rad-orchestration
Multi-agent orchestration for Radicle plans — worktree isolation, task dispatch, CLAIM/SIGNAL conventions, and context feedback loops. Use when dispatching tasks to workers, launching worktree agents, or evaluating multi-agent progress.
What this skill does
# Radicle Orchestration Orchestration conventions for multi-agent parallel execution using Plan COBs as the coordination layer and git worktrees for isolation. ## Model One plan drives the work. Each task is executed by a worker agent in an isolated git worktree. Workers produce one commit and one Context COB per task. The plan-manager dispatches tasks and evaluates feedback between batches. ## Task Readiness A task is **ready** when: 1. It has no `linkedCommit` (not done) 2. No CLAIM comment exists for it (not in progress) 3. All `blocked_by` tasks have `linkedCommit` (dependencies met) 4. Its `affectedFiles` don't overlap with any in-progress task's files (no conflict) ## CLAIM/SIGNAL Protocol - **CLAIM**: Worker posts `CLAIM task:<task-id>` as a plan comment before starting work - **SIGNAL**: Worker posts `SIGNAL task:<task-id> files-added:<paths>` if modifying files beyond the original `affectedFiles`, and updates the task via `rad-plan task edit <plan-id> <task-id> --files "<updated-list>"` These are conventions, not locks. The plan-manager is the sole dispatcher — workers do not self-select tasks. ## Dispatch Flow 1. Read plan state: `rad-plan show <plan-id> --json` 2. Categorize tasks: Completed / In Progress / Ready / Blocked (dependency) / Blocked (file conflict) 3. Check SIGNAL comments for expanded file scopes 4. Load Context COBs from recently completed tasks for feedback 5. Output structured dispatch report with ready tasks and context warnings ## Worker Lifecycle 1. Claim task (plan comment) 2. Read assignment (plan JSON + linked issue) 3. Load prior Context COBs (by plan, task, or file overlap) 4. Implement the change (one logical commit) 5. Create Context COB (reflect on session, run verification) 6. Link Context COB to plan, issue, commit 7. Mark done: `rad-plan task link-commit <plan-id> <task-id> --commit <oid>` 8. Announce: `rad sync --announce` ## Context Feedback Evaluation Between dispatch batches, evaluate completed workers' contexts: | Context Field | Signal | |---|---| | `constraints` conflicting with later tasks | Assumption clash — flag it | | `friction` relevant to upcoming tasks' files | Same pitfall ahead — warn | | `openItems` suggesting new scope | Discovered work — suggest new task | | `filesTouched` outside `affectedFiles` | Unexpected file changes — re-check conflicts | | `verification` failures | Check didn't pass — consider blocking dependents | ## Plan Completion When all tasks have `linkedCommit`: - Set plan status: `rad-plan status <plan-id> completed` - Close linked issue: `rad issue state <issue-id> --closed` - Announce: `rad sync --announce`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.