dispatching-agent-teams

Name: dispatching-agent-teams
Author: krzysztofsurdy

12installs1forks

How to install dispatching-agent-teams?

krzysztofsurdy/code-virtuoso/dispatching-agent-teams

$npx -y skills add krzysztofsurdy/code-virtuoso --skill dispatching-agent-teams

Installs into the current project.

Summary

Spawn and coordinate a pre-composed agent team from a team definition file. Reads team files from teams/, resolves agents and skills, picks the best spawning mode (peer or sequential), and runs the workflow. Use when the user asks to run a team, dispatch a development team, start

Files · 1

View on GitHub

SKILL.md

1	# Dispatching Agent Teams
2
3	Read a team definition file, resolve its agents and skills, and execute the coordination protocol. The team file is the recipe - this skill is the cook.
4
5	## Core Principles
6
7	\| Principle \| Meaning \|
8	\|---\|---\|
9	\| Team file is the contract \| Follow the workflow, entry/exit criteria, and coordination rules defined in the team file. Do not improvise the process. \|
10	\| Detect capabilities first \| Check what spawning mode the platform supports before dispatching. Peer mode if available, sequential fallback otherwise. \|
11	\| Skills before agents \| Preload the team's bundled skills before spawning any agent. Agents need their reference material from the start. \|
12	\| Respect coordination rules \| If the team file says "Architect must approve before implementation starts", enforce it. Do not skip gates. \|
13	\| Fail early, not late \| If a required agent is not installed, stop before dispatching. Do not discover missing agents mid-workflow. \|
14
15	---
16
17	## Workflow
18
19	### Phase 1: Resolve the Team
20
21	Teams are discovered from two locations in this order:
22
23	1. Project teams - `teams/{name}.md` at the user's project root (user-authored teams)
24	2. Library teams - bundled with the `agent-teams` skill at `skills/tools/agent-teams/teams/{name}.md` (or wherever the agent-teams skill is installed)
25
26	Resolution:
27
28	1. If the user provided a team name as argument, search project teams first, then the library. Project teams override library teams when names collide.
29	2. If no argument, scan both locations and present a selection menu showing which are library teams vs project teams.
30	3. Read the team file's YAML frontmatter: `name`, `lead`, `agents`, `skills`, `workflow`.
31	4. Verify every agent in the `agents` list exists as an installed agent definition.
32	5. Verify every skill in the `skills` list exists as an installed skill.
33	6. If any agent or skill is missing, report what is missing and stop. Do not proceed with a partial team.
34
35	### Team Library
36
37	The `agent-teams` skill catalogs the available pre-composed teams (development-team, review-squad, war-room) with their purpose and use cases. To browse what is available before dispatching, consult that skill first.
38
39	To author your own team, see [spec/team-spec.md](../../../spec/team-spec.md) and place the file at the project root's `teams/{name}.md`.
40
41	### Phase 2: Verify Entry Criteria
42
43	1. Read the team file's "Entry Criteria" section.
44	2. Check each criterion against the current state (e.g., "ticket exists", "CI is green", "stakeholder available").
45	3. If a criterion cannot be verified automatically, ask the user to confirm it.
46	4. Do not proceed until all entry criteria are met or explicitly waived by the user.
47
48	### Phase 3: Preload Skills
49
50	Load the skills listed in the team's `skills` frontmatter. These provide reference material that agents will need during their work (e.g., testing patterns, API design principles, verification checklists).
51
52	### Phase 4: Detect Spawning Mode and Workflow Variants
53
54	Check what the current platform supports:
55
56	\| Capability \| Detection \| Mode \|
57	\|---\|---\|---\|
58	\| Platform supports agent teams with peer messaging and shared task lists \| Team creation tools are available \| Peer mode \|
59	\| Platform supports sub-agent spawning but no peer messaging \| Agent delegation tools are available \| Sequential mode \|
60	\| Neither \| No delegation support \| Inline mode - lead executes all phases in the current session \|
61
62	Then check the team's `workflow` type for special handling:
63
64	\| Workflow \| Special protocol \|
65	\|---\|---\|
66	\| `parallel` \| Check Coordination Rules for per-agent context restrictions. If present, build differential briefs per agent (see [spawning-protocol](references/spawning-protocol.md)). \|
67	\| `war-room` \| Use multi-pass rounds: position round, then challenge round, then synthesis. Agents respond with perspective only - no tool use during the debate (see [spawning-protocol](references/spawning-protocol.md)). \|
68	\| `sequential`, `hybrid` \| Standard protocol. \|
69
70	### Phase 5: Dispatch
71
72	#### Peer Mode
73
74	1. Create a team with the lead agent as coordinator.
75	2. Add all other agents as teammates.
76	3. Create shared tasks matching the workflow phases from the team file.
77	4. Set task dependencies based on the workflow order (e.g., "Implementation" is blocked by "Design").
78	5. The lead assigns the first unblocked task. Teammates claim tasks as they unblock.
79	6. Teammates message each other for clarifications as described in the coordination rules.
80
81	#### Sequential Mode
82
83	1. The lead agent runs in t

