Tessl • The management layer for AI agent skills

Highly actionable, copy-paste-ready CLI documentation with excellent exit-code and error-schema coverage. Weaknesses are structural: a duplicated 'When to Use' section, no validation checkpoints before destructive/batch operations, and a monolithic ~530-line body whose Sales Navigator and command reference content should be split into bundle files.

Suggestions

Remove the duplicate 'When to Use' section (keep one) and consolidate the repeated 'not instant' timing warnings into 'Important Behavior' to tighten the body.

Add validation checkpoints before destructive and batch operations: e.g., confirm the target URL before 'connection remove' and 'linkedin reset --all', and verify workflow JSON before 'workflow run' with a status check loop after.

Move the Sales Navigator command reference (and optionally the full per-command flag tables) into a references/ file (e.g., references/sales-navigator.md) with clearly signaled links from SKILL.md, keeping the main file as a lean overview plus core commands.

Dimension	Reasoning	Score
Conciseness	The body is dense and efficient — commands, flag tables, and copy-paste examples with almost no explanation of concepts Claude already knows. Minor redundancy could be trimmed: the 'When to Use' section appears twice (lines 9-10 and 38-45), and the 'not instant / 30 seconds to several minutes' warning is repeated in the intro and 'Important Behavior'.	4 / 5
Actionability	Every command is fully executable with copy-paste-ready invocations ('linkedin person fetch https://www.linkedin.com/in/username --experience --education --json -q'), concrete flag tables, documented exit codes, JSON output/error schemas, and a complete auth-setup command sequence. Specific examples cover the common cases for every subcommand.	5 / 5
Workflow Clarity	Sequences are present for multi-step flows (auth recovery via exit code 2, workflow run then status/wait) and error feedback exists ('always check the success field', exit-code table), but this cap applies: destructive and batch operations — 'linkedin reset --all', 'connection remove', and 'workflow run' batch execution — have no validation/verification steps before execution. Per the rubric, batch/destructive workflows without validation cap at 3.	3 / 5
Progressive Disclosure	Section headers organize the content and there is one clearly signaled external doc link ('See [Building Workflows](https://linkedapi.io/docs/building-workflows/)'), but no bundle files exist and roughly 400 lines of per-command API reference are inlined in SKILL.md. The Sales Navigator and full command reference clearly belong in separate reference files, matching the 'content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

92%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 description with an explicit 'Use when' trigger, a comprehensive list of concrete actions, and a clearly distinct LinkedIn/Sales Navigator niche. The only minor gap is a few missing natural synonyms such as 'InMail' or 'outreach'.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'fetch profiles, search people/companies, send messages, manage connections, create posts, and Sales Navigator' — giving comprehensive coverage of the CLI's capabilities. It matches the anchor for listing multiple specific concrete actions; nothing is vague or generic.	5 / 5
Completeness	Both halves are explicit: 'Use when automating LinkedIn via CLI' answers when, and the colon-delimited action list answers what with concrete trigger phrases. It clearly matches the anchor 'clearly and explicitly answers both what AND when'.	5 / 5
Trigger Term Quality	Good natural keyword coverage: 'automating LinkedIn', 'profiles', 'search people/companies', 'send messages', 'connections', 'posts', and 'Sales Navigator' are all phrases users would naturally say. A few natural terms are missing (e.g., 'InMail', 'outreach', 'network', 'connect/invite'), which keeps it just below the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	'LinkedIn' and 'Sales Navigator' define a clear niche with distinct trigger terms; no other skill category would plausibly collide with this description. Minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (536 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/linkedin-cli/SKILL.md
Revision: 64adc55

Reviewed: 14 days ago

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.

linkedin-cli

Table of Contents

Is this your skill?