skills 22
research
Conduct research.
{{NAME=null}=null}
Briefly describe what this skill does AND when to use it. Use imperative phrasing ("Use this skill when..."). Aim for 80-500 chars. Include keywords the model can pattern-match against the user's prompt.
working-in-a-git-repo
Operating manual for dev work: worktree discipline, build/test/lint commands, file ownership zones, commit style, and a verification checklist before reporting done. Use when starting any feature/fix work in this repo.
test-runner
Runs the project's test suite (or a targeted subset), parses the output, and reports pass/fail with failing-test details. Use when you need to know test status; call with the test command to run, or leave blank for the project default.
reviewer
Reviews a diff or change set for bugs, security issues, test gaps, and style. Use when evaluating a code change, reviewing a pull request, or running a structured review pass before merge.
fix-failing-tests
Seven-step flow for diagnosing and fixing failing tests. Use when the user asks to fix failing tests, green the suite, or says 'tests are red' — works through reproduce → read → root-cause → propose → apply → verify → commit.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
summarizer
Stateless summarizer agent — condenses long text into structured summaries.
ship-feature
Ship a feature end-to-end: understand the ask, research the codebase, plan, build test-first with small commits, verify via scripts, and deliver. Use this skill when starting any non-trivial feature, bug fix, or refactor that needs the full understand → plan → build → verify → deliver cycle.
research
Deep research — clarify question, find primary sources, verify, deliver recommendation. Use when the answer requires checking documentation, papers, or official repos rather than guessing from memory.
planner
Decomposes an ambiguous task into a bounded, ordered plan. Use when the request is open-ended, multi-step, or involves several files/subsystems.
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
example-web-search
Example HTTP tool definition for a fictional web search API. Copy and adapt for real services.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
delegate-to-cli
Delegates bounded subtasks (text-in/text-out, large-token, no harness MCPs needed) to a local CLI agent (claude/codex/gemini) via scripts/delegate.sh. Use when the task is large enough to warrant a subprocess but doesn't need the harness's own primitives. Returns the subagent's final text plus structured error info.
daily-reflection
Scheduled end-of-day synthesis. Runs at 18:00 daily — reads the day's sessions, writes a structured journal entry to memory/journal/, and proposes rule candidates from patterns across recent journals. Use when the harness schedule fires or when the user asks to summarize today's activity.
content-marketer
Elite content marketing strategist specializing in AI-powered content creation, omnichannel distribution, SEO optimization, and data-driven performance marketing. Masters modern content tools, social media automation, and conversion optimization with 2024/2025 best practices. Use PROACTIVELY for comprehensive content marketing.
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.