People who liked this also viewed

6 picks

Type

dispatching-agent-teams

12installs1forks

View on GitHub

How to install dispatching-agent-teams?

krzysztofsurdy/code-virtuoso/dispatching-agent-teams

$npx -y skills add krzysztofsurdy/code-virtuoso --skill dispatching-agent-teams

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Dispatching Agent Teams
2
3	Read a team definition file, resolve its agents and skills, and execute the coordination protocol. The team file is the recipe - this skill is the cook.
4
5	## Core Principles
6
7	\| Principle \| Meaning \|
8	\|---\|---\|
9	\| Team file is the contract \| Follow the workflow, entry/exit criteria, and coordination rules defined in the team file. Do not improvise the process. \|
10	\| Detect capabilities first \| Check what spawning mode the platform supports before dispatching. Peer mode if available, sequential fallback otherwise. \|
11	\| Skills before agents \| Preload the team's bundled skills before spawning any agent. Agents need their reference material from the start. \|
12	\| Respect coordination rules \| If the team file says "Architect must approve before implementation starts", enforce it. Do not skip gates. \|
13	\| Fail early, not late \| If a required agent is not installed, stop before dispatching. Do not discover missing agents mid-workflow. \|
14
15	---
16
17	## Workflow
18
19	### Phase 1: Resolve the Team
20
21	Teams are discovered from two locations in this order:
22
23	1. Project teams - `teams/{name}.md` at the user's project root (user-authored teams)
24	2. Library teams - bundled with the `agent-teams` skill at `skills/tools/agent-teams/teams/{name}.md` (or wherever the agent-teams skill is installed)
25
26	Resolution:
27
28	1. If the user provided a team name as argument, search project teams first, then the library. Project teams override library teams when names collide.
29	2. If no argument, scan both locations and present a selection menu showing which are library teams vs project teams.
30	3. Read the team file's YAML frontmatter: `name`, `lead`, `agents`, `skills`, `workflow`.
31	4. Verify every agent in the `agents` list exists as an installed agent definition.
32	5. Verify every skill in the `skills` list exists as an installed skill.
33	6. If any agent or skill is missing, report what is missing and stop. Do not proceed with a partial team.
34
35	### Team Library
36
37	The `agent-teams` skill catalogs the available pre-composed teams (development-team, review-squad, war-room) with their purpose and use cases. To browse what is available before dispatching, consult that skill first.
38
39	To author your own team, see [spec/team-spec.md](../../../spec/team-spec.md) and place the file at the project root's `teams/{name}.md`.
40
41	### Phase 2: Verify Entry Criteria
42
43	1. Read the team file's "Entry Criteria" section.
44	2. Check each criterion against the current state (e.g., "ticket exists", "CI is green", "stakeholder available").
45	3. If a criterion cannot be verified automatically, ask the user to confirm it.
46	4. Do not proceed until all entry criteria are met or explicitly waived by the user.
47
48	### Phase 3: Preload Skills
49
50	Load the skills listed in the team's `skills` frontmatter. These provide reference material that agents will need during their work (e.g., testing patterns, API design principles, verification checklists).
51
52	### Phase 4: Detect Spawning Mode and Workflow Variants
53
54	Check what the current platform supports:
55
56	\| Capability \| Detection \| Mode \|
57	\|---\|---\|---\|
58	\| Platform supports agent teams with peer messaging and shared task lists \| Team creation tools are available \| Peer mode \|
59	\| Platform supports sub-agent spawning but no peer messaging \| Agent delegation tools are available \| Sequential mode \|
60	\| Neither \| No delegation support \| Inline mode - lead executes all phases in the current session \|
61
62	Then check the team's `workflow` type for special handling:
63
64	\| Workflow \| Special protocol \|
65	\|---\|---\|
66	\| `parallel` \| Check Coordination Rules for per-agent context restrictions. If present, build differential briefs per agent (see [spawning-protocol](references/spawning-protocol.md)). \|
67	\| `war-room` \| Use multi-pass rounds: position round, then challenge round, then synthesis. Agents respond with perspective only - no tool use during the debate (see [spawning-protocol](references/spawning-protocol.md)). \|
68	\| `sequential`, `hybrid` \| Standard protocol. \|
69
70	### Phase 5: Dispatch
71
72	#### Peer Mode
73
74	1. Create a team with the lead agent as coordinator.
75	2. Add all other agents as teammates.
76	3. Create shared tasks matching the workflow phases from the team file.
77	4. Set task dependencies based on the workflow order (e.g., "Implementation" is blocked by "Design").
78	5. The lead assigns the first unblocked task. Teammates claim tasks as they unblock.
79	6. Teammates message each other for clarifications as described in the coordination rules.
80
81	#### Sequential Mode
82
83	1. The lead agent runs in t

People who liked this also viewed

6 picks

Type