[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATF7X3WV2XSAB8X0GY7XHA":3,"skill-same:01M7ATF7X3WV2XSAB8X0GY7XHA":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7ATF7X3WV2XSAB8X0GY7XHA","automation-recommender",null,"Analyze a codebase and recommend DeepSeek Harness automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their DeepSeek Harness setup, mentions improving DeepSeek Harness workflows, asks how to first set up DeepSeek Harness for a project, or wants to know what DeepSeek Harness features they should use.","Sivan757\u002Fdsh-agent-plugins-market","Sivan757","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29885829?v=4","01M7AT8RD4ZDR4ACB02GX7X3GT","01M7AT8RDRG2YFMMYBW0DXAT68",21,"MIT","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automation-recommender\ndescription: Analyze a codebase and recommend DeepSeek Harness automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their DeepSeek Harness setup, mentions improving DeepSeek Harness workflows, asks how to first set up DeepSeek Harness for a project, or wants to know what DeepSeek Harness features they should use.\n---\n\n# Automation Recommender\n\nAnalyze codebase patterns to recommend tailored DeepSeek Harness automations across all extensibility options.\n\n**This skill is read-only.** It analyzes the codebase and outputs recommendations. It does NOT create or modify any files. Users implement the recommendations themselves or ask the agent separately to help build them.\n\n## Output Guidelines\n\n- **Recommend 1-2 of each type**: Don't overwhelm - surface the top 1-2 most valuable automations per category\n- **If user asks for a specific type**: Focus only on that type and provide more options (3-5 recommendations)\n- **Go beyond the reference lists**: The reference files contain common patterns, but use web search to find recommendations specific to the codebase's tools, frameworks, and libraries\n- **Tell users they can ask for more**: End by noting they can request more recommendations for any specific category\n\n## Automation Types Overview\n\n| Type | Best For |\n|------|----------|\n| **Hooks** | Automatic actions on tool events (format on save, lint, block edits) |\n| **Subagents** | Specialized reviewers\u002Fanalyzers that run in parallel |\n| **Skills** | Packaged expertise, workflows, and repeatable tasks (invoked by the agent or user via `\u002Fskill-name`) |\n| **Plugins** | Collections of skills that can be installed |\n| **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) |\n\n## Workflow\n\n### Phase 1: Codebase Analysis\n\nGather project context:\n\n```bash\n# Detect project type and tools\nls -la package.json pyproject.toml Cargo.toml go.mod pom.xml 2>\u002Fdev\u002Fnull\ncat package.json 2>\u002Fdev\u002Fnull | head -50\n\n# Check dependencies for MCP server recommendations\ncat package.json 2>\u002Fdev\u002Fnull | grep -E '\"(react|vue|angular|next|express|fastapi|django|prisma|supabase|convex|stripe)\"'\n\n# Check for existing DeepSeek Harness config\nls -la .agents\u002F AGENTS.md 2>\u002Fdev\u002Fnull\n\n# Analyze project structure\nls -la src\u002F app\u002F lib\u002F tests\u002F components\u002F pages\u002F api\u002F 2>\u002Fdev\u002Fnull\n```\n\n**Key Indicators to Capture:**\n\n| Category | What to Look For | Informs Recommendations For |\n|----------|------------------|----------------------------|\n| Language\u002FFramework | package.json, pyproject.toml, import patterns | Hooks, MCP servers |\n| Frontend stack | React, Vue, Angular, Next.js | Playwright MCP, frontend skills |\n| Backend stack | Express, FastAPI, Django | API documentation tools |\n| Database | Prisma, Supabase, Convex, raw SQL | Database \u002F backend MCP servers |\n| External APIs | Stripe, OpenAI, AWS SDKs | context7 MCP for docs |\n| Testing | Jest, pytest, Playwright configs | Testing hooks, subagents |\n| CI\u002FCD | GitHub Actions, CircleCI | GitHub MCP server |\n| Issue tracking | Linear, Jira references | Issue tracker MCP |\n| Docs patterns | OpenAPI, JSDoc, docstrings | Documentation skills |\n\n### Phase 2: Generate Recommendations\n\nBased on analysis, generate recommendations across all categories:\n\n#### A. MCP Server Recommendations\n\nSee [references\u002Fmcp-servers.md](references\u002Fmcp-servers.md) for detailed patterns.