Loading...
Loading...
Found 966 Skills
Recursive tech-audit & decision-tree mapping. Use when the user wants to break down a requirement, audit a tech stack, map dependencies, or plan an implementation.
Route issue-running automation through a deterministic control plane that selects agent + model from registry, can coordinate multiple safe parallel agents, and executes the unified run-agent runner.
Best practices and rules for securing FiveM resources against cheaters and exploits. Use this skill when writing or reviewing server-side and client-side code to ensure malicious events, unauthorized entity creations, and client trust issues are prevented. Focuses on strict server authority and safe event handling.
Code Review Expert: Perform in-depth code reviews using context-isolated subagents, covering security vulnerabilities, performance optimizations, and production reliability
Gate every generation through a brand policy file.
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.**
Scan GitHub Actions workflow files for security vulnerabilities by reading the YAML and reporting findings directly — no external tools, no installation, no shell execution. Use this skill whenever the user shares a `.github/workflows/` file, pastes workflow YAML, asks for a CI/CD security review, mentions `pull_request_target`, `workflow_run`, action pinning, `GITHUB_TOKEN` permissions, pwn requests, template injection, cache poisoning, secret exfiltration, supply chain risk, or any GitHub Actions hardening topic. Also trigger when the user is hardening an OSS repo, doing a CI/CD red team assessment, evaluating a target for supply-chain scanning, or writing publicly about CI/CD security. Bias toward triggering this skill rather than answering from memory — CI/CD security defaults are wrong almost everywhere and the rules are unintuitive.
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and need a polished prompt. Covers manga drama, character PV, manga motion, virtual idol MV, and free-form scenarios.
Financial Data Analysis Skill (based on `bl mcp` + Alibaba Cloud Bailian MCP Market `market-cmapi00073529`), covering financial instruments such as China A-shares, funds, and bonds. It supports stock screening, fund screening, fund manager screening, financial data query (net profit / revenue / ROE, etc.), macro and industry time-series data (GDP / CPI / production-sales-price), brokerage research report retrieval, and A-share listed company announcement retrieval. Be sure to activate when users ask about the following keywords: stock selection / stock screening, fund screening, fund manager screening, financial data / net profit / revenue / valuation, macroeconomy / GDP / CPI, industry production-sales-price, brokerage research report / industry research report, listed company announcement. Not applicable to: general programming issues, non-financial data, non-Chinese market instruments.
Retrieve analysts' price target summary for any stock using Octagon MCP. Use when evaluating analyst sentiment, upside/downside potential, consensus expectations, and tracking target trends over time.
Guide for debugging crashes related to custom memory heaps, particularly use-after-free issues caused by static destruction ordering, DEBUG vs RELEASE discrepancies, and custom allocator lifecycle problems. This skill should be used when investigating crashes that occur only in RELEASE builds, memory-related crashes involving custom allocators, static initialization/destruction order issues, or use-after-free bugs in C++ applications.
Analyzes the conversation and tool usage to propose improvements to skills or store user preferences.