improve: enhance task-decomposition-expert

[davila7]

Automated Component Improvement

Changes

• Description rewrite: Replaced vague one-liner with 3 concrete <example> blocks (Rails monolith migration, 8-week AI product launch, multi-agent pipeline design) each with invocation <commentary> tags, following the exact pattern of prompt-engineer.md and llm-architect.md
• Added model: sonnet: Was absent in original
• Expanded tools: Changed Read, Write → Read, Write, Edit, Bash, Glob, Grep, WebSearch to match orchestration-level capability
• Removed mandatory ChromaDB coupling: Deleted the "ChromaDB Integration Priority" section and all MUST/ALWAYS/CRITICAL ChromaDB language from the core framework — the component no longer forces an optional external MCP dependency on every user
• Added Requirements Gathering step: Mandatory first action with 6 structured intake questions (goal, constraints, non-negotiables, existing assets, risk tolerance, acceptance criteria)
• Added concrete output format: Work Breakdown Structure with 8/80-hour rule, dependency graph notation with symbols, parallelism map table, risk register table with likelihood/impact/mitigation columns, validation checkpoints
• Added Agent Handoff Plan section: Explicit table mapping workstreams to specialist agents with handoff artifacts
• Added Integration with Other Agents section: Mirrors pattern of other high-quality agents in this category
• Added structured JSON progress format and completion message template

Research Summary

The original component was deeply coupled to ChromaDB as a mandatory dependency (40% of body content), had only 2 tools configured while instructing calls to unconfigured MCP tools, lacked the model field, had a vague description with no examples, and provided no concrete output templates or agent handoff guidance. All Critical and High priority issues from the research report have been resolved.

Validation

• component-reviewer: PASSED
  • name: task-decomposition-expert (kebab-case)
  • description: present with 3 example blocks and commentary tags
  • model: sonnet
  • tools: Read, Write, Edit, Bash, Glob, Grep, WebSearch
  • No hardcoded secrets
  • No absolute paths
  • Correct category: ai-specialists

---

Automated review cycle by Component Improvement Loop

---

Summary by cubic

Rebuilds task-decomposition-expert to produce structured, actionable plans with estimates, dependencies, and clear agent handoffs. Removes forced ChromaDB coupling and upgrades config for better orchestration.

• Clearer description with 3 concrete example blocks and invocation commentary.
• Added model: sonnet; expanded tools to Read, Write, Edit, Bash, Glob, Grep, WebSearch.
• Removed mandatory ChromaDB dependency to avoid forcing an external MCP on users.
• Introduced mandatory requirements intake and standardized outputs: WBS with 8/80 rule, dependency graph, parallelism map, risk register, validation checkpoints, agent handoff plan, and JSON progress/completion messages.
• Area: components (cli-tool/components/); no new components; no catalog regeneration needed; no new env vars or secrets.

^{Written for commit 2203b95. Summary will update on new commits.}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
aitmpl-dashboard	Ready	Preview, Comment	May 8, 2026 8:16pm
claude-code-templates	Ready	Preview, Comment	May 8, 2026 8:16pm

[github-actions]

👋 Thanks for contributing, @davila7!

This PR touches cli-tool/components/** and has been marked review-pending.

What happens next

1. 🤖 Automated security audit runs and posts results on this PR.
2. 👀 Maintainer review — a human reviewer validates the component with the component-reviewer agent (format, naming, security, clarity).
3. ✅ Merge — once approved, your PR is merged to main.
4. 📦 Catalog regeneration — the component catalog is rebuilt automatically.
5. 🚀 Live on aitmpl.com — your component appears on the website after deploy.

While you wait

• Check the Security Audit comment below for any issues to fix.
• Make sure your component follows the contribution guide.

This is an automated message. No action is required from you right now — a maintainer will review soon.

[github-actions]

⚠️ Security Audit Report

Status: ❌ FAILED

Metric	Count
Total Components	763
✅ Passed	360
❌ Failed	403
⚠️ Warnings	1005

❌ Failed Components (Top 5)

Component	Errors	Warnings	Score
vercel-edge-function	3	4	81/100
prompt-engineer	2	0	90/100
neon-expert	2	2	88/100
agent-overview	2	1	89/100
unused-code-cleaner	2	1	89/100

...and 398 more failed component(s)

---

📊 View Full Report for detailed error messages and all components

[cubic-dev-ai]

1 issue found across 1 file

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="cli-tool/components/agents/ai-specialists/task-decomposition-expert.md">

<violation number="1" location="cli-tool/components/agents/ai-specialists/task-decomposition-expert.md:42">
P2: The atomic action duration range is contradictory: `1–8 hours` conflicts with the stated `8/80 rule` (`8–80 hours`). Update the Level 3 definition to match the 8/80 constraint.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

P2: The atomic action duration range is contradictory: 1–8 hours conflicts with the stated 8/80 rule (8–80 hours). Update the Level 3 definition to match the 8/80 constraint.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At cli-tool/components/agents/ai-specialists/task-decomposition-expert.md, line 42:

<comment>The atomic action duration range is contradictory: `1–8 hours` conflicts with the stated `8/80 rule` (`8–80 hours`). Update the Level 3 definition to match the 8/80 constraint.</comment>

<file context>
@@ -1,96 +1,148 @@
+```
+Level 1: Primary Objectives (high-level outcomes, 3–7 total)
+  Level 2: Tasks (supporting activities per objective)
+    Level 3: Atomic Actions (specific executable steps, 1–8 hours each)
+```
+
</file context>

Suggested change

	Level 3: Atomic Actions (specific executable steps, 1–8 hours each)
	Level 3: Atomic Actions (specific executable steps, 8–80 hours each)