Loading...
Loading...
Found 892 Skills
Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.
Query Catalog, database, and table metadata resources in Alibaba Cloud Data Lake Formation (DLF). Provides read-only queries via the DLF OpenAPI Python SDK, supporting listing and viewing Catalogs, databases, tables with their detailed information and Schema definitions. Use cases: "list available Catalogs", "list databases", "view table schema", "search tables", "search tables by name", "fuzzy search", "view DLF metadata", "what databases are in the data lake", "what columns does a table have", "find tables whose name contains xxx". This Skill only contains read-only operations — no create, modify, or delete operations.
Use BEFORE `/seeflow` whenever the user phrases the request as inspection rather than creation — "show me", "show the", "how does X work", "what does X do", "diagram our system", "explain the flow", "where does X live", "what handles Y", "what depends on Z", or names a flow by slug/title without an explicit "create / scaffold / generate / add" verb. Also use when onboarding to a repo that already has seeflow flows registered. Read-only — never mutates flows; auto-hands off to `/seeflow` only when no matching flow is registered.
Socratic drilling — it asks, you answer, it pushes back. Does NOT give you the answer until you've earned it. Use when the user says "drill me on", "quiz me", "socratic", "test me on [subject]", or wants to study actively.
HK IPO Subscription Analysis — A "Four-Dimensional Evaluation" framework to diagnose whether Hong Kong new stocks are worth subscribing (Pricing Rationality / Issue Quality / Market Timing / Fundamental Outlook). Outputs three-tier ratings: Recommend / Neutral / Avoid, plus prospectus highlights, risk warnings, and subscription references. It is retail-investor friendly with conclusions upfront. Covers three scenarios: in-depth evaluation of a single new stock, browsing recent IPO subscription calendars, and judging whether to chase newly listed stocks after missing the subscription. Prioritizes data from Longbridge CLI (ipo detail / ipo subscriptions / ipo wait-listing / ipo listed / peer-comparison / news / quote / kline / index-quote, etc.); uses MCP fallback for data missing from CLI; uses WebSearch as a last resort for data still unavailable (prospectus TAM, original cornerstone announcement, claw-back ratio, grey market price, underwriter industry ranking). **The report must end with a fixed "Data Source Details" appendix**, where every figure can be traced to line number + capture time + period. Only covers Hong Kong Main Board and GEM; does not involve US / A-share IPOs; must actively prompt leverage risks when margin financing (孖展) is involved. Triggers: "打新", "港股打新", "新股申购", "新股申購", "新股", "打新分析", "新股分析", "招股", "招股书", "招股書", "基石投资者", "基石投資者", "国际配售", "國際配售", "公开发售", "公開發售", "暗盘", "暗盤", "回拨机制", "回撥機制", "孖展", "新股盈亏", "新股盈虧", "次新股", "破发", "破發", "中签率", "中籤率", "新股几手", "新股幾手", "新股值不值得打", "新股能不能打", "港股 IPO 推荐", "港股 IPO 推薦", "近期港股新股", "HK IPO analysis", "hong kong IPO worth it", "HK new listing", "cornerstone investor", "prospectus highlights", "grey market premium", "subscription ratio", "claw-back", "margin financing IPO", "0700.HK", "09988.HK", "01024.HK"
Handle Chainlink ACE (Automated Compliance Engine) work using the public smartcontractkit/chainlink-ace repository and official docs.chain.link ACE Platform docs. Use for audited ACE core contracts, managed Platform/Beta scope, Coordinator API, Reporting API, Policy Management, PolicyEngine, PolicyProtected, policy chains, custom policies, extractors, mappers, Cross-Chain Identity (CCIDs), credential registries, KYC/AML credentials, sanctions screening, regulated tokens, ERC-20 and ERC-3643 compliance token examples, upgrade guidance, and BUSL licensing. Trigger on any mention of ACE, Automated Compliance Engine, chainlink-ace, Chainlink compliance, policy enforcement, ERC-3643, or onchain compliance rules, even if the user does not explicitly say 'ACE'.
Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / instructions.md / queries.yml / memory pairs, then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.
Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says "grade my IRAC", "check my essay", or "I wrote this, give me feedback".
Internal sub-skill for job-hunt suite. Performs STAR decomposition of resume and scores JD-resume match across 4 dimensions. Does NOT generate tailoring suggestions (handled by tailor). Do NOT invoke directly — use the job-hunt main skill instead.
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.**
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, ingestion of customer-supplied pre-generated AnomalyGen images, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. EA variant — does not run AnomalyGen inline; the customer pre-generates synthetic NG/OK pairs out-of-band and the loop ingests them. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and pre-generated synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.