linkedin-reader

Read LinkedIn for financial research using opencli (read-only). Use this skill whenever the user wants to read their LinkedIn feed, search for jobs in the finance/trading industry, view professional posts about markets or earnings, or gather professional sentiment from LinkedIn. Triggers include: "check my LinkedIn feed", "search LinkedIn for", "LinkedIn posts about", "what's on LinkedIn about AAPL", "finance jobs on LinkedIn", "LinkedIn market sentiment", "who's posting about earnings on LinkedIn", "LinkedIn feed", "professional network buzz", "what are analysts saying on LinkedIn", any mention of LinkedIn in context of reading financial news, market research, job searches, or professional commentary. This skill is READ-ONLY — it does NOT support posting, liking, commenting, connecting, or any write operations.

Quality

85%

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

Quality

Content

75%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 highly actionable with concrete, executable commands and a clear step sequence supported by validation and error-recovery tables. Its main weakness is redundancy — setup, error, and flag material is duplicated between SKILL.md and the reference file, hurting both conciseness and clean progressive disclosure.

Suggestions

Remove the duplicated setup, error-reference, and flag tables from SKILL.md, keeping only a brief summary inline and pointing to references/commands.md for the full detail to improve both conciseness and progressive disclosure.

Replace the inline status-check block with a single 'run opencli doctor first' instruction to cut padding without losing the validation gate.

Add an explicit validate→fix→retry loop for command failures (e.g., on AuthRequiredError or EmptyResultError) to lift workflow clarity from a pre-flight check to a true feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and tables, but setup instructions, flag tables, and the error reference are duplicated between SKILL.md and references/commands.md, and the inline status-check block adds padding that could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout ('opencli linkedin timeline --limit 20 -f json', 'opencli linkedin search "quantitative analyst" --limit 10 -f json') with flag and output-column tables covering the common cases, matching the top anchor.	5 / 5
Workflow Clarity	A clear 5-step sequence (Setup → Identify → Execute → Present → Diagnostics) with a setup validation gate ('opencli doctor', status block) and an error-fix table, but the validation is a pre-flight connectivity check rather than an explicit validate→fix→retry loop on outputs.	4 / 5
Progressive Disclosure	Good structure with a clearly signaled one-level-deep reference ('references/commands.md — Complete read command reference'), but notable content (setup steps, error tables, flag tables) is duplicated between SKILL.md and the reference rather than cleanly split.	4 / 5
	Total	16 / 20 Passed

Description

95%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 strong, explicit description that clearly states what the skill does, when to use it, and its read-only boundary, with comprehensive natural trigger phrases. The only minor weakness is that the listed capabilities are broad read/view verbs rather than sharply distinct technical actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('read their LinkedIn feed', 'search for jobs', 'view professional posts', 'gather professional sentiment'), but the actions are broad read/view verbs on a single platform rather than multiple distinct technical operations, leaving minor coverage gaps relative to the top anchor.	4 / 5
Completeness	Explicitly answers both 'what' (read feed, search jobs, view posts, gather sentiment) and 'when' via a clear 'Use this skill whenever...' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say ('check my LinkedIn feed', 'search LinkedIn for', 'what's on LinkedIn about AAPL', 'finance jobs on LinkedIn', 'LinkedIn market sentiment') with good synonym variation, matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (LinkedIn + financial research, read-only) with distinct triggers and an explicit boundary ('does NOT support posting, liking, commenting, connecting'), minimizing conflict with other skills.	5 / 5
	Total	19 / 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: himself65/finance-skills
Path: plugins/social-readers/skills/linkedin-reader/SKILL.md
Commit: 81e1f50

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.