goose-blog-post
Write and publish blog posts for the block/goose open source project
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./goose-blog-post/SKILL.mdQuality
Discovery
40%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 identifies a clear niche (blog posts for the block/goose project) which gives it strong distinctiveness, but it lacks depth in describing specific capabilities and entirely omits explicit trigger guidance ('Use when...'). The description is too terse to help Claude reliably select this skill from a large pool.
Suggestions
Add a 'Use when...' clause specifying trigger conditions, e.g., 'Use when the user asks to write, draft, edit, or publish blog posts or articles for the block/goose project.'
Expand the capability list with specific actions such as 'drafts blog content, formats markdown, adds frontmatter metadata, and publishes to the project site.'
Include natural keyword variations users might say, such as 'blog', 'article', 'post', 'content writing', 'goose blog'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (blog posts for block/goose open source project) and two actions (write and publish), but doesn't elaborate on specific sub-tasks like drafting, formatting, adding metadata, or deploying. | 2 / 3 |
Completeness | Describes what the skill does (write and publish blog posts) but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also fairly thin, placing this at a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'blog posts', 'publish', and the project name 'block/goose', but misses common variations users might say such as 'blog', 'article', 'post', 'content', or 'writing'. | 2 / 3 |
Distinctiveness Conflict Risk | The specific project name 'block/goose' makes this highly distinctive and unlikely to conflict with other skills; it targets a very clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with an excellent multi-step workflow including validation checkpoints and a comprehensive final checklist. Its main weaknesses are verbosity (some sections explain things Claude already knows, like writing style basics) and the monolithic structure that could benefit from splitting detailed reference material into separate files. The complete example blog post and concrete commands/templates make this very usable in practice.
Suggestions
Trim the 'Voice & Style' section — advice like 'short paragraphs for readability' and 'avoid marketing fluff' is guidance Claude already follows; keep only goose-specific conventions.
Consider moving the 'Content Types That Work Well' section and the full example into a separate reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough but could be tightened. Some sections are verbose (e.g., the three writing modes explanation, the content types list at the end, and the voice/style guidelines contain advice Claude already knows like 'short paragraphs for readability'). The social metadata section is necessarily detailed due to the Docusaurus hash requirement, but overall the document is longer than it needs to be. | 2 / 3 |
Actionability | Highly actionable with concrete bash commands, exact file paths, complete YAML and markdown templates, a full example blog post, and specific conventions (naming patterns, image dimensions, URL formats). Every step has executable guidance rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation checkpoints: verifying author exists in authors.yml, local preview to get image URLs, a dedicated review step (Step 7), and a comprehensive final checklist (Step 8) with specific items to verify. The feedback loop of presenting drafts for author review before finalizing is well-defined. | 3 / 3 |
Progressive Disclosure | The content is entirely monolithic in a single file with no references to supporting files, despite being quite long (~250+ lines). The content types section, the full example, and the detailed social metadata instructions could reasonably be split into separate reference files. However, the internal organization with clear headers is good. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- block/agent-skills
- Commit
60bfdad
- Reviewed
Table of Contents
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.