nicolify-feature

Full-stack feature development pipeline for Nicolify. Orchestrates 6 specialized agents (architect, backend, agentic, backend-auditor, ux-designer, frontend) through 4 phases with user checkpoints. Use when building new features, adding CRUD endpoints, creating new UI screens, or implementing cross-stack functionality.

Quality

81%

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

Quality

Content

75%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 is a well-structured, actionable orchestration playbook with explicit checkpoints and feedback loops. Its main weaknesses are mild redundancy in the UX-approach explanation, placeholder-laden agent prompts, and under-specified parallel-agent synchronization.

Suggestions

Clarify how to detect parallel-agent completion (e.g., poll TaskOutput / task notifications) instead of relying on UI-SPEC.md 'appearing', so the frontend wave's synchronization is unambiguous.

Consolidate the UX-approach decision and the 'Determine agents needed' list into a single section to remove the restated A/B logic.

Consider extracting the Phase 4 bash command suite into a references/ script so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no padding of concepts Claude already knows, but the UX-approach logic is restated across 'UX Approach Decision' and 'Determine agents needed', and the agent prompt templates carry some redundancy that could be trimmed.	4 / 5
Actionability	It provides concrete Agent() invocations with full prompts and copy-paste-ready bash commands with explicit tool paths (.venv/bin/ruff, npx tsc, npx playwright), but the agent prompts use unfilled placeholders like [path] and [module] requiring substitution.	4 / 5
Workflow Clarity	Four phases with Checkpoints 1-3, parallel waves with explicit dependencies, and an audit->fix feedback loop give a clear validated sequence, but parallel-agent synchronization (e.g., frontend 'when UI-SPEC.md appears') is underspecified.	4 / 5
Progressive Disclosure	Well-organized into Prerequisites, four Phase sections, and Error Handling with no nested references and no bundle files present; the bash command block and agent-prompt templates are long enough that they could arguably live in separate reference files, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is strong: third-person voice, concrete agent roster and phase structure, and an explicit 'Use when' clause with natural trigger phrases. Minor room to expand action coverage and synonyms, but it clearly answers what and when.

Dimension	Reasoning	Score
Specificity	"Orchestrates 6 specialized agents (architect, backend, agentic, backend-auditor, ux-designer, frontend) through 4 phases with user checkpoints" names the domain and several concrete actions, but the action set is orchestration-focused rather than comprehensively enumerating what the pipeline produces.	4 / 5
Completeness	It explicitly answers both what ("Orchestrates 6 specialized agents... through 4 phases with user checkpoints") and when ("Use when building new features, adding CRUD endpoints, creating new UI screens, or implementing cross-stack functionality") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"building new features, adding CRUD endpoints, creating new UI screens, or implementing cross-stack functionality" are natural phrases users would say, though a few common synonyms (e.g., 'endpoint', 'API') are missing.	4 / 5
Distinctiveness Conflict Risk	The Nicolify-specific scope and named agent roster give it a clear niche with distinct triggers and minimal overlap risk against generic skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/ap_sales_agent
Path: .claude/skills/nicolify-feature/SKILL.md
Commit: d31f7bc

Reviewed: ~18 hours 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.