\n\n| Codebase Signal | Recommended MCP Server |\n|-----------------|------------------------|\n| Uses popular libraries (React, Express, etc.) | **context7** - Live documentation lookup |\n| Frontend with UI testing needs | **Playwright** - Browser automation\u002Ftesting |\n| Uses Supabase | **Supabase MCP** - Direct database operations |\n| Uses Convex | **Convex MCP** - Live deployment introspection, run queries\u002Fmutations, manage env vars and logs |\n| PostgreSQL\u002FMySQL database | **Database MCP** - Query and schema tools |\n| GitHub repository | **GitHub MCP** - Issues, PRs, actions |\n| Uses Linear for issues | **Linear MCP** - Issue management |\n| AWS infrastructure | **AWS MCP** - Cloud resource management |\n| Slack workspace | **Slack MCP** - Team notifications |\n| Memory\u002Fcontext persistence | **Memory MCP** - Cross-session memory |\n| Sentry error tracking | **Sentry MCP** - Error investigation |\n| Docker containers | **Docker MCP** - Container management |\n\n#### B. Skills Recommendations\n\nSee [references\u002Fskills-reference.md](references\u002Fskills-reference.md) for details.\n\nCreate skills in `.agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md` and commands in `.agents\u002Fcommands\u002F\u003Cname>.md`; the project contributes both only while the market plugin's project-layout scan is on. Some are also available via plugins:\n\n| Codebase Signal | Skill | Plugin |\n|-----------------|-------|--------|\n| Building plugins | skill-development | plugin-dev |\n| Git commits | commit | commit-commands |\n| React\u002FVue\u002FAngular | frontend-design | frontend-design |\n| Automation rules | writing-rules | hookify |\n| Feature planning | feature-dev | feature-dev |\n\n**Custom skills to create** (with templates, scripts, examples):\n\n| Codebase Signal | Skill to Create | Invocation |\n|-----------------|-----------------|------------|\n| API routes | **api-doc** (with OpenAPI template) | Both |\n| Database project | **create-migration** (with validation script) | User-only |\n| Test suite | **gen-test** (with example tests) | User-only |\n| Component library | **new-component** (with templates) | User-only |\n| PR workflow | **pr-check** (with checklist) | User-only |\n| Releases | **release-notes** (with git context) | User-only |\n| Code style | **project-conventions** | Model-only |\n| Onboarding | **setup-dev** (with prereq script) | User-only |\n\n#### C. Hooks Recommendations\n\nSee [references\u002Fhooks-patterns.md](references\u002Fhooks-patterns.md) for configurations.\n\n| Codebase Signal | Recommended Hook |\n|-----------------|------------------|\n| Prettier configured | PostToolUse: auto-format on edit |\n| ESLint\u002FRuff configured | PostToolUse: auto-lint on edit |\n| TypeScript project | PostToolUse: type-check on edit |\n| Tests directory exists | PostToolUse: run related tests |\n| `.env` files present | PreToolUse: block `.env` edits |\n| Lock files present | PreToolUse: block lock file edits |\n| Security-sensitive code | PreToolUse: require confirmation |\n\n#### D. Subagent Recommendations\n\nSee [references\u002Fsubagent-templates.md](references\u002Fsubagent-templates.md) for templates. Subagents are agent role cards under the plugin's `com.deepseek.harness\u002Fagents\u002F` or the project's `.agents\u002Fagents\u002F`, delegated to with `subagent_run`.\n\n| Codebase Signal | Recommended Subagent |\n|-----------------|---------------------|\n| Large codebase (>500 files) | **code-reviewer** - Parallel code review |\n| Auth\u002Fpayments code | **security-reviewer** - Security audits |\n| API project | **api-documenter** - OpenAPI generation |\n| Performance critical | **performance-analyzer** - Bottleneck detection |\n| Frontend heavy | **ui-reviewer** - Accessibility review |\n| Needs more tests | **test-writer** - Test generation |\n\n#### E. Plugin Recommendations\n\nSee [references\u002Fplugins-reference.md](references\u002Fplugins-reference.md) for available plugins.