Planner Elaborate Assignments
Elaborate all assignments for a target phase via parallel L0 subagents. One invocation per phase; spawns one L0 per assignment concurrently. (Pass 2 loop body)
Install
npx skills add TalonT-Org/AutoSkillit --skill planner-elaborate-assignmentsgit clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/planner-elaborate-assignments ~/.claude/skills/planner-elaborate-assignmentsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# planner-elaborate-assignments
Pass 2 loop body. Receives one phase context file (written by `expand_assignments`), spawns one L0
subagent per assignment in parallel using the native Agent/Task tool, collects results,
and writes per-assignment result files plus a phase sentinel file. The L1 (this skill)
is the sole writer for this phase's assignments — no concurrent write races.
## When to Use
- Invoked by the planner recipe when the recipe dispatches parallel elaboration via `dispatch_items`
- One invocation per phase; handles all assignments within the phase in a single session
## Arguments
- **$1** — Absolute path to the phase context file (written by `expand_assignments`) (contains `id=<phase_id>`, `metadata.assignment_count`, `metadata.assignment_ids`, `metadata.assignment_names`, `prior_results`)
- **$2** — Absolute path to the run-scoped planner directory (e.g., `{{AUTOSKILLIT_TEMP}}/planner/run-YYYYMMDD-HHMMSS`)
## Critical Constraints
**NEVER:**
- Allow L0 subagents to write files directly — L0s return JSON only
- Let an L0 failure abort the phase — always write a stub and continue
- Write output outside `$2/assignments/`
- Spawn L0s sequentially — always in parallel
- Read `{{AUTOSKILLIT_TEMP}}` artifacts outside your designated input files and output directory
- Explore parent directories of your input paths (e.g., `ls $(dirname $1)/..`)
- Read result files from other phases
- Run subagents in the background (`run_in_background: true` is prohibited)Details
- Skill name
planner-elaborate-assignments- Repository
- TalonT-Org/AutoSkillit
- Path
src/autoskillit/skills_extended/planner-elaborate-assignments/SKILL.md- License
- MIT
- Repo updated
- 8 November 2026
FAQ
What does the Planner Elaborate Assignments skill do?
Elaborate all assignments for a target phase via parallel L0 subagents. One invocation per phase; spawns one L0 per assignment concurrently. (Pass 2 loop body)
How do I install the Planner Elaborate Assignments skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill planner-elaborate-assignments. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Planner Elaborate Assignments popular?
It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.
Related skills
Analyze Prs
5TalonT-Org/AutoSkillit
Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.
Arch Lens C4 Container
5TalonT-Org/AutoSkillit
Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?
Arch Lens Concurrency
5TalonT-Org/AutoSkillit
Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?
Planner Elaborate Wps
5TalonT-Org/AutoSkillit
Elaborate all work packages for a target phase via parallel L0 subagents. One invocation per phase; spawns one L0 per WP concurrently. (Pass 3 loop body)
Open Kitchen
5TalonT-Org/AutoSkillit
Open the AutoSkillit kitchen — reveals all kitchen MCP tools for this session. Human-only entry point.
Planner Refine Assignments
5TalonT-Org/AutoSkillit
Refine elaborated assignments for a single phase via parallel L0 subagents (L1+L0 pattern), using per-phase context file with peer_summaries for cross-phase visibility
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.