content-publish

Publish content to joelclaw.com via the Convex-first pipeline. Covers the full lifecycle: draft → review → publish → revalidate → verify. Handles secret leasing, tag conventions, content types (article, tutorial, note, essay), and verification gates. Use when: 'write article about X', 'publish article <slug>', 'draft a tutorial', 'publish this', 'push to convex', or any content publishing task.

Quality

84%

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

81%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-structured, actionable runbook with a clear lifecycle and genuine verification gates including an error-recovery loop. The main weaknesses are minor: some restated notes between the inline sections and Gotchas, and a Publish step rendered as comments rather than an executable command.

Suggestions

Replace the comment-only Publish step ('# Re-run the upsert with draft: false') with an actual executable command or a concrete Node payload snippet so the whole lifecycle is copy-paste ready.

De-duplicate the Gotchas against the inline sections — the ISO-datetime rule and the 'run npx convex from apps/web/' note each appear twice; keep them in Gotchas and link, or state once inline.

Consider moving the Node JSON-payload script into a references/ file and linking to it, which would tighten SKILL.md and let progressive_disclosure reach the top anchor.

Dimension	Reasoning	Score
Conciseness	Lean, operational runbook with no general-concept padding; minor redundancy between the inline notes and the Gotchas section (ISO datetime rule and apps/web/ path are each restated), keeping it just below a 5.	4 / 5
Actionability	Mostly executable guidance with concrete `npx convex`, Node payload script, and curl commands; the Publish step is comment-only pseudocode ('# Re-run the upsert with draft: false') rather than a ready command, a minor gap.	4 / 5
Workflow Clarity	Clear six-step sequence (draft → content prep → review → publish → revalidate → verify) with explicit validation in Step 6 ('All four checks must pass') and an error-recovery feedback loop ('If 404... likely still draft: true'), satisfying the 5 anchor including for a destructive/batch operation.	5 / 5
Progressive Disclosure	No bundle files exist; the single ~155-line SKILL.md is well-organized into clearly headed sections with no nested references. Good structure, but being a self-contained runbook over 50 lines with a few inlined blocks (e.g., the Node payload script) that could live in a reference keeps it just below 5.	4 / 5
	Total	17 / 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.

A strong description that pairs a clear, specific capability statement with an explicit 'Use when' trigger list and a well-scoped niche. Minor room to expand trigger synonyms and enumerate actions more exhaustively, but it satisfies both the what and when requirements cleanly.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions across the lifecycle ('secret leasing, tag conventions, content types..., verification gates') plus the draft→review→publish→revalidate→verify sequence; falls just short of a fully exhaustive action list for a 5.	4 / 5
Completeness	Explicitly answers what (Convex-first pipeline lifecycle and sub-tasks) and when (a dedicated 'Use when:' clause with concrete trigger phrases), matching the 5 anchor.	5 / 5
Trigger Term Quality	Good coverage of natural user phrases ('write article about X', 'publish article <slug>', 'draft a tutorial', 'publish this', 'push to convex'); a few common synonyms/variations are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'joelclaw.com via the Convex-first pipeline' with distinct triggers, giving it a clear niche with minimal conflict risk against other 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: joelhooks/joelclaw
Path: skills/content-publish/SKILL.md
Commit: 1f7207d

Reviewed: 4 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.