\n\n| Codebase Signal | Recommended Plugin |\n|-----------------|-------------------|\n| General productivity | **agent-skills** - Core skills bundle |\n| Document workflows | Install docx, xlsx, pdf skills |\n| Frontend development | **frontend-design** plugin |\n| Building AI tools | **mcp-builder** for MCP development |\n\n### Phase 3: Output Recommendations Report\n\nFormat recommendations clearly. **Only include 1-2 recommendations per category** - the most valuable ones for this specific codebase. Skip categories that aren't relevant.\n\n```markdown\n## DeepSeek Harness Automation Recommendations\n\nI've analyzed your codebase and identified the top automations for each category. Here are my top 1-2 recommendations per type:\n\n### Codebase Profile\n- **Type**: [detected language\u002Fruntime]\n- **Framework**: [detected framework]\n- **Key Libraries**: [relevant libraries detected]\n\n---\n\n### 🔌 MCP Servers\n\n#### context7\n**Why**: [specific reason based on detected libraries]\n**Configure**: add it to `.agents\u002Fmcp.json`\n\n---\n\n### 🎯 Skills\n\n#### [skill name]\n**Why**: [specific reason]\n**Create**: `.agents\u002Fskills\u002F[name]\u002FSKILL.md`\n**Invocation**: User-only \u002F Both \u002F Model-only\n**Also available in**: [plugin-name] plugin (if applicable)\n```yaml\n---\nname: [skill-name]\ndescription: [what it does]\ndisable-model-invocation: true  # for user-only\n---\n```\n\n---\n\n### ⚡ Hooks\n\n#### [hook name]\n**Why**: [specific reason based on detected config]\n**Where**: `.agents\u002Fhooks\u002Fhooks.json`\n\n---\n\n### 🤖 Subagents\n\n#### [agent name]\n**Why**: [specific reason based on codebase patterns]\n**Where**: `.agents\u002Fagents\u002F[name].md`\n\n---\n\n**Want more?** Ask for additional recommendations for any specific category (e.g., \"show me more MCP server options\" or \"what other hooks would help?\").\n\n**Want help implementing any of these?** Just ask and I can help you set up any of the recommendations above.\n```\n\n## Decision Framework\n\n### When to Recommend MCP Servers\n- External service integration needed (databases, APIs)\n- Documentation lookup for libraries\u002FSDKs\n- Browser automation or testing\n- Team tool integration (GitHub, Linear, Slack)\n- Cloud infrastructure management\n\n### When to Recommend Skills\n\n- Document generation (docx, xlsx, pptx, pdf — also in plugins)\n- Frequently repeated prompts or workflows\n- Project-specific tasks with arguments\n- Applying templates or scripts to tasks (skills can bundle supporting files)\n- Quick actions invoked with `\u002Fskill-name`\n- Workflows whose heavy work should stay out of the main context — the skill body delegates to an agent role card with `subagent_run`\n\n**Invocation control:**\n- `disable-model-invocation: true` — User-only (for side effects: deploy, commit, send)\n- `user-invocable: false` — Model-only (for background knowledge)\n- Default (omit both) — Both can invoke\n\n### When to Recommend Hooks\n- Repetitive post-edit actions (formatting, linting)\n- Protection rules (block sensitive file edits)\n- Validation checks (tests, type checks)\n\n### When to Recommend Subagents\n- Specialized expertise needed (security, performance)\n- Parallel review workflows\n- Background quality checks\n\n### When to Recommend Plugins\n- Need multiple related skills\n- Want pre-packaged automation bundles\n- Team-wide standardization\n\n---\n\n## Configuration Tips\n\n### MCP Server Setup\n\nMCP servers are declared in a plugin's `mcp.json` or the project's `.agents\u002Fmcp.json`.