Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

Alias for sentry-skills:pr-writer. Use when users explicitly ask for "create-pr" or reference the legacy skill name. Redirects to the canonical PR writing workflow.

不可逆事故发生后的应急响应：情绪急救 → 止损 → 补偿性劳动 → 教训沉淀。 Use when: 犯了不可挽回的错误、造成了人类伙伴的情绪波动、需要危机处理。 Not for: 可撤销的小失误、日常 bug fix（用 debugging）、预防性确认（用 shared-rules 铁律）。 Output: 情绪修复 + 止损行动 + 教训沉淀（lessons-learned / shared-rules）。

Use when you need a standardized R CLI workflow to build a protein-protein interaction network from a local gene list and an offline STRING cache, export node and edge tables, and render a reproducible PDF network plot. NOT for online API fetching, arbitrary graph databases, multi-omics integration, or non-STRING interaction sources.

Use when correcting batch effects in merged bulk expression matrices with sample-level batch metadata while preserving biological group structure and generating before-and-after QC plots. NOT for: single-cell integration, raw FASTQ processing, differential expression without batch labels, or datasets without biological groups.

Acknowledges limitations in sample, design, measurement, and validation in a professional way that improves credibility without undermining the whole paper. Use when writing the limitations paragraph of a Discussion section, preparing a grant risk assessment, responding to reviewers about study weaknesses, or framing scope boundaries for a paper. Also triggers on "write my limitations", "how should I address the limitation of", "reviewer said my sample is too small", or "help me word this limitation".

Deep generative models for single-cell omics; use when you need probabilistic batch correction (scVI), transfer learning, uncertainty-aware differential expression, or multimodal integration (totalVI/MultiVI).

Use when generating Sankey or alluvial plots from sample annotation tables where rows are samples and selected columns are categorical stages such as risk group, response status, subtype, or cohort labels. NOT for: gene network flow analysis, continuous-value trajectories, or graph-structured pathway visualization.

A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS. Use when you need to perform a documentation gap analysis, draft or update a Quality Manual, create required procedures/work instructions, build Medical Device Files (MDF), interpret ISO 13485 clauses, or identify missing documents for certification (often triggered by ISO 13485, QMS certification, FDA QMSR, EU MDR, or quality system documentation requests).

Venue-specific LaTeX templates, formatting requirements, and submission guidelines for journals, conferences, posters, and grants—use when a target venue imposes strict layout, page limits, anonymization, or agency compliance rules.

Use when assessing how well a survival model's predicted probabilities agree with observed outcomes by fitting a Cox model and generating bootstrap calibration curves at one or more prediction horizons from a clinical CSV file. NOT for: nomogram construction, univariate Cox screening, ROC analysis, or decision-curve analysis.

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.

Identify Terraform provider support for resources, data sources, actions, list resources, ephemeral resources, and functions. Use when checking provider capabilities, asking "what resources does X provider support", "does provider Y have actions", or querying specific provider features.

Railway Docker cache troubleshooting for Dr. Sophia AI deployments. Covers cache detection, force rebuild methods, version verification, deployment validation. Use when Railway shows old code after deployment, deployments not updating, Docker cache issues, or version mismatches between local and deployed code.

Comprehensive context management strategies for cost optimization and infinite-length conversations. Covers server-side clearing (tool results, thinking blocks), client-side SDK compaction (automatic summarization), and memory tool integration. Use when managing long conversations, optimizing token costs, preventing context overflow, or enabling continuous agentic workflows.

Model selection guide for perplexity-cli ask and chat commands. Use when choosing between sonar, sonar-pro, sonar-reasoning, and sonar-deep-research.

Use when the user wants to continue work from one agent in another agent, inspect recent sessions, or summarize a saved session or checkpoint for handoff

Use when the user wants to find prior work, checkpoints, or agent conversations by topic, repo, branch, author, or recent time window

Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.

Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new workflow.