orchestrating-agent-work
/orchestrating-agent-work
Analizuje złożone zadanie inżynierskie, przeprowadza wywiad diagnostyczny, wybiera strategię wykonania (DAG lub pętla), planuje artefakt oraz nadzoruje wykonanie i weryfikację.
- Autor
- richfrem ↗
- Repozytorium
- agent-plugins-skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 24.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 44
- Skrypty
- 13
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 24.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 13 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: scripts/agent_orchestrator.py, scripts/graph_runner.py, scripts/select_strategy.py, scripts/swarm_run.py, scripts/validate_manifest.py, tests/test_graph_fixes.py, tests/test_graph_runner.py, tests/test_isolation.py
Co robi i kiedy
Analizuje złożone zadanie inżynierskie, przeprowadza wywiad diagnostyczny, wybiera strategię wykonania (DAG lub pętla), planuje artefakt oraz nadzoruje wykonanie i weryfikację.
Wyzwalacze z opisu
Oryginalny opis (EN)
Interactive orchestrator for complex engineering work. Analyzes the task, conducts a diagnostic interview to select the appropriate execution strategy (Directed Acyclic Graph versus Loop, and which Loop type), plans the artifact, and supervises execution and verification. Use for "how should I orchestrate this", "plan this workflow", "should this be a DAG or a loop", "run these jobs in parallel", "delegate this to a worker agent", or "run/resume this graph manifest". Not for single trivial edits or skill self-improvement.
Jak działa
- Contents
- Dependencies
- Constraints
- Quick Start
- Workflow
- Strategies
- Verification
- References
Podgląd SKILL.md
--- name: orchestrating-agent-work plugin: agent-orchestration description: > Interactive orchestrator for complex engineering work. Analyzes the task, conducts a diagnostic interview to select the appropriate execution strategy (Directed Acyclic Graph versus Loop, and which Loop type), plans the artifact, and supervises execution and verification. Use for "how should I orchestrate this", "plan this workflow", "should this be a DAG or a loop", "run these jobs in parallel", "delegate this to a worker agent", or "run/resume this graph manifest". Not for single trivial edits or skill self-improvement. allowed-tools: Bash, Read, Write, Glob, Grep --- # Orchestrating Agent Work (`orchestrating-agent-work`) Interactive front door: analyze the task, conduct diagnostic interview, select Graph vs. Loop, plan, execute, and verify. ## Contents - [Dependencies](#dependencies) • [Constraints](#constraints) • [Quick Start](#quick-start) • [Workflow](#workflow) • [Strategies](#strategies) • [Verification](#verification) • [References](#references) ## Dependencies Requires Python 3.8+ (standard library only). ## Constraints - **Interactive Confirmation**: Ask at most 3 questions (one per turn) for ambiguous dimensions; present structured choices with `Option A [Recommended]`; human confirms or overrides selection before planning. - **Topology First (Graph vs. Loop)**: Choose Graph (DAG) for distinct steps, parallel fan-out reads, or ordering barriers; choose Loop for iterative delegation. - **Trust but Verify**: Never accept worker output without running automated test suites and auditing the git diff. - **Loop Isolation**: Inner execution loops are strictly forbidden from running `git` write commands (commits and merges stay with caller). - **Confinement & Redirection**: Workspace mutations run in an isolated worktree; background CLI calls redirect stdin (`< /dev/null`). - **Human Gate Integrity**: Graph runs with `--approval none` require an explicit human-approved manifest SHA; never self-sign manifests you wrote. ## Quick Start ```bash python3 scripts/select_strategy.py --out docs/plans/work-tasks/<task-id>/ python3 scripts/validate_manifest.py graph-manifest.json python3 scripts/graph_runner.py graph-manifest.json --worktree .worktrees/task-<id> --approval prompt ``` ## Workflow 1. **Analyze**: Ingest requirements, evaluate dependency structure, ordering barriers, concurrency, and risk ([routing-and-closure.md](references/routing-and-closure.md)). 2. **Interview & Select**: Ask 1–3 structured questions; run `select_strategy.py`; present **Graph (DAG)** vs **Loop** (Dual-Loop vs Swarm); confirm human agreement ([strategy-selection.md](references/strategy-selection.md)). 3. **Plan**: - **Graph (DAG)**: Compile and validate `graph-manifest.json` ([graph-planning.md](references/graph-planning.md), [topology-rules.md](references/topology-rules.md)). - **Dual-Loop**: Author `handoffs/task_packet_<id>.md` with atomic scope and "NO GIT" rule ([strategy-dual-loop.md](references/strategy-dual-loop.md)). - **Parallel Swarm**: Partition tasks into independent units; author `<id>.job.md` ([strategy-agent-swarm.md](references/strategy-agent-swarm.md)). 4. **Execute**: - **Graph**: Run state machine via `graph_runner.py` with worktree isolation and rollback ([graph-execution.md](references/graph-execution.md)). - **Dual-Loop**: Dispatch tactical coding worker into isolated worktree with stdin redirection (`< /dev/null`). - **Parallel Swarm**: Run `swarm_run.py` with resume support. 