\n\n**Team sharing**: Check `.agents\u002Fmcp.json` into repo so entire team gets same MCP servers\n\n**Debugging**: The market page's MCP services tab reports each service's status and failures\n\n**Prerequisites to recommend:**\n- GitHub CLI (`gh`) - enables native GitHub operations\n- Puppeteer\u002FPlaywright CLI - for browser MCP servers\n\n### Headless Mode (for CI\u002FAutomation)\n\nRecommend the headless profile for automated pipelines:\n\n```bash\n# Pre-commit hook example\ndsh --profile headless \"fix lint errors in src\u002F\"\n\n# CI pipeline piping the final message into the next command\ndsh --profile headless \"\u003Cprompt>\" | your_command\n```\n\n### Permissions for Hooks\n\nHook commands run under the session's sandbox and approval policy. Set the default for new sessions in `~\u002F.dsh\u002Fsettings.yaml`:\n\n```yaml\npermission:\n  defaultPreset: workspace-write\n```\n\nSwitch the policy for the current session with the `\u002Fpermission` command.\n","# Automation Recommender\n\nAnalyze codebase patterns to recommend tailored DeepSeek Harness automations across all extensibility options.\n\n**This skill is read-only.** It analyzes the codebase and outputs recommendations. It does NOT create or modify any files. Users implement the recommendations themselves or ask the agent separately to help build them.\n\n## Output Guidelines\n\n- **Recommend 1-2 of each type**: Don't overwhelm - surface the top 1-2 most valuable automations per category\n- **If user asks for a specific type**: Focus only on that type and provide more options (3-5 recommendations)\n- **Go beyond the reference lists**: The reference files contain common patterns, but use web search to find recommendations specific to the codebase's tools, frameworks, and libraries\n- **Tell users they can ask for more**: End by noting they can request more recommendations for any specific category\n\n## Automation Types Overview\n\n| Type | Best For |\n|------|----------|\n| **Hooks** | Automatic actions on tool events (format on save, lint, block edits) |\n| **Subagents** | Specialized reviewers\u002Fanalyzers that run in parallel |\n| **Skills** | Packaged expertise, workflows, and repeatable tasks (invoked by the agent or user via `\u002Fskill-name`) |\n| **Plugins** | Collections of skills that can be installed |\n| **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) |\n\n## Workflow\n\n### Phase 1: Codebase Analysis\n\nGather project context:\n\n```bash\n# Detect project type and tools\nls -la package.json pyproject.toml Cargo.toml go.mod pom.xml 2>\u002Fdev\u002Fnull\ncat package.json 2>\u002Fdev\u002Fnull | head -50\n\n# Check dependencies for MCP server recommendations\ncat package.json 2>\u002Fdev\u002Fnull | grep -E '\"(react|vue|angular|next|express|fastapi|django|prisma|supabase|convex|stripe)\"'\n\n# Check for existing DeepSeek Harness config\nls -la .agents\u002F AGENTS.md 2>\u002Fdev\u002Fnull\n\n# Analyze project structure\nls -la src\u002F app\u002F lib\u002F tests\u002F components\u002F pages\u002F api\u002F 2>\u002Fdev\u002Fnull\n```\n\n**Key Indicators to Capture:**\n\n| Category | What to Look For | Informs Recommendations For |\n|----------|------------------|----------------------------|\n| Language\u002FFramework | package.json, pyproject.toml, import patterns | Hooks, MCP servers |\n| Frontend stack | React, Vue, Angular, Next.js | Playwright MCP, frontend skills |\n| Backend stack | Express, FastAPI, Django | API documentation tools |\n| Database | Prisma, Supabase, Convex, raw SQL | Database \u002F backend MCP servers |\n| External APIs | Stripe, OpenAI, AWS SDKs | context7 MCP for docs |\n| Testing | Jest, pytest, Playwright configs | Testing hooks, subagents |\n| CI\u002FCD | GitHub Actions, CircleCI | GitHub MCP server |\n| Issue tracking | Linear, Jira references | Issue tracker MCP |\n| Docs patterns | OpenAPI, JSDoc, docstrings | Documentation skills |\n\n### Phase 2: Generate Recommendations\n\nBased on analysis, generate recommendations across all categories:\n\n#### A. MCP Server Recommendations\n\nSee [references\u002Fmcp-servers.md](references\u002Fmcp-servers.md) for detailed patterns.