linkedin-post

Draft a LinkedIn post in the user's voice from a topic, note, or rough idea.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./runtime/api-server/src/embedded-capabilities/linkedin-ghostwriter/skills/linkedin-post/SKILL.md

Quality

Content

86%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.

The body is an efficient, well-structured instruction set for a simple single-purpose skill, with mostly concrete guidance and a clear sequence; the only gaps are a missing worked example and an explicit review/retry feedback loop.

Suggestions

Add one short before/after example post to make the voice and structure guidance fully copy-paste concrete.

Clarify what "linkedin_*" refers to (name the specific tool(s) or MCP calls) so step 6 is unambiguous.

Add a brief review/retry checkpoint, e.g. "If the draft does not match the user's past tone, revise against 1-2 of their recent posts before returning."

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — six terse directives with zero padding and no explanation of concepts Claude already knows, matching the "every token earns its place" anchor.	5 / 5
Actionability	Guidance is concrete and directive ("never 'I'm excited to share'", "keep paragraphs to 1-2 lines", "publish via linkedin_"), but it lacks a worked example post and "linkedin_" leaves the exact tooling unspecified — minor gaps that hold it just below level 5.	4 / 5
Workflow Clarity	A clear six-step numbered sequence ending in a "ready to review" checkpoint, but there is no explicit feedback/retry loop (e.g. what to do when the tone does not match past posts), which the level-5 anchor requires.	4 / 5
Progressive Disclosure	Under 50 lines with a single well-organized purpose and no need for external references — the simple-skill exception applies, so the clean title plus ordered list earns the top score.	5 / 5
	Total	18 / 20 Passed

Description

53%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.

The description is concise and names a clear, specific domain, but it omits an explicit "Use when..." trigger clause and relies on a single action/keyword, which caps completeness and trigger coverage at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to write or draft a LinkedIn post from a topic, note, or rough idea."

Include natural synonym terms users say (e.g. "LinkedIn update", "write a LinkedIn post") to broaden trigger coverage.

Optionally name 1-2 more concrete sub-actions (e.g. match tone to past posts, suggest hashtags sparingly) to lift specificity toward level 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action — "Draft a LinkedIn post in the user's voice from a topic, note, or rough idea" — plus the input types, but it is a single action rather than the multiple specific actions the level-4/5 anchors require.	3 / 5
Completeness	It clearly states the "what" (draft a LinkedIn post in the user's voice) but provides no explicit "Use when..." trigger clause, and the rubric caps completeness at 3 when such trigger guidance is missing.	3 / 5
Trigger Term Quality	"LinkedIn post" is a natural phrase a user would say, but the description lacks common synonyms or variations (e.g. "LinkedIn update", "LinkedIn article", "write a post") that the level-4 anchor expects.	3 / 5
Distinctiveness Conflict Risk	The LinkedIn-specific niche is mostly distinct with only minor overlap risk against general copywriting/writing skills, though the absence of explicit triggers keeps it just below the level-5 "clear niche with distinct triggers" anchor.	4 / 5
	Total	13 / 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.

Repository: holaboss-ai/holaOS
Path: runtime/api-server/src/embedded-capabilities/linkedin-ghostwriter/skills/linkedin-post/SKILL.md
Commit: 4684714

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.