multi-ai-planning

Create production-ready, agent-executable plans using verification-first approach, hierarchical decomposition, dependency mapping, and quality gates. Optional multi-AI research integration (Claude + Gemini + Codex). Use when planning complex features, migrations, refactorings, security implementations, or any multi-step agentic workflows requiring rigorous verification and parallel execution coordination.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/multi-ai-planning/SKILL.md

Quality

Content

45%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content has a well-structured, validation-rich workflow but is undermined by severe verbosity, heavy template-placeholder padding, and broken references to scripts, templates, and schemas that are not present in the bundle. Progressive disclosure is weak because almost everything is inlined rather than split into reference files.

Suggestions

Trim the body substantially: remove the redundant Quick Reference, Best Practices, and Common Mistakes sections (which restate the 6-step workflow) and condense the Step 5 quality-scoring template blocks to remove [X]/20 placeholder padding.

Move the detailed quality-scoring rubric and plan/task/checkpoint templates into separate reference files, keeping SKILL.md as a concise overview that points to them.

Resolve broken references: scripts/validate-schema.sh, generate-plan-md.sh, and visualize-deps.sh, the templates/ directory, the examples/ directory, and plan/task/checkpoint *.schema.json files are referenced but do not exist — either add them to the bundle or remove the references.

Dimension	Reasoning	Score
Conciseness	The ~1140-line body is noticeably to severely verbose: heavy template-placeholder padding ([X]/20), sections that restate the workflow (Quick Reference, Best Practices, Common Mistakes), and explanations of concepts Claude already knows (SMART criteria, critical path, topological sort).	2 / 5
Actionability	Some concrete executable guidance exists (Task-tool code blocks, verify-plan.sh, JSON structures), but many examples are bracketed templates and reference scripts/templates/schemas that do not exist in the bundle.	3 / 5
Workflow Clarity	A clear 6-step sequence with per-step validation checklists, a Decision Point, and a feedback loop (Step 5: score <90 → gap analysis → re-verify); minor gap is that the bundled verify-plan.sh is a superficial grep-based checker.	4 / 5
Progressive Disclosure	The SKILL.md is a monolithic 1140-line body with content that belongs in separate files inlined (quality-scoring rubric, templates, best practices), and it references non-existent files (validate-schema.sh, generate-plan-md.sh, visualize-deps.sh, templates/, examples/, *.schema.json).	2 / 5
	Total	11 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states both capability and explicit use-when triggers with natural keywords. It is slightly held back by methodological abstraction in its action list and some jargon in the trailing trigger clause.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ('verification-first approach, hierarchical decomposition, dependency mapping, and quality gates'), but they read as methodological labels rather than concrete operations, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('Create production-ready, agent-executable plans...') and when ('Use when planning complex features, migrations, refactorings...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger terms are present ('planning complex features, migrations, refactorings, security implementations'), but the trailing 'multi-step agentic workflows requiring rigorous verification and parallel execution coordination' is jargon-heavy rather than user-spoken.	4 / 5
Distinctiveness Conflict Risk	The verification-first, multi-AI, agent-executable niche is mostly distinct, but 'planning complex features' has minor overlap risk with general planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1147 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/multi-ai-planning/SKILL.md
Commit: 93ed392

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.