Stage all changes, create a conventional commit, and push to the remote branch. Use when explicitly asks to push changes ("push this", "commit and push"), mentions saving work to remote ("save to github", "push to remote"), or completes a feature and wants to share it.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

Author-triggered fresh-context scan of PR diff before formal review. Finding generator, NOT approval authority. Use when: quality-gate 通过、PR 非 trivial、想降低正式 reviewer 认知负荷。 Not for: 正式 review verdict、approval、merge decision。 Output: Finding list（附在 review request 中）。

钉钉文件管理（存储层，覆盖钉盘与文档空间）。Use when 用户说 钉盘/文档空间/我的文档中的普通文件或文件夹、查找/最近访问或编辑文档列表/上传/下载/复制/移动/重命名/删除/回收站/权限/评论/元信息，或本地与钉盘文件夹比较、拉取、推送、双向同步；也承接在线文档节点的存储管理。文档正文编辑与导出走 dingtalk-doc；明确的知识库空间及空间内节点组织走 dingtalk-wiki。命令前缀：dws drive。

Reach Jira and Slack where the Atlassian and Slack MCPs stop, via the `jira` and `slack` CLIs. Use to download a ticket's or thread's attachments, upload a file to a Jira issue or Slack message, delete a Slack post, or write a Jira description with checkboxes or embedded images.

Turns your protocol and analysis workflow into publication-ready Methods text. Use when writing or revising the Methods section of a biomedical manuscript, ensuring it complies with reporting guidelines (CONSORT, STROBE, PRISMA, TRIPOD), matches what is in the Results section, and satisfies journal-specific word limits and declarations. Also triggers on "write my methods", "revise my methods section", "how to report my statistics", "what do I need to include in methods for [study type]", or "make my methods CONSORT-compliant".

Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification, lambda.min, lambda.1se. NOT for: survival/Cox modeling, multiclass outcomes, single-cell data, or non-expression tables.

Access over 200M protein structures from AlphaFold DB; use when you need to retrieve predicted 3D structures (PDB/mmCIF), confidence metrics (pLDDT/PAE), or protein metadata by UniProt accession.

Write a Docker Sandbox kit — a spec.yaml declaring setup steps, network permissions and credentials. Use when authoring or fixing a kit, choosing between kind mixin and kind sandbox, migrating a spec from schemaVersion 1 to 2, or a kit fails sbx kit validate.

JSON input and output schemas for all perplexity-cli commands (search, ask, chat). Use when constructing --json payloads or parsing command output programmatically.

Agent recipes, piping patterns, scripting idioms, and common workflows for perplexity-cli. Use when constructing multi-step queries, piping output, or integrating into agent workflows.

Manages production incident response workflows from initial triage through postmortem. Guides responders through alert acknowledgment, mitigation, status communication, and follow-up. Use when the user mentions outages, service degradation, on-call pages, incident response, postmortems, error rate spikes, latency issues, or on-call escalation. Covers rollback decisions, stakeholder updates, and structured post-incident review.

Use this skill for dispatching prepared VASP jobs with vasp_execute_batch, choosing valid input/output layouts, avoiding nested or overlapping calc trees, and collecting clean failure evidence.

Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy evaluation or autonomous rule-based Tasks.

Create complete, portable handoffs from Manus to another agent or Manus instance. Use when transferring an in-progress task, project, workflow, research effort, or operational context and the recipient needs both a concise execution prompt and a structured repository of supporting documents, custom skills, decisions, rules, and artifacts.

Govern a personal software and creative portfolio with explicit ownership, lifecycle status, and attention limits. Use when deciding where a new idea belongs, reviewing overlapping repositories, selecting one active experiment, maintaining a portfolio ledger, or archiving dormant work without applying startup traction metrics to personal tools.

Audit and fix agent-facing documentation by comparing docs to implementation, identifying broken links and stale references, surfacing undocumented conventions, and updating CLAUDE.md files. Use when CLAUDE.md may be stale, docs don't match code, or undocumented conventions exist.

Post-session reflection skill for review session, retrospective, or session summary. Reads recent git history, artifacts, and context files to extract learnings and produce improvement proposals for skills, CLAUDE.md, hooks, and plan templates. Use after any substantive session to capture what did we learn and embed improvements back into codebase context.