CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/linkedin-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 skill provides a reasonable catalog of LinkedIn API operations via Rube MCP with clear tool naming and sequencing, but suffers from significant verbosity, repeated information, and lack of validation steps for destructive operations. Many pitfalls explain concepts Claude already knows, and the absence of executable code or concrete examples (beyond tool slug names) limits actionability.

Suggestions

Remove redundant pitfalls sections—consolidate into one section and eliminate explanations of obvious concepts (e.g., 'deletion is permanent', what URN formats look like).

Add validation/confirmation steps for destructive operations like DELETE_LINKED_IN_POST (e.g., verify post exists first, confirm with user before deletion).

Add concrete executable examples showing actual tool invocation with sample parameters and expected response shapes, rather than just listing parameter names.

Remove the duplicated image upload flow (appears in both Workflow 3 and Common Patterns) and the vacuous 'When to Use' footer section.

DimensionReasoningScore

Conciseness

Significant verbosity throughout. Many pitfalls sections explain things Claude already knows (e.g., 'Deletion is permanent and cannot be undone', 'HTML markup in post text is not supported', explaining what URNs are). The 'When to use' descriptions are unnecessary padding. The Known Pitfalls section at the bottom repeats information already covered in individual workflow pitfalls. The final 'When to Use' section is completely vacuous.

2 / 5

Actionability

Tool sequences are clearly listed with named tool slugs and key parameters, which is useful. However, there's no executable code—just tool names and parameter lists. The skill instructs to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' which undermines the specificity of the documented parameters. The image upload binary step (step 2 in workflow 3) lacks concrete guidance on how to actually perform the upload.

3 / 5

Workflow Clarity

Multi-step workflows are sequenced with clear numbered steps and labeled as Required/Optional/Prerequisite, which is good. However, there are no validation checkpoints or error recovery steps. The delete post workflow is a destructive operation with no confirmation or verification step, and the image upload flow lacks explicit validation before proceeding to post creation. Per rubric rules, missing validation for destructive operations caps this at 3.

3 / 5

Progressive Disclosure

The content is structured with headers and a quick reference table, but everything is inlined in a single file with substantial repetition (e.g., image upload flow described in workflow 3 and again in Common Patterns). No bundle files exist, and no external references are provided. The pitfalls are duplicated between individual workflows and the consolidated Known Pitfalls section, suggesting the content would benefit from better organization.

3 / 5

Total

11

/

20

Passed

Description

70%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 does a good job identifying the specific platform (LinkedIn) and listing concrete actions, making it distinctive and reasonably specific. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The operational instruction about searching tools first, while useful, doesn't substitute for trigger guidance.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks to post on LinkedIn, update their LinkedIn profile, manage LinkedIn comments, or upload images to LinkedIn.'

Expand trigger terms to include natural synonyms like 'publish on LinkedIn', 'share a LinkedIn update', 'LinkedIn article', or 'social media post on LinkedIn'.

DimensionReasoningScore

Specificity

Lists several specific actions: create posts, manage profile, company info, comments, and image uploads. Coverage is good but 'manage profile' and 'company info' are somewhat vague compared to fully concrete actions.

4 / 5

Completeness

The 'what' is clearly stated with specific LinkedIn actions. However, there is no explicit 'Use when...' clause or trigger guidance. The instruction to 'always search tools first' is operational guidance, not a 'when' clause. Per rubric rules, missing 'Use when' caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'LinkedIn', 'posts', 'profile', 'comments', 'image uploads', and 'company info'. Missing some natural variations users might say like 'publish', 'share on LinkedIn', 'update bio', or 'LinkedIn article'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive with 'LinkedIn' as a clear domain, plus the specific mention of 'Rube MCP (Composio)' as the integration mechanism. Very unlikely to conflict with other skills given the narrow platform focus.

5 / 5

Total

16

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.