Loading...
Loading...
Found 2,521 Skills
Generate and publish blog posts from any project to kelegele/agent-blog. ZERO DEPENDENCIES — does NOT require Node.js, pnpm, git, or any local build tools. Works with only a browser and a GitHub token. Triggers on: "写篇博客", "blog this", "发博文", "publish blog", "把项目写成文章", "写篇文章", "blog it", "post article", "新文章", "new blog post", "blog this project", "发一篇博文", "写一篇博文", "blog post about this", "edit blog post", "修改文章", "更新博文", "edit article". Collects project context, collaborates on outline, writes Markdown with correct frontmatter, validates article format, generates a standalone HTML preview by reading live blog source, manages draft/review/publish flow. Pushes to kelegele/agent-blog main branch. Vercel auto-deploys on push. Use this skill whenever the user expresses intent to write about their current work as a blog post.
Use when a GitHub issue needs triage — typically one carrying status/needs-triage label, a freshly opened issue without type/priority labels, or when the user says "triage
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.
Front door of the SDD flow. When the user asks for a feature or bug fix ("implementa…", "agrega…", "arregla…", "add…", "build…", "fix…"), FIRST scan the request + codebase context for load-bearing ambiguity and ask a few targeted clarifying questions (selectable options, recommended first) BEFORE writing any spec or code — then hand a well-formed goal to /opsx:propose (small) or the sdd-feature-flow workflow (large). Skip the questions when the request is already unambiguous. Modeled on GitHub Spec-Kit's /clarify.
Create GitHub issues with proper formatting, labels, and AI implementation prompts. Use when asked to create an issue, report a bug, or request a feature.
This skill is used when users want to find plugins for DeepSeek Harness: such as asking 'Are there any plugins that can...', 'Help me install XX', or 'What interesting things are there in the ecosystem'. It discovers public repositories across individuals and organizations from the `dsh-plugin` topic on GitHub, filters candidates, waits for user confirmation, then determines the installation method from the repository declaration and verifies the mounting. It only handles finding and installing plugins; for developing new plugins, redirect to `make-dsh-plugin`.
Initialize projects with safe, preference-driven scaffolds, docs, AI instructions, quality gates, GitHub setup, and design baselines. Use when starting a repo or non-destructively adding conventions. NOT for product features, agents, MCP servers, cloud provisioning, or destructive migrations.
Full GitHub issue lifecycle: pick an issue, create it, branch, commit, squash, push, PR, merge. Owns every git and gh write in the pipeline. Handles project board integration, base branch detection (main/master/epic-*), and compact step reports. Supports entering at any step.
Synchronize or export GitHub repository labels against a predefined label set. Compares, creates, updates, deletes, or reads labels as reusable JSON definitions.
Create or update a GitHub pull request with a standardized template. Use when the user wants to open a PR, create a pull request, update a PR description, submit changes, or push a PR.
File a GitHub issue for the platform team when the app cannot do what the person needs, when something is platform-owned (the library in vendor/, models, deploy, auth, connectors), or when a change failed twice or is too big. Interviews the person first, gathers evidence and a mockup, shows the draft, then files it. Use whenever docs/CAPABILITIES.md says "Not possible", or you are stuck.
Reviews PR comments from GitHub (Copilot, reviewers), evaluates against actual code, replies with reasoning, and resolves threads. Triggers on "review pr comments", "address pr feedback", "fix pr comments", or "review copilot suggestions".