\n\n| Codebase Signal | Recommended MCP Server |\n|-----------------|------------------------|\n| Uses popular libraries (React, Express, etc.) | **context7** - Live documentation lookup |\n| Frontend with UI testing needs | **Playwright** - Browser automation\u002Ftesting |\n| Uses Supabase | **Supabase MCP** - Direct database operations |\n| Uses Convex | **Convex MCP** - Live deployment introspection, run queries\u002Fmutations, manage env vars and logs |\n| PostgreSQL\u002FMySQL database | **Database MCP** - Query and schema tools |\n| GitHub repository | **GitHub MCP** - Issues, PRs, actions |\n| Uses Linear for issues | **Linear MCP** - Issue management |\n| AWS infrastructure | **AWS MCP** - Cloud resource management |\n| Slack workspace | **Slack MCP** - Team notifications |\n| Memory\u002Fcontext persistence | **Memory MCP** - Cross-session memory |\n| Sentry error tracking | **Sentry MCP** - Error investigation |\n| Docker containers | **Docker MCP** - Container management |\n\n#### B. Skills Recommendations\n\nSee [references\u002Fskills-reference.md](references\u002Fskills-reference.md) for details.\n\nCreate skills in `.agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md` and commands in `.agents\u002Fcommands\u002F\u003Cname>.md`; the project contributes both only while the market plugin's project-layout scan is on. Some are also available via plugins:\n\n| Codebase Signal | Skill | Plugin |\n|-----------------|-------|--------|\n| Building plugins | skill-development | plugin-dev |\n| Git commits | commit | commit-commands |\n| React\u002FVue\u002FAngular | frontend-design | frontend-design |\n| Automation rules | writing-rules | hookify |\n| Feature planning | feature-dev | feature-dev |\n\n**Custom skills to create** (with templates, scripts, examples):\n\n| Codebase Signal | Skill to Create | Invocation |\n|-----------------|-----------------|------------|\n| API routes | **api-doc** (with OpenAPI template) | Both |\n| Database project | **create-migration** (with validation script) | User-only |\n| Test suite | **gen-test** (with example tests) | User-only |\n| Component library | **new-component** (with templates) | User-only |\n| PR workflow | **pr-check** (with checklist) | User-only |\n| Releases | **release-notes** (with git context) | User-only |\n| Code style | **project-conventions** | Model-only |\n| Onboarding | **setup-dev** (with prereq script) | User-only |\n\n#### C. Hooks Recommendations\n\nSee [references\u002Fhooks-patterns.md](references\u002Fhooks-patterns.md) for configurations.\n\n| Codebase Signal | Recommended Hook |\n|-----------------|------------------|\n| Prettier configured | PostToolUse: auto-format on edit |\n| ESLint\u002FRuff configured | PostToolUse: auto-lint on edit |\n| TypeScript project | PostToolUse: type-check on edit |\n| Tests directory exists | PostToolUse: run related tests |\n| `.env` files present | PreToolUse: block `.env` edits |\n| Lock files present | PreToolUse: block lock file edits |\n| Security-sensitive code | PreToolUse: require confirmation |\n\n#### D. Subagent Recommendations\n\nSee [references\u002Fsubagent-templates.md](references\u002Fsubagent-templates.md) for templates. Subagents are agent role cards under the plugin's `com.deepseek.harness\u002Fagents\u002F` or the project's `.agents\u002Fagents\u002F`, delegated to with `subagent_run`.\n\n| Codebase Signal | Recommended Subagent |\n|-----------------|---------------------|\n| Large codebase (>500 files) | **code-reviewer** - Parallel code review |\n| Auth\u002Fpayments code | **security-reviewer** - Security audits |\n| API project | **api-documenter** - OpenAPI generation |\n| Performance critical | **performance-analyzer** - Bottleneck detection |\n| Frontend heavy | **ui-reviewer** - Accessibility review |\n| Needs more tests | **test-writer** - Test generation |\n\n#### E. Plugin Recommendations\n\nSee [references\u002Fplugins-reference.md](references\u002Fplugins-reference.md) for available plugins.\n\n| Codebase Signal | Recommended Plugin |\n|-----------------|-------------------|\n| General productivity | **agent-skills** - Core skills bundle |\n| Document workflows | Install docx, xlsx, pdf skills |\n| Frontend development | **frontend-design** plugin |\n| Building AI tools | **mcp-builder** for MCP development |\n\n### Phase 3: Output Recommendations Report\n\nFormat recommendations clearly. **Only include 1-2 recommendations per category** - the most valuable ones for this specific codebase. Skip categories that aren't relevant.\n\n```markdown\n## DeepSeek Harness Automation Recommendations\n\nI've analyzed your codebase and identified the top automations for each category. Here are my top 1-2 recommendations per type:\n\n### Codebase Profile\n- **Type**: [detected language\u002Fruntime]\n- **Framework**: [detected framework]\n- **Key Libraries**: [relevant libraries detected]\n\n---\n\n### 🔌 MCP Servers\n\n#### context7\n**Why**: [specific reason based on detected libraries]\n**Configure**: add it to `.agents\u002Fmcp.json`\n\n---\n\n### 🎯 Skills\n\n#### [skill name]\n**Why**: [specific reason]\n**Create**: `.agents\u002Fskills\u002F[name]\u002FSKILL.md`\n**Invocation**: User-only \u002F Both \u002F Model-only\n**Also available in**: [plugin-name] plugin (if applicable)\n```yaml\n---\nname: [skill-name]\ndescription: [what it does]\ndisable-model-invocation: true  # for user-only\n---\n```\n\n---\n\n### ⚡ Hooks\n\n#### [hook name]\n**Why**: [specific reason based on detected config]\n**Where**: `.agents\u002Fhooks\u002Fhooks.json`\n\n---\n\n### 🤖 Subagents\n\n#### [agent name]\n**Why**: [specific reason based on codebase patterns]\n**Where**: `.agents\u002Fagents\u002F[name].md`\n\n---\n\n**Want more?** Ask for additional recommendations for any specific category (e.g., \"show me more MCP server options\" or \"what other hooks would help?\").\n\n**Want help implementing any of these?** Just ask and I can help you set up any of the recommendations above.\n```\n\n## Decision Framework\n\n### When to Recommend MCP Servers\n- External service integration needed (databases, APIs)\n- Documentation lookup for libraries\u002FSDKs\n- Browser automation or testing\n- Team tool integration (GitHub, Linear, Slack)\n- Cloud infrastructure management\n\n### When to Recommend Skills\n\n- Document generation (docx, xlsx, pptx, pdf — also in plugins)\n- Frequently repeated prompts or workflows\n- Project-specific tasks with arguments\n- Applying templates or scripts to tasks (skills can bundle supporting files)\n- Quick actions invoked with `\u002Fskill-name`\n- Workflows whose heavy work should stay out of the main context — the skill body delegates to an agent role card with `subagent_run`\n\n**Invocation control:**\n- `disable-model-invocation: true` — User-only (for side effects: deploy, commit, send)\n- `user-invocable: false` — Model-only (for background knowledge)\n- Default (omit both) — Both can invoke\n\n### When to Recommend Hooks\n- Repetitive post-edit actions (formatting, linting)\n- Protection rules (block sensitive file edits)\n- Validation checks (tests, type checks)\n\n### When to Recommend Subagents\n- Specialized expertise needed (security, performance)\n- Parallel review workflows\n- Background quality checks\n\n### When to Recommend Plugins\n- Need multiple related skills\n- Want pre-packaged automation bundles\n- Team-wide standardization\n\n---\n\n## Configuration Tips\n\n### MCP Server Setup\n\nMCP servers are declared in a plugin's `mcp.json` or the project's `.agents\u002Fmcp.json`.\n\n**Team sharing**: Check `.agents\u002Fmcp.json` into repo so entire team gets same MCP servers\n\n**Debugging**: The market page's MCP services tab reports each service's status and failures\n\n**Prerequisites to recommend:**\n- GitHub CLI (`gh`) - enables native GitHub operations\n- Puppeteer\u002FPlaywright CLI - for browser MCP servers\n\n### Headless Mode (for CI\u002FAutomation)\n\nRecommend the headless profile for automated pipelines:\n\n```bash\n# Pre-commit hook example\ndsh --profile headless \"fix lint errors in src\u002F\"\n\n# CI pipeline piping the final message into the next command\ndsh --profile headless \"\u003Cprompt>\" | your_command\n```\n\n### Permissions for Hooks\n\nHook commands run under the session's sandbox and approval policy. Set the default for new sessions in `~\u002F.dsh\u002Fsettings.yaml`:\n\n```yaml\npermission:\n  defaultPreset: workspace-write\n```\n\nSwitch the policy for the current session with the `\u002Fpermission` command.