payload

Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.

Quality

88%

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

82%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.

A well-organized, highly actionable Payload development reference with strong code examples and a clean task→reference navigation structure. The main weaknesses are minor content redundancy and reference links that point to bundle files not present in the workspace.

Suggestions

Ship the referenced reference/*.md bundle files (FIELDS.md, COLLECTIONS.md, HOOKS.md, ACCESS-CONTROL.md, QUERIES.md, ADAPTERS.md, ADVANCED.md, PLUGIN-DEVELOPMENT.md, FIELD-TYPE-GUARDS.md, ENDPOINTS.md, ACCESS-CONTROL-ADVANCED.md) so the navigation links resolve.

Consolidate the overlap between 'Common Gotchas' (items 1–3) and the 'Security Pitfalls'/'Data Integrity' sections to remove repeated guidance and recover tokens.

Add an explicit validation checkpoint to the Building & Type Generation flow (e.g., verify payload-types.ts regenerated before proceeding) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence (no 'what is a CMS' preamble), but there is minor redundancy between the 'Common Gotchas' list and the 'Security Pitfalls'/'Best Practices' sections that could be consolidated.	4 / 5
Actionability	Abundant copy-paste-ready TypeScript (buildConfig, CollectionConfig, hooks, access functions, queries) plus specific commands (npx create-payload-app, pnpm dev, payload build) cover the common cases fully.	5 / 5
Workflow Clarity	Sequences like Quick Start and the Building & Type Generation decision flow are clear, and ❌/✅ pitfall pairs give feedback-style guidance, but there are no explicit validate→fix→retry checkpoints for the riskier operations.	4 / 5
Progressive Disclosure	Structure is exemplary — a task→file Quick Reference table, well-signaled one-level-deep reference links, and a Reference Documentation index — but the referenced reference/*.md files are not present in the bundle, so the signaled navigation is not actually resolvable.	4 / 5
	Total	17 / 20 Passed

Description

95%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, concrete, Payload-specific description with explicit 'Use when' triggers and natural domain keywords. It is held just below a perfect specificity score only because it leans on two action verbs plus a list of objects rather than multiple distinct actions.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete Payload artifacts and task areas (payload.config.ts, collections, fields, hooks, access control, validation errors, relationship queries, transactions), but relies on only two action verbs ('working with', 'debugging') rather than the multiple distinct verbs of the anchor-5 example.	4 / 5
Completeness	Explicitly answers both 'what' (working with Payload projects across the listed components) and 'when' via two concrete 'Use when…' trigger clauses covering debugging scenarios.	5 / 5
Trigger Term Quality	Uses exactly the natural terms a Payload developer would say — 'Payload projects', 'collections', 'fields', 'hooks', 'access control', 'validation errors', 'security issues', 'relationship queries', 'transactions' — including the config filename payload.config.ts.	5 / 5
Distinctiveness Conflict Risk	Payload-specific niche anchored by payload.config.ts and Payload-internal concepts; minimal overlap risk with other skills.	5 / 5
	Total	19 / 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 (519 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 46 missing	Warning

	Total	14 / 16 Passed

Repository: whimzyLive/nightshift-ai
Path: .agents/skills/payload/SKILL.md
Commit: a2b4df7

Reviewed: 8 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.