5. **Verify & Close**: Run test suites, audit diffs (`agent_orchestrator.py verify`), and complete retrospective survey before completion. ## Strategies | Strategy | When to Choose | Plan Artifact | Reference | |---|---|---|---| | `direct` | Minimal localized edit without sub-agent overhead | Implementation plan | [routing-and-closure.md](references/routing-and-closure.md) | | `graph` | Distinct dependent steps, parallel fan-out reads, join barriers, ordered mutations | `graph-manifest.json` | [graph-planning.md](references/graph-planning.md), [graph-execution.md](references/graph-execution.md) | | `dual-loop` | One bounded task; outer supervisor orchestrates tactical inner worker | `handoffs/task_packet_<id>.md` | [strategy-dual-loop.md](references/strategy-dual-loop.md) | | `agent-swarm` | Many identical independent tasks partitioned across bulk files or items | `<id>.job.md` | [strategy-agent-swarm.md](references/strategy-agent-swarm.md) | ## Verification ```bash python3 scripts/agent_orchestrator.py verify --packet handoffs/task_packet_<id>.md --worktree . cat "$(git rev-parse --git-common-dir)/graph-run/<graph_id>/<run_id>/state.json" ``` Consult matching section in [acceptance-criteria.md](references/acceptance-criteria.md); on failure use [fallback-tree.md](references/fallback-tree.md). ## References - Steps: [routing-and-closure.md](references/routing-and-closure.md) • [strategy-selection.md](references/strategy-selection.md) • [graph-planning.md](references/graph-planning.md) • [graph-execution.md](references/graph-execution.md) • [delegated-dag-refactoring-playbook.md](references/delegated-dag-refactoring-playbook.md) - Strategies: [strategy-dual-loop.md](references/strategy-dual-loop.md) • [strategy-agent-swarm.md](references/strategy-agent-swarm.md) - Contracts: [topology-rules.md](references/topology-rules.md) • [graph-manifest-schema.json](references/graph-manifest-schema.json) • [PATTERN_GUIDE.md](references/PATTERN_GUIDE.md) • [patterns.json](references/patterns.json) • [cli-agent-executor.md](references/cli-agent-executor.md) • [cheapest_models.md](references/cheapest_models.md) • [post_run_survey.md](references/post_run_survey.md) - Architecture: [orchestrating_agent_work_architecture.mmd](references/diagrams/orchestrating_agent_work_architecture.mmd) • [acceptance-criteria.md](references/acceptance-criteria.md) • [fallback-tree.md](references/fallback-tree.md)
Pliki w paczce (44)
- SKILL.md 6 KB
- assets/templates/dual-loop-meta-tasks.md 2 KB
- assets/templates/loop_retrospective_template.md 2 KB
- assets/templates/red_team_briefing_template.md 1 KB
- assets/templates/scratchpad-template.md 1 KB
- assets/templates/strategy-packet-template.md 1 KB
- assets/templates/workflow-retrospective-template.md 1 KB
- evals/evals.json 7 KB
- references/PATTERN_GUIDE.md 6 KB
- references/acceptance-criteria.md 7 KB
- references/cheapest_models.json 1 KB
- references/cheapest_models.md 1 KB
- references/cli-agent-executor.md 3 KB
- references/delegated-dag-refactoring-playbook.md 5 KB
- references/fallback-tree.md 10 KB
- references/graph-execution.md 4 KB
- references/graph-manifest-schema.json 7 KB
- references/graph-planning.md 3 KB
- references/patterns.json 2 KB
- references/post_run_survey.md 1 KB
- references/routing-and-closure.md 2 KB
- references/strategy-agent-swarm.md 2 KB
- references/strategy-dual-loop.md 2 KB
- references/strategy-red-team-review.md 2 KB
- references/strategy-selection.md 4 KB
- references/topology-rules.md 6 KB
- references/diagrams/agent_swarm.mmd 2 KB
- references/diagrams/dual_loop_architecture.mmd 1 KB
- references/diagrams/graph-planner-flow.mmd 1 KB
- references/diagrams/graph_execution_state_machine.mmd 1 KB
- references/diagrams/orchestrating_agent_work_architecture.mmd 5 KB
- scripts/agent_orchestrator.py 8 KB
- scripts/graph_runner.py 36 KB
- scripts/select_strategy.py 13 KB
- scripts/swarm_run.py 28 KB
- scripts/validate_manifest.py 20 KB
- tests/test_graph_fixes.py 13 KB
- tests/test_graph_runner.py 30 KB
- tests/test_isolation.py 4 KB
- tests/test_loop_strategies.py 8 KB
- tests/test_select_strategy.py 8 KB
- tests/test_swarm_run.py 9 KB
- tests/test_swarm_run_models.py 3 KB
- tests/test_validate_manifest.py 18 KB
Wersje
W bazie nie ma innych skilli o nazwie orchestrating-agent-work.
Migawka bazy z 13.11.2026 · wersja paczki 656a9c87897f (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100orchestrate
Wykonuje plan z pliku plan.json jako graf DAG z zadaniami równoległymi i sekwencyjnymi, korzystając z natywnego narzędzia Agent Claude bez zewnętrznego silnika. - 100graph
Zamienia zadanie, PRD, SPEC lub zestaw issues w graf zależności (DAG), dzieli go na warstwy i implementuje niezależne węzły równolegle przez subagentów w izolowanych git worktree. - 95agent-skill-orchestrator
Analizuje zadanie, dobiera zasoby, wtyczki i skille z oceną dopasowania oraz tworzy plan wykonania z alternatywami. - 100dag-runtime
Wykonuje przepływy DAG z równoległym przetwarzaniem fal, uruchamianiem agentów, izolacją kontekstu, egzekwowaniem uprawnień i pełnym śladem wykonania. - 100orchestrate
Analizuje zależności zadań, buduje plan wykonania w falach i uruchamia agentów specjalistów równolegle i sekwencyjnie przy złożonych zadaniach obejmujących kilka dziedzin. - 90ralphinho-rfc-pipeline
Dzieli RFC na wieloagentowy graf wykonania: jednostki pracy z zależnościami i testami akceptacyjnymi, badania, planowanie, implementacja, testy i przegląd, a potem scalanie przez kolejkę z weryfikacją systemu.