Data analysis, machine learning, LLM apps, and prompt design (9.4K skills)
Determines if current hormone levels are within target range for affirmed gender (e.g., testosterone 400-700 ng/dL for transgender males, estradiol 100-200 pg/mL for transgender females). Triggers include patient on hormone therapy and time for level check.
The English summary is being prepared. Showing the original description.
Assesses patient’s knowledge of diabetic ketoacidosis prevention, recognition, and treatment. Triggered by clinician prompts such as 'Review sick-day rules and DKA signs' or 'Ensure patient knows when to seek help for hyperglycemia'.
The English summary is being prepared. Showing the original description.
Assesses that CGM low- and high-glucose alarm thresholds are individualized to optimize patient benefit and minimize alarm fatigue. Triggered by clinician prompts to 'Review low-glucose alarm thresholds' or 'Ensure alarms are individualized and not excessive'.
The English summary is being prepared. Showing the original description.
Systematically interpret a Medtronic CareLink or MiniMed 780G Daily Review download in a structured 6-step clinical workflow — covering Time in Range, insulin delivery, day/night patterns, hypo and hyperglycemia root causes, and a prioritised action plan. Trigger when a clinician uploads or shares a CareLink report, MiniMed download, 780G Daily Review, pump download, or asks to review a patient's CGM or insulin pump data.
The English summary is being prepared. Showing the original description.
Guide pump setting adjustments for the MiniMed 780G system based on CareLink data, using Medtronic's 3-step follow-up workflow. Use when a clinician has CareLink data for a 780G patient and wants to know what to change — which setting, by how much, and how to program it. Triggers include: "what do I adjust", "how to fix high TIR", "how to reduce hypos", "adjust ICR/ISF/basal", "SmartGuard settings", "780G pump settings review", or any question about optimising 780G therapy after reviewing a download.
The English summary is being prepared. Showing the original description.
Assesses patient’s understanding of how CGM data (trends, rates of change) differ from discrete SMBG fingerstick values. Triggered when clinicians hear requests to explain lag and trend arrows on CGM or teach the difference between CGM glucose and fingerstick glucose.
The English summary is being prepared. Showing the original description.
This skill recommends bilateral adrenalectomy for occult or metastatic ectopic ACTH secretion or as a life-preserving emergency treatment in patients with very severe ACTH‑dependent Cushing’s syndrome who cannot be promptly controlled by medical therapy. It is triggered by life‑threatening complications of uncontrolled hypercortisolism such as infection, pulmonary thromboembolism, cardiovascular catastrophe, or acute psychosis.
The English summary is being prepared. Showing the original description.
Adjusts intravenous bisphosphonate dosing and infusion duration for patients with hypercalcemia of malignancy and renal insufficiency (creatinine clearance <60 mL/min). Triggered when a clinician encounters renal impairment and asks how to modify zoledronic acid or pamidronate infusion rates.
The English summary is being prepared. Showing the original description.
Establishes age- and gender-specific blood pressure goals for pediatric patients with primary aldosteronism (PA) using published normative data to assess treatment adequacy and avoid over-treatment. Use when managing hypertension in children with PA to evaluate if BP is adequately controlled; triggers include pediatric PA hypertension, BP not normalized with glucocorticoid therapy, and need for age‑specific BP targets.
The English summary is being prepared. Showing the original description.
Determines the appropriate IV pamidronate dose (60‑90 mg) and infusion duration (2‑24 h) for adults with hypercalcemia of malignancy based on renal function. Triggered when a clinician orders pamidronate and asks how to adjust for kidney dysfunction (eGFR < 60 mL/min/1.73 m²).
The English summary is being prepared. Showing the original description.
Reconcile baseline-versioned files that the `create-baseline upgrade` CLI staged for LLM-assisted semantic merge. Use when the CLI prints "Open Claude Code and run /upgrade-project to reconcile". Reads the stage manifest at `.claude/state/upgrade/<ts>/manifest.json`, reasons through each pending file's three-way delta in main context, writes a reconciled LOCAL, then deletes the stage when every file lands. Supports `--dry-run` (preview the reconciled diff without writing) and a structured "needs-user-input" fallback when the conflict cannot be disambiguated automatically.
The English summary is being prepared. Showing the original description.
Write technical documentation that matches the measured profile of professionally-written docs. Carries the craft rules derived from 114k words of pre-2022 documentation (SQLite, PostgreSQL, Python, Django, Rust, Go, Pro Git, nginx), the per-Diátaxis-type numeric targets, and the copywriting register for page leads. Use when drafting or rewriting any documentation prose, or when a page is factually right but reads as machine-written.
The English summary is being prepared. Showing the original description.
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
The English summary is being prepared. Showing the original description.
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.
The English summary is being prepared. Showing the original description.
An infographic skill for AI agents — works inside Claude Code, Codex, Hermes, OpenClaw, Cursor, and any agent host that loads skills. Create professional infographics as self-contained HTML files with PNG exports. Use when the user asks to create, design, generate, build, or make an infographic, data visualization, visual explainer, chart poster, cheatsheet, or pocket guide. Trigger phrases include "make this visual", "turn this into a graphic", "visualize this data", "infographic for X", "cheatsheet for X", or when the user provides structured data (tokenomics allocations, ecosystem/partner lists, timelines, comparisons, step-by-step processes) AND asks for a visual output. Covers tokenomics, ecosystem overviews, game overviews, cheatsheets, airdrop guides, comparisons, and process flows. Do NOT trigger for plain text answers, markdown tables, bulleted summaries, questions asking for advice or explanations about a topic (even when the topic is tokenomics, ecosystem, vesting, etc.), inline chat diagrams, or data processing with no visual output requested. The signal is "asks for a visual", not "mentions a keyword".
The English summary is being prepared. Showing the original description.
W&B: log ML experiments, sweeps, model registry, dashboards.
The English summary is being prepared. Showing the original description.
OBLITERATUS: abliterate LLM refusals (diff-in-means).
The English summary is being prepared. Showing the original description.
Outlines: structured JSON/regex/Pydantic LLM generation.
The English summary is being prepared. Showing the original description.
vLLM: high-throughput LLM serving, OpenAI API, quantization.
The English summary is being prepared. Showing the original description.
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
The English summary is being prepared. Showing the original description.
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
The English summary is being prepared. Showing the original description.
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
The English summary is being prepared. Showing the original description.
Karpathy's LLM Wiki: build/query interlinked markdown KB.
The English summary is being prepared. Showing the original description.
Iterative Python via live Jupyter kernel (hamelnb).
The English summary is being prepared. Showing the original description.