Loading...
Loading...
Found 736 Skills
Covers both giving and getting feedback — structures and scripts feedback conversations (positive, constructive, or behavioral) and provides techniques for drawing honest feedback from your own team. Produces SBI-framed feedback statements, opening lines for hard conversations, scripts for real situations, ways to handle resistance, and methods for extracting real feedback from reports. Use when the user wants to give someone feedback, says "how do I tell someone," "this person is struggling," "address a behavior," "hard conversation," "someone is underperforming," "praise this person," "write feedback for," "I need to say something," "difficult conversation," "get feedback from my team," "my team won't give me feedback," "blind spots," or "what does my team think of me." Do NOT use for formal annual or performance reviews (use performance-reviews) or sensitive HR situations that go beyond feedback (use difficult-situations).
ALWAYS invoke this skill when the user mentions 10x-cli, @przeprogramowani/10x-cli, the 10xDevs CLI, or the 10xDevs course environment in a setup context. This skill fetches the live README — Claude does not know 10x-cli's current install steps without it. Applies to: installing, updating, reconfiguring for different AI tools (Cursor, Copilot, Claude Code), permission/npm errors, authentication, and onboarding after 10xDevs enrollment. Excludes: developing 10x-cli source code, contributing to the repo, building similar CLIs, or general project setup.
Search, qualify, and enrich people and companies. Use this skill whenever the user wants to find professionals, candidates, or KOLs by title, company, location, seniority, or audience; enrich known contacts with email, phone, or LinkedIn; research companies for industry, funding, tech stack, or hiring activity; look up someone's contact info; source candidates for recruiting; generate B2B lead lists; or perform background web research on people or organizations. Trigger this skill even when the user doesn't explicitly say "search" or "enrich" — any mention of finding contacts, sourcing, prospecting, looking up a person or company, or gathering business intelligence should activate it.
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
Use this skill whenever building, reviewing, or refactoring React components that fetch data from APIs — especially at scale (recommender carousels, infinite feeds, pages with many parallel fetches, dashboards). Covers request orchestration (parallelism, batching, deduplication), cache strategy (keys, normalization, staleTime, SWR), backend protection (concurrency caps, debounce/throttle, jittered retries, circuit breakers), prefetching (route loaders, hover/intent, idle, server hydration), failure resilience (AbortController, timeouts, error boundaries, stale fallback, idempotent mutations), and feed/carousel patterns (virtualization, cursor pagination, summary/detail split). Trigger even if the user doesn't explicitly mention "performance" or "scale" — any non-trivial React data-fetching code benefits from these patterns. Includes 5 ready-to-use scaffolding templates (resource query hook, carousel data loader, infinite feed, hover-prefetch link, request collapser).
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
Audit a Duvo Assignment — or a multi-Assignment workflow connected by a Case Queue — across many Jobs to find systemic inefficiencies and quality issues, then recommend concrete SOP and architecture changes. Use when the user asks to "analyze this workflow", "audit my Assignment", "why is this Assignment slow / inconsistent / low quality across runs", "why does my queue keep backing up", or wants a health check over an Assignment's recent Jobs — as opposed to debugging one failed Job (that's job-debugger). Reads recent Jobs, eval scores, the producer/consumer queue topology, and the SOPs those Jobs actually ran against via the Duvo public API; hands off to sop-writer for any SOP rewrite.
Official Roblox Studio MCP server tools reference. What each tool does, how to use it, reliability patterns, and workflows for script editing, building, playtesting, and debugging. Use when the AI has an MCP connection to Roblox Studio.
Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Two responsibilities — (1) place the project's `ruff.toml` from the bundled template once the stack and workspace are in place, and (2) run ruff against any Python files Claude has just generated or edited. Stops at "the touched files pass `ruff check`." TRIGGER when (any of these): (1) a Python file was just created or edited via Write / Edit / MultiEdit — invoke this skill before declaring the task done so ruff is run on the touched files; (2) a fresh ML workspace was just scaffolded by `organize-ml-workspace` and the project has no `ruff.toml` at its root yet — drop the bundled template; (3) the user asks about lint, format, docstring style, or reaches for `black` / `isort` / `flake8` / `pydocstyle` (redirect to ruff — the stack's canonical linter, owned by `data-science-python-stack` Tier 1). SKIP when: the project is non-Python; the only edits in this turn are to Markdown / TOML / JSON / YAML; the file lives in a third-party vendored directory the user doesn't own. HOW TO USE: run ruff manually on the files you just touched — do not configure a PostToolUse hook for this. **Read the "Stop conditions" block and emit the Pre-flight checklist as visible text in your response — both are mandatory before running ruff.**
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities. Use when creating skills, writing SKILL.md files, designing tool descriptions, or optimizing triggers. Triggers on "create a skill", "skill template", "write skill instructions", SKILL.md, metadata.json, progressive disclosure, trigger optimization, MCP tool design, or skill testing. Does NOT cover specific frameworks or languages (use dedicated skills).
Use when turning a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Does not cover dbt Fusion. Before implementing, verify dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, and manifest availability.