multi-ai-implementation

Production-ready code generation and incremental development using Explore-Plan-Code-Commit workflow. TDD-driven with <200 line changes, automatic rollback, and multi-agent coordination. Use when implementing features, refactoring code, migrating systems, or integrating components requiring rigorous testing and quality assurance.

Quality

73%

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-implementation/SKILL.md

Quality

Content

62%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 workflow is exceptionally well-structured with strong validation and feedback loops, and the guidance is largely actionable. Its main weakness is severe verbosity from redundant restatements and over-explanation of basic concepts, compounded by a monolithic structure that fails to link its own bundle file.

Suggestions

Collapse the redundant restatements — the quick-reference table, Best Practices, Common Mistakes, and Appendix B all re-explain the same 6 steps and doom-loop rules; keep one canonical form and trim the others.

Remove or relocate explanations of concepts Claude already knows (the Understanding prerequisites on TDD/git, the expand-migrate-contract primer, and the generic error-handling tutorial) to cut hundreds of lines.

Reference the existing scripts/pre-flight-check.sh from the Prerequisites or Step 1 section, and either create examples/ or remove the dangling pointer, so the in-body references resolve to real files.

Dimension	Reasoning	Score
Conciseness	At ~1200 lines the body is noticeably verbose: the 6-step workflow is restated as a quick-reference table, best practices, common mistakes, and three appendices, and it over-explains concepts Claude already knows (TDD, git workflow, expand-migrate-contract, error handling).	2 / 5
Actionability	Provides mostly executable guidance — real git/npm commands and a runnable TypeScript generateToken example — but the Task-tool `task({...})` coordination blocks are pseudocode rather than real syntax, and many templates use unfilled `[bracket]` placeholders.	4 / 5
Workflow Clarity	The 6 steps are clearly sequenced, each with Purpose/Inputs/Process/Outputs/Validation, and include explicit feedback loops and checklists (doom-loop breaker, TCR automatic rollback, quality-gate iteration) that match the top anchor.	5 / 5
Progressive Disclosure	There is section structure, but content that belongs in separate files is inlined (Appendices A–C, large template blocks), the provided `scripts/pre-flight-check.sh` bundle is never referenced from the body, and the closing pointer to `examples/` points at a directory that does not exist.	3 / 5
	Total	14 / 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 well-constructed description that clearly states both capability and trigger conditions with concrete, third-person language. The main weakness is slight breadth in the trigger terms, which creates minor overlap risk with generic coding skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'code generation', 'incremental development', 'TDD-driven with <200 line changes', 'automatic rollback', and 'multi-agent coordination' — though 'production-ready code generation' is slightly broad, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Production-ready code generation and incremental development using Explore-Plan-Code-Commit workflow') and when ('Use when implementing features, refactoring code, migrating systems, or integrating components') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when' clause provides natural user phrases ('implementing features', 'refactoring code', 'migrating systems', 'integrating components'), giving good coverage but missing common synonyms and concrete file/stack signals.	4 / 5
Distinctiveness Conflict Risk	The Explore-Plan-Code-Commit workflow plus TDD/rollback/multi-agent signals carve a fairly distinct niche, but 'implementing features' and 'refactoring code' are broad enough to overlap with general development skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1204 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

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

Reviewed: 1 day 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.