Results for “try-on”

Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".

Build throwaway code that answers exactly one design question — a tiny terminal app to feel out logic/state models, or several radically different UI variants switchable on one route. Use when the user wants to "prototype", "mock up", "sketch", "try a few versions", "see what it'd look like", "feel out this state machine", or is stuck choosing between designs they can only judge by seeing or driving them. Also used by the whiteboard skill for napkin-type tickets.

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Throwaway experiments to validate an idea before build.

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Runs throwaway experiments to validate feasibility, compare approaches, and surface unknowns before committing to a real build.

Run multiple AI agents against a product, SDK, or docs site to score setup friction, speed, efficiency, error recovery, and doc quality from a minimal prompt.

Throwaway experiments to validate an idea before build.

Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.

Runs commands, inspects git state, debugs CI failures, and makes narrow fixes with exact proof of what was executed and verified.

Throwaway experiments to validate an idea before build.

Design low-effort experiments to test product assumptions for an existing product, including prototypes, A/B tests, spikes, and other validation methods.

Runs throwaway experiments to validate feasibility before building, producing a verdict with evidence.

Internal harness probe for the OI-3 readability-guidance spike. Use only when explicitly told to invoke spike-probe. Verifies that a freshly-created project skill renders into a subagent's context via the Skill tool.

Builds a throwaway prototype to answer a design question, choosing between a runnable terminal app for logic/state questions or multiple UI variations switchable from one route.

Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified.

Write effective unit tests with best practices for any project. Use when writing tests, creating test cases, improving test coverage, increasing confidence before release, or when the user mentions testing. Mutation score / assertion theater → test-mutation.

Test-Driven Development (TDD)

Organizes email triage, drafting, replying, and sending with verification that messages landed in the Sent folder.

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Verify that a change really works before you claim completion

Executes terminal commands, inspects git state, debugs CI or builds, and makes narrow fixes with exact proof of what was executed and verified.

Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.

Use when implementing any feature or bugfix, before writing implementation code.

Rereads code, specs, plans, reviews, or skill edits with fresh eyes to catch blunders, oversights, and omissions before closure, reporting concrete evidence-backed findings.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

当用户想测试或复盘某个 skill 的实际执行效果时使用——如“测一下这个 skill”“看看 agent 是否按 skill 执行”“生成 skill 覆盖率或溯源报告”。在隔离沙箱中发起一次 headless 盲测，逐步骤溯源并产出中文复盘报告。不要用于编写新 skill、调试业务代码、代码审查，或复盘当前会话已经发生的执行。

Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

Organizes email triage, drafting, sending, and verification workflows with evidence-first reporting for mailbox operations.