Loading...
Loading...
Found 1,895 Skills
Covers the full meeting lifecycle for engineering managers — produces guidance on whether to schedule a meeting, how to run it well, how to protect team focus time, how to kill recurring waste, and how to evaluate a past meeting from a transcript or description. Use when the user says "too many meetings," "meetings are a waste of time," "how do I run this meeting," "meeting agenda," "meeting culture," "nobody comes prepared," "meetings go nowhere," "how do I decline meetings," "distractions," "focus time," "engineers can't focus," "context switching," "protect engineering time," "review this meeting," or "transcript."
AI autonomous research agent for LLM training optimization using opencode as the agent. The agent autonomously modifies train.py, runs experiments, evaluates val_bpb, and iterates to find the best model. Use when: "run autoresearch", "start experiment", "train model", "autonomous research", "optimize LLM training".
Protocol and DeFi risk evaluation covering hack history, oracle dependencies, treasury health, TVL concentration, and yield sustainability. Use when the user asks "is X safe", "how risky is", protocol security, risk analysis, or wants to evaluate risk before investing or depositing funds.
Analyze municipal bonds including tax-equivalent yield calculations, GO vs revenue bond evaluation, and muni credit analysis. Use when the user asks about municipal bonds, tax-exempt income, tax-equivalent yield, AMT bonds, or muni credit quality. Also trigger when users mention 'muni bonds', 'tax-free bonds', 'state tax exemption', 'general obligation', 'revenue bonds', 'Build America Bonds', 'muni yield ratio', 'de minimis rule', or ask whether munis make sense for their tax bracket.
Screen core candidate stocks with high capital returns, stable moats, long-term compound interest potential, and strong earnings quality, and output priorities, valuation disciplines, and key points for continuous tracking. Applicable to scenarios such as long-term core position stock selection, compound interest asset pool construction, and high-quality company comparison.
Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr
Evaluate the source, strength, sustainability and weakening risks of a company's competitive advantages, and determine whether the moat truly exists and can be converted into returns. Suitable for scenarios such as long-term stock initial screening, high-quality company research, and competitive barrier judgment.
Use when planning, funding, scoping, or synthesizing enterprise research across workstreams — clinical study design, R&D program finance, market sizing/surveys, or product/user research. Triggers on "design this clinical study", "what sample size", "R&D budget", "burn rate", "capitalize or expense", "TAM SAM SOM", "market sizing", "survey design", "segment the market", "plan user interviews", "usability test", "synthesize research insights". Forks context to route to one of four Research-Operations sub-skills (clinical-research, research-finance, market-research, product-research) and returns a digest. Distinct from ra-qm-team (regulatory submission), finance (corporate close/valuation), research/grants (funding discovery), product-team (persona/journey/live experiments), and marketing-skill (campaign analytics).
Produce first drafts that match a writer's authentic voice using their Voice DNA Document. Consumes DNA documents from writing-dna-discovery skill. Generates 2 meaningfully different drafts with headlines, confidence assessment, decision notes, and DNA refinement suggestions. Collaborative partner that evaluates, pushes back, and advocates for quality. Handles blog posts, essays, newsletters, and more.
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.
Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos-Reason2 with SFT, or working with Cosmos-RL. Trigger phrases include "fine-tune Cosmos-Reason", "Cosmos-RL SFT", "video QA fine-tune", "Cosmos-Reason2-8B training".