CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

linkedin-search

Use this skill whenever the user wants to search for jobs in any location or market, find job listings, or look up a specific job posting — in any country, city, or remotely. Invoke for open positions, vacancies, and hiring across any sector or role (software, data, design, marketing, finance, legal, operations, etc.). The location is always supplied explicitly by the user. Trigger phrases: find a job, job search, search for jobs, job openings, vacancies, hiring, positions open, remote jobs, "are there any X jobs in <place>", look up this job posting.

71

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A clean, execution-focused body: fully executable commands with documented flags and realistic examples, specified error and retry behavior, and appropriate single-file structure with no unnecessary bundle files. The only weaknesses are minor — a few lines of repo-meta commentary that could be trimmed and an implicit rather than explicit search-to-detail sequence.

DimensionReasoningScore

Conciseness

The body is tight and operational — flag tables, a format-selection table, and copy-paste examples with no explanation of concepts Claude already knows. Two blocks are trimmable meta-commentary: the 'country-agnostic worked example of the repo's job-portal-skill pattern' blockquote and some framing in the intro, which keeps it just short of the lean anchor.

4 / 5

Actionability

Every command is copy-paste ready: full invocations for both 'search' and 'detail', every flag documented with concrete example values ('"Mumbai, Maharashtra, India"', '--jobage 30', 'urn:li:jobPosting:...'), and five usage examples covering the common cases including sub-day recency and remote-only searches.

5 / 5

Workflow Clarity

For a simple two-command skill the flow is unambiguous — search returns job IDs that are passed as-is to detail, error output is specified as stderr JSON with exit code 1, and retry behavior on 429/5xx is documented. It falls short of the top anchor only because the search→parse→detail pipeline is never laid out as an explicit sequence with a checkpoint between steps.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent) and none are needed: everything required to run the skill — commands, flags, examples, output formats, error conventions — fits inline in ~85 well-organized lines. Sections (When to use, Commands, Usage examples, Output formats, Notes) are clear and nothing that belongs in a separate file is inlined.

5 / 5

Total

18

/

20

Passed

Description

91%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: concrete actions, an explicit use-when clause, and a comprehensive list of natural trigger phrases including a realistic question form. The only notable gaps are that it doesn't name LinkedIn (a distinctiveness risk if sibling job-portal skills exist) and it undersells the filter and detail-retrieval capabilities documented in the body.

DimensionReasoningScore

Specificity

Names three concrete actions — 'search for jobs', 'find job listings', 'look up a specific job posting' — and scopes them across locations, sectors, and roles. Minor gaps: it omits the skill's filtering (recency, workplace type) and full-detail retrieval capabilities that the body actually supports, keeping it below comprehensive.

4 / 5

Completeness

Both halves are explicit: the 'what' is stated as concrete actions, and the 'when' is an explicit 'Use this skill whenever the user wants to...' clause backed by a concrete trigger-phrase list. Voice follows the standard skill-description imperative pattern, not penalized first/second person.

5 / 5

Trigger Term Quality

An explicit trigger list covers natural phrasings and synonyms users would actually say: 'find a job, job search, search for jobs, job openings, vacancies, hiring, positions open, remote jobs', plus a natural question form '"are there any X jobs in <place>"' and 'look up this job posting'.

5 / 5

Distinctiveness Conflict Risk

Job-search triggers ('vacancies', 'job openings', 'look up this job posting') are a clear niche and unlikely to fire for unrelated skills. However, the description never names LinkedIn — the body says this is one of a pattern of job-portal skills — so a closely related job-board skill could overlap on these generic job-search triggers.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

MadsLorentzen/ai-job-search

Path

.agents/skills/linkedin-search/SKILL.md

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.