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.

65

1.45x
Quality

51%

Does it follow best practices?

Impact

87%

1.45x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/linkedin-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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 overview of LinkedIn automation via Rube MCP with clear tool sequences and a useful quick reference table. However, it suffers from significant verbosity—repeating information across sections, explaining concepts Claude already knows, and listing obvious pitfalls. The lack of validation checkpoints in destructive operations and the absence of concrete executable examples (relying on tool names rather than actual invocation patterns) weaken its practical utility.

Suggestions

Cut redundant content: the image upload flow is described three times (workflows 1, 3, and Common Patterns). Consolidate into one canonical workflow and reference it.

Remove pitfalls Claude already knows (token expiration, deletion being permanent, rate limit concepts) and keep only LinkedIn-specific gotchas like URN format requirements and the two-phase image upload.

Add explicit validation/confirmation steps to destructive workflows (delete post) and the image upload flow—e.g., verify image status before creating the post as a required step.

Provide concrete tool invocation examples showing actual parameter values rather than just listing parameter names, so Claude can copy-paste patterns directly.

DimensionReasoningScore

Conciseness

Significant verbosity throughout. Many pitfalls are things Claude already knows (e.g., 'Deletion is permanent and cannot be undone', 'HTML markup in post text is not supported', 'Tokens expire'). The skill repeats the image upload flow three times (in workflows 1, 3, and Common Patterns). Explanations of URN formats and rate limits are general knowledge Claude possesses. The document could be cut by 50%+ without losing actionable information.

1 / 3

Actionability

Tool names and sequences are clearly listed, and the quick reference table is helpful. However, there is no executable code—just tool names with parameter lists. The skill instructs to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' which undermines providing concrete schemas here. The image upload binary step ('Upload the image binary to the returned upload URL') lacks specifics on how to actually do this.

2 / 3

Workflow Clarity

Multi-step workflows are sequenced with clear ordering and labeled as Required/Optional/Prerequisite, which is good. However, there are no validation checkpoints or error recovery loops. The delete workflow lacks a confirmation step despite being destructive. The image upload workflow doesn't include verification as a required step despite the two-phase nature being flagged as a pitfall.

2 / 3

Progressive Disclosure

The content is structured with headers and a quick reference table, which aids navigation. However, with no bundle files, all content is inline in a single long document (~150 lines). The pitfalls sections are repeated across individual workflows and then again in a consolidated 'Known Pitfalls' section, creating redundancy. The content could benefit from splitting detailed pitfalls and patterns into separate reference files.

2 / 3

Total

7

/

12

Passed

Description

67%

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 reasonably strong in specificity and distinctiveness, clearly identifying LinkedIn as the target platform and listing concrete actions. Its main weaknesses are the lack of an explicit 'Use when...' clause and incomplete coverage of natural trigger terms users might employ when requesting LinkedIn-related help.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to post on LinkedIn, update their LinkedIn profile, manage LinkedIn comments, or upload images to LinkedIn.'

Include additional natural trigger terms and variations such as 'social media', 'LinkedIn post', 'publish on LinkedIn', 'share on LinkedIn', or 'LinkedIn update' to improve discoverability.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'create posts, manage profile, company info, comments, and image uploads.' Also includes the operational guidance to 'search tools first for current schemas.'

3 / 3

Completeness

Clearly answers 'what' (automate LinkedIn tasks including posts, profile, comments, etc.) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the nature of the tasks listed, which caps this at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Includes 'LinkedIn', 'posts', 'profile', 'comments', 'image uploads' which are natural terms users might say. However, it's missing common variations like 'social media', 'LinkedIn post', 'publish on LinkedIn', 'update LinkedIn', or 'share on LinkedIn' that users would naturally use.

2 / 3

Distinctiveness Conflict Risk

Highly distinctive with clear niche: LinkedIn automation via a specific MCP tool (Rube/Composio). The combination of platform (LinkedIn) and integration method (Rube MCP, Composio) makes it very unlikely to conflict with other skills.

3 / 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.

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
davepoon/buildwithclaude
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.