Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

code-puppy-agent

How Code Puppy itself is built — its internal architecture, structure, codebase layout, and source modules. Explains agents, tools, the plugin/callback hook system, models, MCP, sessions and history/context windows, skills, slash commands, config, messaging/UI, system-prompt assembly, and i18n. Activate for ANY question about how Code Puppy works internally, why it behaves a certain way, where something lives in the code, how a feature is implemented, or how to navigate, debug, or extend the codebase (add a tool, agent, plugin, command, skill, model, or MCP server).

653 repo starsObserved in 1 repos

Agent Building

add-integration

Add MCP server integrations. Use when: connecting a custom tool, API, or service to the plugin via .mcp.json.

652 repo starsObserved in 2 repos

Agent Building

agents-md-improver

Maintain AGENTS.md-based project instructions for tools that support AGENTS.md. Use for instruction audits, session learnings, AGENTS.md updates, or migrating useful CLAUDE.md rules into a shared instruction source. Not for general docs, code review, runtime debugging, or global memory unless asked.

652 repo starsObserved in 2 repos

Agent Building

clean-room-loop

Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room / reverse-engineering / source-to-clean-implementation task hands-off but without paying per-token for `clean-room-skill run`, or says "clean-room as a workflow", "unattended clean-room without API cost", "/clean-room-loop". Runs a short discussion (authorization, end goal, target stack, policies, source roots, output roots, iterations) then launches the `clean-room-loop` workflow with the answers. NOT the enforced OS-level wall - that is `clean-room-skill run --agent-runtime claude`.

652 repo starsObserved in 2 repos

Agent Building

council-verdicts

Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next

652 repo starsObserved in 2 repos

Agent Building

cowork-setup

One-shot setup that wires Digital Marketing Pro for team usage in Anthropic Cowork. Verifies the Cowork sandbox, checks for a Google Drive integration, creates the canonical Drive folder layout, and confirms team-ready brand-state routing. Use this the first time a Cowork user installs DMP OR when brand profiles aren't persisting across sessions.

652 repo starsObserved in 2 repos

Agent Building

eval

Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v1 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.

652 repo starsObserved in 2 repos

Agent Building

eval-config

Configure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.

652 repo starsObserved in 2 repos

Agent Building

governed-execution

Use when executing an accepted HOTL workflow through the best available host or fallback driver.

652 repo starsObserved in 2 repos

Agent Building

honcho-memory

Persistent cross-session memory via Honcho — recall what you know about the user before working, and save durable insights after.

652 repo starsObserved in 2 repos

Agent Building