A guide to finding, checking, installing, updating, and removing community extensions for DeepSeek Harness (dsh), an AI coding-agent framework. It covers plugins distributed through GitHub topics, npm packages, directories, bundles, tarballs, and a graphical interface.
Advisor-orchestrated in-session build loop. The session model (the strongest model you have, or a new SOTA model you want to evaluate) acts as planner + advisor + reviewer; implementation is delegated to cheaper subagent models. Derives a verifiable completion condition up front and interviews the user if one can't be…
Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing…
Transform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Use when the user wants to prepare project-specific context engineering documents, AI coding agent instruction files, project starter Markdown files, vibe coding guardrails, PRD/TDD/architecture/security/testing docs, AGENTS.md/CLAUDE.md/Cursor/Windsurf/Continue/Copilot context files, or a complete AI-coding-ready…
Review database migrations and schema changes for safety — reversibility, lock duration, online-vs-offline behavior, batch-size on backfills, tenant isolation, RLS policies (Supabase), idempotence, audit-log impact. Use this skill on any PR that touches migrations/, supabase/migrations/, .sql, schema files…
Use this skill when modifying AI agents, skills, prompts, commands, hooks, instructions, MCP configuration, or platform-specific AI customization files.
Use when: creating, refactoring, auditing, upgrading, or debugging Copilot custom agents, skills, instructions, prompts, or hooks for Apple platform software engineering and agile delivery workflows.
The full doc is 430 lines, but you only need to paste this section (70 lines) into an agent's system prompt for 95% of requests to route correctly. Everything below it is edge-case reference for the routing layer's authors.
Use Ragmir for local-first retrieval from private project documents, document ingestion, knowledge-base audits, or MCP access to a repository corpus. Prefer it to memory when the answer may be in local documents.
Search the live web through the agent-web-search CLI — powered by model-native search grounding and agent search backends. Optimized for complete natural-language questions rather than keyword fragments when online sources or cross-provider web research are needed.
Generate and incrementally maintain an interactive architecture map plus a per-module code-quality audit (health scores 0-100, smell findings, lines-of-code, and a clickable dependency graph) for any codebase. Use when the user wants to visualize a project's functional modules, audit or score code quality, check…
Use Bipa CLI to make Pix payments, check balances, analyze transaction history, and decode BR codes for AI agents. MUST use this skill whenever the user mentions paying someone via Pix, checking their balance, reviewing transactions, scanning a Pix QR code, setting up Bipa CLI, or asks the agent to handle any…
Use at a specflo project's execute phase, when turning a validated plan.md into committed, verified code one task at a time. Triggers include "execute the plan", "start building", "work the next task", or specflo status showing the execute phase. Do NOT use before a plan has been validated, or for trivial fixes…
Create an implementation plan — discovery in the real codebase first, then a plan document with verified code anchors, spec impact, and dependencies, filed under Active in the plans hub. Use when the user says "plan ", "write a plan for ...", or asks to turn a backlog task or accepted feature into work.
Use when the user wants to create or edit an ArchAstro agent's config files before deployment, including AgentTemplate files, Script configs, custom tools, routines, and environment setup. Trigger phrases include "build this agent", "write the template", "create the scripts", "set up the routines", "author this agent…
Preview images, video, PDFs, code files, diffs, and tweets from inside an agent CLI that cannot render them. Use when the user asks to see, view, preview, show, or look at a file — screenshots, generated images, charts, mockups, video clips, PDFs, or a code diff — or says "show me", "let me see it", "preview that"…
Query this repo's code graph instead of ls/grep/reading files blindly. Use whenever you are understanding the codebase or its architecture, tracing how something works, or searching for a symbol or term; before changing a symbol, to get its blast radius (dependent symbols, tests to run, API surface, and other indexed…
★not rated 6 8d agoA151 tokens
EUPL-1.2
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: