Name: jbaruch/blog-writer
Rating: 77.60000000000001 (1 reviews)
Author: jbaruch

jbaruch/blog-writer

Write developer blog posts from video transcripts, meeting notes, or rough ideas — extracting narrative, structuring hooks and technical sections, formatting code placeholders, learning the author's voice through interactive onboarding, and checking drafts against 39 AI anti-patterns with three-pass scanning, craft sweep, and rewrite auditing — whenever the user wants to write a blog post, draft a blog, turn a transcript into a blog, work on blog content, or continue a blog series.

Quality

97%

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

92%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-engineered, highly actionable workflow that sequences 12 steps with explicit gates, script-based validation, and feedback loops, while delegating detailed material to a one-level-deep reference set. Its only real weakness is mild verbosity in routing/gate phrasing that could be trimmed.

Suggestions

Collapse the repeated 'Proceed immediately to Step N' lines and 'Gate:' boilerplate into a single stated convention to recover a few tokens without losing clarity.

Tighten the Step 9 shape-convergence prose (the blocked_by list and re-record instructions overlap with what record-post-shape.sh already enforces) so only the skill-specific routing remains.

Consider moving the detailed exit-code routing tables for the three scripts into their own reference file, keeping SKILL.md focused on the step sequence and the per-step decision.

Dimension	Reasoning	Score
Conciseness	The body is dense operational content (script routing, exit-code tables, gates) rather than padding or basic-concept explanation, but the repeated 'Proceed immediately to Step N' closings and the lengthy Step 9 shape-convergence prose could be tightened in places.	4 / 5
Actionability	Fully executable guidance throughout: exact script invocations with paths and arguments ('bash .../setup-persona-dir.sh --probe', 'python3 .../sweep.py blog-draft-[slug].md'), named JSON fields, and explicit exit-code routing with placeholder args clearly marked.	5 / 5
Workflow Clarity	Steps 1-12 are clearly sequenced with explicit gates ('Gate: ...') and validation feedback loops (Step 9 verify-re-record-re-run loop, Step 10/11 'Re-run until it exits 0' after every rewrite), satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	The body is an orchestration overview pointing one level deep to seven clearly-signaled reference files (all of which exist under references/), with bulk material like the anti-pattern catalog and process procedures appropriately split out; navigation is explicit via the ordered Step 6 file list.	5 / 5
	Total	19 / 20 Passed

Description

100%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, third-person description that names multiple concrete actions and pairs them with explicit, natural trigger phrases for both primary and secondary use cases. It clearly answers what the skill does and when to use it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions in third person ('Extracts narrative from source material, structures content with hooks and technical sections, formats code examples with placeholders, and checks drafts against a catalog of AI anti-patterns'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the four actions above) and 'when' via a concrete 'Use this skill whenever...' clause plus a secondary 'Also trigger when...' clause, matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	Covers the natural phrases users would say ('write a blog post, draft a blog, turn a transcript into a blog, work on blog content', 'video transcript', 'blog series') including synonyms and source-material variations; there is no relevant file extension for this non-file-type skill.	5 / 5
Distinctiveness Conflict Risk	The niche — developer blog posts derived from transcripts/meeting notes/ideas, audited against an AI anti-pattern catalog — is distinct, and its triggers ('turn a transcript into a blog') are unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

2 days ago

Table of Contents

Discovery Implementation Validation