linkedin-automation

Automate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always search tools first for current schemas.

1.45x

Quality

74%

Does it follow best practices?

Impact

87%

1.45x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/linkedin-automation/SKILL.md

Quality

Content

68%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 delivers concrete, well-sequenced guidance for five LinkedIn workflows with useful pitfall coverage and a navigable quick-reference table, and it stays lean throughout. Its main weaknesses are the missing validation step before the destructive delete operation (capping workflow clarity) and recurring duplication of the image-upload flow. One example tool-call payload per workflow would close the remaining actionability gap.

Suggestions

Add an explicit validation step before the destructive delete workflow, e.g. "Confirm the post exists and the user explicitly approved deletion before calling LINKEDIN_DELETE_LINKED_IN_POST; deletion is permanent".

Consolidate the three restatements of the two-phase image-upload flow (workflow 3, Common Patterns, Known Pitfalls) into one canonical section and cross-reference it.

Include one concrete example RUBE tool call (with realistic arguments) for the flagship create-post workflow so guidance is copy-paste ready rather than parameter-list-only.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean tool sequences, key parameters, and pitfall lists with no explanations of concepts Claude already knows, but the image-upload two-phase flow is repeated three times (workflow 3, Common Patterns, Known Pitfalls) and the "Powered by Composio" footer is filler — minor trimmable redundancy matching anchor 4.	4 / 5
Actionability	Concrete tool slugs, ordered sequences, and named parameters ("text: Post content text", "visibility: 'PUBLIC' or 'CONNECTIONS'") give mostly executable guidance; the gap is the absence of any example tool-call payloads, and schema specifics are delegated to RUBE_SEARCH_TOOLS rather than shown, fitting anchor 4.	4 / 5
Workflow Clarity	Sequences are clearly ordered and setup has checkpoints ("Confirm connection status shows ACTIVE before running any workflows"), but the destructive "Delete a Post" workflow has no validation or confirmation step — the rubric's destructive-operation cap limits this to 3 despite otherwise good sequencing.	3 / 5
Progressive Disclosure	No bundle files exist, and the single-file body is well organized with per-workflow sections, a Common Patterns section, and a Quick Reference table for navigation; the ~170-line body inlines per-tool detail that could live in reference files, matching anchor 4's 'good structure, minor organization gaps'.	4 / 5
	Total	15 / 20 Passed

Description

70%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 specific and clearly niched to LinkedIn automation with concrete named actions, but it lacks any explicit 'when to use' trigger guidance, which both caps completeness and limits its discoverability. The closing sentence "Always search tools first for current schemas" is operational instruction rather than capability or trigger description. Adding a Use-when clause and natural synonyms would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to post, comment on, or delete LinkedIn content, manage their LinkedIn profile or company page, or attach images to LinkedIn posts."

Use verb-based phrasing for all listed actions (e.g. "retrieve profile and company info, comment on posts, delete posts") so every capability reads as a concrete action and delete-post coverage is included.

Include natural synonyms users would say — "publish/share a post", "feed", "update my profile" — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"create posts, manage profile, company info, comments, and image uploads" lists several specific actions, though "company info" and "comments" are noun fragments and delete-post coverage from the body is absent — minor gaps, matching anchor 4 rather than the comprehensive coverage of anchor 5.	4 / 5
Completeness	The description has a clear "what" ("Automate LinkedIn tasks via Rube MCP: create posts, manage profile...") but no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	"LinkedIn", "posts", "profile", "comments", and "image uploads" are natural phrases users would say, but common synonyms like "publish", "share", "feed", or "update my profile" are missing, fitting anchor 4's 'a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	"LinkedIn" names a clear niche with distinct triggers (LinkedIn posts, profile, comments) and pairs with a specific integration path (Rube MCP/Composio), giving minimal conflict risk with other skills — matching anchor 5.	5 / 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: davepoon/buildwithclaude
Path: plugins/all-skills/skills/linkedin-automation/SKILL.md
Commit: 10bfc43

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.