shenwell
UserAgent skills for Cursor & Claude Code: goal-mode keeps agents working until tests/lint/CI are green (open /goal). npx skills add shenwell/ai-agent-skills
Categories
Indexed Skills (17)
goal-mode
Keep coding agents working until tests, lint, typecheck, or CI are green — instead of stopping after one try or claiming "done" without proof. Autonomous coding-agent loop with a verifiable finish line: GOAL.md contract, phased plan, worker/verifier proof loop, time budget, auto-resume (Cursor Cloud Agent). Open alternative to Claude Code /goal. Use when the user says /goal, "goal mode", "goal mode for Cursor", "keep going until tests pass", "don't stop until green", "coding agent until tests pass", "verify until done", "agent stops after one attempt", "how to make agent not stop until complete", "fix CI", "fix all lint errors", "green build", "unattended refactor", "overnight agent", "resume the goal", or wants multi-hour autonomous execution with verification before completion. Prefer over one-shot chat or Cursor Agent Mode for long refactors, migrations, and CI repair until green. Do not use for one-shot Q&A or vague "make it better" without a measurable finish line.
memo-session-skill
Persistent AI agent memory for coding sessions — cross-session knowledge that survives context window resets. Consolidates session noise into durable facts and routes them via memory routing into MEMORY.md, memory/ HOT/WARM/COLD layers, project wiki, AGENTS.md, skills, and optional portfolio memory — git-tracked, with conflict gate and temperature limits. Stateful handoff when volatile chat context is lost; complements vector RAG or managed memory platforms, does not replace them. Use when the user says "wrap up the session", "save what we learned", "handoff", "open loops", "update memory", "agent memory", "persistent memory", "cross-session persistence", "how to give my agent memory", or when another skill requests a memory checkpoint. Also for portfolio/global memory, bootstrap project memory, session changelog, `/inbox`, process inbox, or ingest files from memory/inbox. When memo-session-mcp is connected, use search_all for portfolio/project lookup and reindex_changed after writes. Prefer after non-trivial
analyst
Software factory planning station. Turn a classified work item into a plan with acceptance criteria, grounded in the real repository. May propose decomposition into child factory jobs. Use when the factory pipeline delegates analysis. Do not write the implementation.
designer
Software factory design station. Produce a visual contract (tokens, signature, UX states, a11y floor) before UI implementation. Use when the factory pipeline delegates design. Do not write production UI code.
factory-pipeline
Run the software factory pipeline on a development task. Use when the user says /factory, asks to factory a bug or feature, wants classify-plan-implement-review, hands in a GitHub issue (#N, issue URL, sync, next), or sends a plain-chat work item while chat.autoStart is enabled. Handles multi-phase intake and analyst-driven decomposition into child jobs. Not for one-line edits the user asked you to type yourself.
factory-setup
First-time workspace and GitHub configuration for the software factory. Use when the user says /factory-setup, asks to set up the factory, configure GitHub, create a repo, fix clone layout, or prepare a fresh install before /factory runs.
factory-upgrade
Upgrade the software factory kit in a consumer workspace from the upstream kit repo. Use when the user says /factory-upgrade, asks to update the factory, pull the latest pipeline, or refresh kit skills and commands.
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
github-intake
Pull GitHub issues into the factory queue, create-if-missing issues from chat intake, comment progress on the originating issue, and rebuild the local station board. Use when /factory has no task, the user says sync or board, the task is an issue number or URL, chat free text needs ensure-issue, or a station completes on a GitHub-sourced job.
implementer
Software factory implementation station. Execute an analysis plan in the real repository, verify with the repo's own checks, commit, and push a feature branch when policy allows. Use when the factory pipeline delegates implementation. Do not review your own work.
reviewer
Software factory review station. Independent verdict on a pushed or local feature branch against the analysis acceptance criteria. Use when the factory pipeline delegates review. Never write or fix code. Never trust the implementer's summary without reading the diff.
triaging-issues
Grounding a GitHub work item before running the factory pipeline: checking for duplicates, working with the repo's existing labels, deciding whether to ask for clarification or proceed, and asking for reproduction details well. Load when a work item arrives from a GitHub issue, or when asked to triage, label, dedupe, or close issues. Not needed for plain chat tasks with no issue behind them.
ui-ux-pro-max
UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local data: 79 searchable styles (50 active), 192 product palettes and reasoning profiles, 74 font pairings, 119 UX guidelines, 105 icons, 17 GSAP presets, 25 chart types, and 22 stacks.
software-factory
Cursor-native software factory: classifier, analyst, implementer, and reviewer stations move work from chat or GitHub issues to a feature branch and PR. Use when the user says /factory, wants a multi-agent pipeline with independent review, GitHub issue intake, or a station board for factory jobs. Not a single-skill drop-in — copy this folder to the workspace root (see README.md) or open it as the Cursor workspace folder.
classifier
Software factory triage station. Classify a work item by type, priority, complexity, UI surface, and whether it is actionable. Use when the factory pipeline delegates classification, not for implementing or reviewing code.
researcher
Software factory research station. Look up facts the repository does not hold (upstream bugs, library versions, primary sources) and return cited findings. Use when the factory pipeline delegates research. Do not plan or implement.
writing-quality
Writing-quality guardrails for any prose the agent drafts or edits: pull request descriptions, issue comments, review reports. Use whenever writing or revising content meant for humans. Not needed for code, queries, or tool plumbing.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.