一键导入
mav-create-tasks
How to decompose a solution design into discrete, independently implementable tasks. Used as a dependency from workflow skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
How to decompose a solution design into discrete, independently implementable tasks. Used as a dependency from workflow skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | mav-create-tasks |
| description | How to decompose a solution design into discrete, independently implementable tasks. Used as a dependency from workflow skills. |
| user-invocable | false |
| disable-model-invocation | true |
Decompose a solution design into discrete, independently implementable tasks. Each task is small enough to be implemented, verified, and committed in a single focused effort.
digraph tasks {
"Read the solution design" [shape=box];
"Identify discrete units of work" [shape=box];
"Order by dependency" [shape=box];
"Count tasks" [shape=diamond];
"Post checklist comment" [shape=box];
"Create sub-issues" [shape=box];
"Read the solution design" -> "Identify discrete units of work";
"Identify discrete units of work" -> "Order by dependency";
"Order by dependency" -> "Count tasks";
"Count tasks" -> "Post checklist comment" [label="< 5 tasks"];
"Count tasks" -> "Create sub-issues" [label=">= 5 tasks"];
}
From the solution design's "Areas Affected" and "Approach", identify natural task boundaries:
Each task should touch a small, cohesive set of files. If a task feels like it needs a paragraph to describe, it is too big — split it.
Arrange tasks so each builds on the previous:
The output format depends on the number of tasks:
Post a single comment on the issue with a checkbox list:
## Tasks
- [ ] **<imperative title>** — <1-2 sentence description>
- [ ] **<imperative title>** — <1-2 sentence description>
- [ ] **<imperative title>** — <1-2 sentence description>
Each task is checked off as it is completed. Progress is tracked by updating the comment.
Create GitHub sub-issues linked to the parent issue. Each sub-issue contains:
gh issue create \
--title "<imperative title>" \
--body "$(cat <<'EOF'
<1-2 sentence description of what to implement>
Parent: #<parent-issue>
EOF
)"
Post a summary comment on the parent issue listing all sub-issues with their execution order:
## Tasks
| # | Issue | Title | Depends On |
|---|-------|-------|------------|
| 1 | #101 | <title> | — |
| 2 | #102 | <title> | — |
| 3 | #103 | <title> | #101 |
**Execution order:** #101, #102 → #103
Sub-issues that have no dependency between them can be worked on in any order. Use the Depends On column only when one task genuinely requires another to be completed first.
Before the task list is considered complete:
Scan a project for missing best-practice areas and implement the top recommendation for each gap (linting, unit testing) — installs tools, writes configs, verifies, and commits. Pass 'recommend' to stop after writing recommendations without implementing (replaces the old do-recommend skill).
Implement a focused code change. Use this skill as the wrapper for any implementation work so the Maverick workflow report captures what was done and so the agent applies the project's coding standards before editing. Intended to be invoked once per task from inside a do-issue-* or do-epic phase, not standalone.
Audit a codebase for security risks in one of two modes. In full-audit mode it scans the entire codebase and writes a findings report to docs/security-audit.md (run as part of do-init or on demand). In update mode it reviews only a diff plus the code it could impact, returning a structured findings list as a pre-push gate for do-issue-solo and do-issue-guided. Covers secrets exposure, dependency vulnerabilities, authentication and authorisation patterns, input validation, transport security, and common OWASP risks.
Create, restructure, or update technical documentation. Handles greenfield projects, refactoring non-compliant docs, and incremental updates after code changes.
Work on a multi-story GitHub epic end-to-end. Builds a DAG from the child stories, groups them into waves, runs waves in parallel via per-story worktrees, ejects PRs that fail agent-code-review for human handling, and propagates blocks to downstream stories. Requires git worktrees.
Initialise a project for use with Maverick — verifies the GitHub App, installs the CLI if needed, writes the project config with integration tracking, scaffolds docs, generates project skills, runs an initial cybersecurity audit, then commits the changes and opens a PR.