docs-quiz
Run an interactive documentation-based quiz for a user-selected technology and topic area. Use when the user wants to practice a framework, library, API, language feature, or other technical docs by choosing between two short code snippets that test mental-model comprehension.
What this skill does
# Docs Quiz Run a short, looping quiz based on current documentation for the technology and area the user names. The goal is to improve the user's mental model, not to drill syntax trivia. ## Question Design Each question must test a meaningful concept from the docs. Focus on how the technology behaves, why a choice is appropriate, what constraints apply, and how the parts relate to each other. Use two short code snippets as the only answer options. Do not use prose summaries, conceptual descriptions, command labels, API names, or mixed prose/code as options. - one snippet correctly applies the concept - one snippet reflects a plausible but incorrect mental model Avoid questions where the deciding factor is only: - import package names - exact method names - punctuation, spelling, or single-character syntax differences - formatting, naming style, or boilerplate order Keep snippets focused on one concept and include enough surrounding context for the user to reason from the model rather than guess an API detail. Add comments only when needed to make the contrast clear. ## Setup 1. Identify the technology and topic area from the user's request. 2. Read authoritative, current docs for that technology before the first question. 3. If the technology is missing, ask one concise clarification question. 4. If the topic area is missing, start with fundamental concepts and build progressively toward more advanced concepts. 5. Keep questions focused on the requested or inferred progression unless the user asks to change scope. ## Quiz Round For each round: 1. Pick one docs concept that changes how a developer should reason about the technology. 2. Create two short code snippet options that follow the Question Design rules. 3. Randomize which option is correct. 4. Show only: - a level-3 heading (`###`) containing a direct question that asks the user to choose the option that applies the concept correctly - `_Option 1_` - first option - `_Option 2_` - second option 5. Wait for the user's response. ## Progress Display After every quiz-answer explanation, show the quiz progress so far between two `---` lines with the label `Progress:` before the progress marks. Add a blank line before and after the closing `---` so Markdown does not parse the progress label as a heading. Use `✅` for each correct choice and `❌` for each wrong choice or no-choice answer, separated by spaces. Example: ```text --- Progress: ✅ ✅ ❌ --- ``` ## Response Outcomes Treat `1`, `2`, `Option 1`, or `Option 2` as a choice. Classify every quiz response as a correct choice, wrong choice, or no-choice answer. Reply with the matching outcome below, show the progress display, then immediately continue with the next round in the same format. Only correct-choice explanations have a character limit. Other quiz-answer explanations should use enough normal prose to teach the deciding rule or docs concept. After the explanation and before the progress display, include a Markdown link with text `Docs` that points to the specific docs section explaining the concept. ### Correct Choice Recognize when the user chooses the correct option. Reply with `✅ Correct!` on its own line, followed by a blank line, then an explanation under 240 characters that mentions the deciding rule or concept. ### Wrong Choice Recognize when the user chooses the wrong option. Reply with `❌ Incorrect` on its own line, followed by a blank line, then explain the specific rule or docs concept in normal prose. ### No-Choice Answer Recognize when the user does not choose an option. Explain the specific rule or docs concept in normal prose. ## Documentation Rules - Use only official documentation sources: official docs, API references, language specifications, or official repository docs. - Do not use blogs, tutorials, Q&A sites, examples from third-party sites, AI summaries, or any other unofficial source. - For fast-moving technologies, verify current docs before generating questions. - If official docs are unavailable, say so and do not generate quiz questions for that technology or topic.
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.