integrations
Show MCP integration status. Use when: checking active connectors, available integrations, or skill unlocks.
652 repo starsObserved in 2 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
loop-execution
Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.
652 repo starsObserved in 2 repos
Agent Building
memory-clean
Use when the user explicitly asks to clean, compact, prune, trim, deduplicate, optimize, or reduce Wingman memory, or asks to resolve stale or conflicting memory rules.
652 repo starsObserved in 2 repos
Agent Building
reviewer_configure-review
Configure or update a repo's .review.yml context layer (subsystem cluster depth, per-prefix depth overrides, summary top-k threshold, ignore for noisy *tracked* paths, context_limits retrieval breadth per repo profile) and its task board selection (which board this repo uses — yougile/youtrack — key_pattern, url_template; never credentials) from a draft the skill generates and the user edits. Use when the user asks to set up or tune review config ("настроить .review.yml", "configure review config", "настрой контекст-слой", "tune cluster depth", "что игнорировать в ревью", "выбрать доску для репо", "set up reviewer for this repo"). Standalone baseline — needs only git, no reviewer MCP / DB required; optionally uses the reviewer MCP tool count_tasks to size context_limits.search_tasks.
652 repo starsObserved in 2 repos
Agent Building
reviewer_sync-codebase
Build or update the reviewer base index (vector store + code graph) from a local repo clone. Use when the user asks to "index the codebase", "build the index", "sync the code", "rebuild the graph", "просиндексируй код", "построй индекс".
652 repo starsObserved in 2 repos
Agent Building
river-review
River Review のメインエントリポイント。 レビュー依頼の intent classification → 専門 skill 選択 → 実行 → finding verification → feedback classification → fixture / reference / suppression への還元までを束ねる improvement-loop orchestrator。
652 repo starsObserved in 2 repos
Agent Building
runtype-persona
Use when embedding, deploying, configuring, styling, or debugging Runtype Persona chat widgets, fullscreen AI assistant layouts, chat surfaces, client-token installs, theme tokens, artifacts, tool/reasoning visibility, programmatic widget access, WebMCP page tools, or browser-side local tools. Prefer generate_persona_embed_code and get_persona_theme_reference over hand-written snippets.
652 repo starsObserved in 2 repos
Agent Building
subagent-execution
Delegated step runner over the HOTL execution state machine — delegates eligible steps to fresh subagents while the controller keeps governance, verification, and stop conditions.
652 repo starsObserved in 2 repos
Agent Building
using-hotl
Use when the user explicitly asks for HOTL routing or needs guidance choosing the right HOTL workflow skill.
652 repo starsObserved in 2 repos
Agent Building
agent-introspection
Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.
652 repo starsObserved in 1 repos
Agent Building