Skip to content
Skills Library
Programming · Review & audit

multi-agent

/multi-agent

Defines the explicitly parallel variants of ttsc review and issue campaigns. Use only when the user explicitly requests a team, parallel, or multi-agent review or campaign. Route review work to review.md and issue campaigns to issue-campaign.md. Overall Self-Review and unqualified review remain solo; the solo campaign's mandatory Individual Self-Review is a separate narrow subagent workflow. A multi-agent issue campaign differs from the solo campaign only in parallel batch implementation inside its one shared checkout, branch, and cycle pull request.

Licence
Apache-2.0
Last repository change
25.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Defines the explicitly parallel variants of ttsc review and issue campaigns. Use only when the user explicitly requests a team, parallel, or multi-agent review or campaign. Route review work to review.md and issue campaigns to issue-campaign.md. Overall Self-Review and unqualified review remain solo; the solo campaign's mandatory Individual Self-Review is a separate narrow subagent workflow. A multi-agent issue campaign differs from the solo campaign only in parallel batch implementation inside its one shared checkout, branch, and cycle pull request.

Original author description

Defines the explicitly parallel variants of ttsc review and issue campaigns. Use only when the user explicitly requests a team, parallel, or multi-agent review or campaign. Route review work to review.md and issue campaigns to issue-campaign.md. Overall Self-Review and unqualified review remain solo; the solo campaign's mandatory Individual Self-Review is a separate narrow subagent workflow. A multi-agent issue campaign differs from the solo campaign only in parallel batch implementation inside its one shared checkout, branch, and cycle pull request.

How it works

  1. Shared Parallelism Rules
Original SKILL.md headings · 32 lines, 429 words
SKILL.md preview
---
name: multi-agent
description: "Defines the explicitly parallel variants of ttsc review and issue campaigns. Use only when the user explicitly requests a team, parallel, or multi-agent review or campaign. Route review work to review.md and issue campaigns to issue-campaign.md. Overall Self-Review and unqualified review remain solo; the solo campaign's mandatory Individual Self-Review is a separate narrow subagent workflow. A multi-agent issue campaign differs from the solo campaign only in parallel batch implementation inside its one shared checkout, branch, and cycle pull request."
---

# Multi-Agent Workflows

This skill is the single entry point for every explicitly parallel review or campaign. Read the base solo skill first, then enter through the detailed document below for the requested workflow. That document names any shared multi-agent topic procedures it also requires.

| Explicit request | Base skill | Detailed multi-agent procedure |
| --- | --- | --- |
| Team, parallel, or multi-agent review | [review](../review/SKILL.md) | [review.md](review.md) |
| Parallel or multi-agent issue campaign | [issue-campaign](../issue-campaign/SKILL.md) | [issue-campaign.md](issue-campaign.md) |

`ttsc` has no benchmark-campaign skill. Use [benchmark](../benchmark/SKILL.md) for measurement integrity, then the applicable issue-campaign workflow for authorized benchmark-driven implementation.

Do not load this skill merely for Individual Self-Review, Overall Self-Review, an unqualified review, or a campaign that does not explicitly request parallel agents.

## Shared Parallelism Rules

- Use the smallest number of agents that adds independent evidence or owns immediately executable disjoint work. Available thread capacity is not a reason to create an agent.
- Never create a waiter, poller, coordinator-only child, duplicate implementation owner, or agent that cannot begin useful work immediately.
- Give every review or discovery agent the complete declared surface. Parallel review adds independent full passes; it never partitions coverage by package, file, concern, platform, or test lane.
- Partition implementation only through verified dependency and file-ownership boundaries. One agent owns one coarse batch and its disjoint file set inside the campaign's single shared checkout, topic branch, and cycle pull request.
- Keep the lead active on fact-checking, integration, conflict resolution, and decisions that do not duplicate an assigned agent.
- Do not let agents re-delegate.
- Overall Self-Review remains solo. In a parallel campaign the lead alone runs it, over the integrated pull-request diff.
- Never create a clone or worktree. Every workflow in this skill, parallel implementation included, runs in the current checkout.
- Remove every finished local branch, process, and assignment-owned temporary asset before declaring its assignment complete.

The solo campaign's [Individual Self-Review](../review/SKILL.md#individual-self-review) is a different topology and relaxes neither the full-surface rule nor the solo Overall Self-Review rule above.

A parallel review gives several reviewers the entire declared surface independently, and the lead adjudicates their findings. Individual Self-Review gives exactly one read-only reviewer one pushed commit's parent-to-commit diff, returns advice to the main agent while implementation continues, and leaves that main agent's whole-surface Overall Self-Review as the merge gate.

A batch implementation agent spawns no Individual Self-Review because agents do not re-delegate. It reviews its own pushed batch through [Batch Self-Review](issue-campaign.md#batch-self-review), and the solo development procedure's subagent carve-out stays with a solo campaign's main agent.
Files in this package (3)
  • SKILL.md 4 KB
  • issue-campaign.md 2 KB
  • review.md 4 KB

Versions

RepositoryScoreLicence
This page · systemfsoftware/systemfsoftware90Apache-2.0
shibing624/agentica100Apache-2.0
masihmoafi/skills100MIT
fengshao1227/ccg-workflow95MIT
GuYu-001/ccg-ros2-workflow95MIT
wrongstack/wrongstack90MIT
samchon/typia90MIT

Database snapshot: 13.11.2026 · package version a242769c90c2 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100review
    Defines exhaustive solo Overall Self-Review, mandatory advisory Individual Self-Review for solo issue-campaign commits, unqualified review, and solo repository-wide issue-discovery rounds for ttsc. Use for every self-review or unqualified review request and as the default review…
  • 90issue-campaign
    Defines the default solo repository-wide issue campaign for ttsc: repeated full-scope discovery to an empty round before each unified CI-validated implementation pull request, lead-vetted issue publication, mandatory Individual and Overall Self-Review, and renewed cycles until a…
  • 90review
    Defines exhaustive solo review, Self-Review, and solo repository-wide issue-discovery rounds for typia. Use for every self-review or unqualified review request and as the default review mode inside issue campaigns. This skill never spawns review agents; use the multi-agent skill…
  • 100issue-campaign
    Defines the default solo repository-wide issue campaign for typia: exhaustive discovery, lead-vetted issue publication, one unified CI-validated implementation pull request per cycle, solo Self-Review, and repeated rediscovery until a full clean round. Use for broad audits, many…
  • 100git-issue
    GitHub issue to PR end-to-end — branch, TDD implementation, PR — one issue or several in parallel. Use when asked to work on an issue, fix issue #N, or batch-process several.
  • 92pr-preparer
    Explicit-use only — invoke when the user explicitly names this skill, or when an active explicitly invoked workflow calls it. Prepares and opens a ready-for-review pull request from completed branch changes.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.