create-linkedin-content

Draft voice-tuned LinkedIn post variants from a free-form brief. Reads a personal voice guide (generated via generate-voice-guide), produces 2–5 variants with distinct framings, applies LinkedIn-specific defaults (arrow bullets, "why this matters" beat, 150–500 words), and self-checks against the voice guide's banned phrases before returning.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/content/capabilities/create-linkedin-content/SKILL.md

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 strong, highly actionable skill body: concrete commands, platform-specific defaults, a framings catalog, and a real self-check phase with fix guidance. The main weaknesses are minor — inherited-by-reference workflow details from create-x-content and a few rationale sentences that could be trimmed.

Dimension	Reasoning	Score
Conciseness	The body is efficient — tight tables for inputs and framings, a numbered resolution chain, and no explanation of concepts Claude already knows. Minor instances of over-explanation could be trimmed, e.g. 'LinkedIn rewards longer than X but shorter than a blog post' and the rationale sentences in the Tips section, keeping it below anchor 5.	4 / 5
Actionability	Fully actionable for an instruction-only skill: copy-paste-ready commands ('/create-linkedin-content --brief "..."'), a flags table with defaults, a 4-step voice-guide resolution order, concrete framings with structures and 'when to use', a 7-item self-check, exact file-naming patterns, and a frontmatter template. Two worked examples even show expected variant outcomes.	5 / 5
Workflow Clarity	Phases 1–6 are clearly sequenced with a validation checkpoint (Phase 4's 7 checks, including fix actions like 'rewrite to sound like a human practitioner' and 'Add a "why this matters" beat if missing'). It falls short of 5 because Phases 1–2 defer to create-x-content ('Same 2–5 decision rubric') without restating those details, leaving the fix loop for checks 1–4 implicit.	4 / 5
Progressive Disclosure	With no bundle files present, everything a drafting skill needs is appropriately inlined in one well-sectioned document with headers, tables, and code fences that make navigation easy. The only organization gap is the reliance on an external sibling skill for Phase 1–2 details rather than any in-file reference structure, keeping it below 5.	4 / 5
	Total	17 / 20 Passed

Description

71%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 specific, third-person description with concrete actions and low conflict risk, but it entirely lacks a 'Use when...' trigger clause, which both caps completeness and limits natural trigger-term coverage. Adding explicit usage triggers (e.g., 'Use when the user asks to draft, write, or polish a LinkedIn post') would lift it to top-tier quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to write, draft, or generate a LinkedIn post or LinkedIn content' — this addresses the completeness cap and trigger-term gaps directly.

Include common natural synonyms users would say ('LinkedIn post', 'LinkedIn content', 'social post for LinkedIn') so the description matches a wider range of phrasings.

Optionally state the relationship to create-x-content in one clause (e.g., 'LinkedIn counterpart to create-x-content') to eliminate the remaining sibling-skill overlap risk.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions in third person — 'Draft voice-tuned LinkedIn post variants', 'produces 2–5 variants with distinct framings', 'applies LinkedIn-specific defaults (arrow bullets, "why this matters" beat, 150–500 words)', 'self-checks against the voice guide's banned phrases' — with comprehensive coverage of the skill's behavior.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines; the 'when' is only weakly implied by the LinkedIn domain.	3 / 5
Trigger Term Quality	'LinkedIn post variants', 'brief', and 'voice guide' are natural terms a user would say, giving good keyword coverage anchored on a distinctive platform term, but common variations like 'LinkedIn content' or 'write a post' are missing. It is above anchor 3 because the core natural phrase 'LinkedIn post' is present and specific, below 5 because coverage is not comprehensive.	4 / 5
Distinctiveness Conflict Risk	'LinkedIn-specific defaults' and 'voice guide (generated via generate-voice-guide)' carve out a clear niche that would not trigger for unrelated skills; the only overlap risk is with the closely related sibling create-x-content skill, which the explicit LinkedIn platform term mostly resolves.	4 / 5
	Total	16 / 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: gooseworks-ai/goose-skills
Path: skills/content/capabilities/create-linkedin-content/SKILL.md
Commit: cc3e518

Reviewed: 7 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.