\n",{"name":5,"description":7},"main","8279d7eebf12240ce77d350399cef4923e1338b5","plugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender",2,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fdsh-agent-plugins-market","https:\u002F\u002Fgithub.com\u002FSivan757","It seems like everything is getting better.","2026-11-14 02:00:01",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Sivan757\u002Fdsh-agent-plugins-market --skill automation-recommender",{"tool":38,"command":39},"bunx","bunx skills add Sivan757\u002Fdsh-agent-plugins-market --skill automation-recommender",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Sivan757\u002Fdsh-agent-plugins-market --skill automation-recommender","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fhooks-patterns.md","REFERENCE","参考文档",6439,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002Freferences\u002Fhooks-patterns.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmcp-servers.md",8446,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002Freferences\u002Fmcp-servers.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fplugins-reference.md",3164,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002Freferences\u002Fplugins-reference.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fskills-reference.md",9958,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002Freferences\u002Fskills-reference.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fsubagent-templates.md",5351,"https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fautomation-recommender\u002Freferences\u002Fsubagent-templates.md",[69,76,83,91,98,105],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M7ATFYMAYZDJENQA7NK1DS6Q","verify","Verify that a code change actually does what it's supposed to by running the app and observing behavior. Use when asked to verify a PR, confirm a fix works, test a change manually, check that a feature works, or validate local changes before pushing.","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7ATFVE6NHZ1J2R2DJF07GCD","simplify","Review changed code for reuse, quality, and efficiency, then fix any issues found. Use when the user asks to \"simplify the code\", \"clean up the diff\", \"reduce duplication in my changes\", or after finishing a feature before committing.","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fsimplify\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7ATFR42EZW03GMFJ9C5ZXW7","insight","Analyze this machine's DeepSeek Harness session history and report how sessions actually go — operating style, what works, friction points, and what to try next. Use when the user asks \"how have I been using this\", \"analyze my sessions\", \"make an insight report\", or wants a retrospective.","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Finsight\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Finsight\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M7ATFHC1A2XTHYYFYCEBFDPA","init","Set up a minimal AGENTS.md (and optionally skills and hooks) for this repo. Use when the user asks to \"initialize the project\", \"generate AGENTS.md\", \"set up project instructions\", or runs \u002Finit.","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Finit\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M7ATFCNSJKCZG98P0N2CX15J","explore","Fast read-only codebase exploration that returns a report instead of filling the main context. Use when the user asks to \"explore the codebase\", \"find where X is handled\", \"how does Y work\", or when a search would take many reads to answer.","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fexplore\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M7ATF3Y98DT74ZTRGYASJB46","agents-md-audit","Audit and improve AGENTS.md files in repositories. Use when user asks to check, audit, update, improve, or fix AGENTS.md files. Scans for all AGENTS.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions \"AGENTS.md maintenance\" or \"project memory optimization\".","https:\u002F\u002Fgithub.com\u002FSivan757\u002Fdsh-agent-plugins-market\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit\u002Fskills\u002Fagents-md-audit\u002FSKILL.md",[],[]]