CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

freehire-search

Use this skill to search live software / tech / data / engineering job listings across many countries and markets (and remote) via the freehire.me aggregator's public API, or to look up a specific posting. It aggregates roles from ~50 ATS platforms into one schema, so a single skill covers many markets — but its faceted filtering (skills, category, seniority) is tuned tech-first, so scope triggers to technical roles. Trigger phrases: find a tech job, software job search, developer jobs, engineering vacancies, data/ML jobs, DevOps roles, remote developer jobs, "are there any <tech role> jobs in <place>", look up this freehire job posting.

70

Quality

88%

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

88%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.

An exemplary command-reference body: executable throughout, rich in API-specific gotchas Claude could not infer, with clear command-selection guidance and documented error behavior. Its only real costs are length-driven — the self-hosting digression and the fully inlined flag/facet reference could be trimmed or moved to a reference file to reduce token load.

DimensionReasoningScore

Conciseness

The bulk is high-density, non-obvious operational fact ("Uppercase only: a lowercase or is an ordinary search word", "us is a country code, not a region", "--region none matches jobs with no resolved region", salary-period comparison) that Claude could not know. Minor trimmable digressions keep it below anchor 5: the ~25-line self-hosting/Docker Compose aside, and the tech-scope section that restates the description's caveat at length — but these are a minority, placing it noticeably above the anchor-3 midpoint.

4 / 5

Actionability

Every command is fully executable copy-paste-ready bash (full `bun run ... cli.ts` invocations with all flags), backed by an eight-example usage section covering the common cases (region+remote, OR synonyms, title: operator, country+jobage, detail-by-slug), exact output shapes (JSON schema of results, stderr error codes), and a live facet-discovery endpoint. Nothing is pseudocode or abstract.

5 / 5

Workflow Clarity

A read-only, two-command skill with unambiguous per-command usage plus explicit decision guidance between them ("Do not loop detail over search hits", "--no-description for a cheap discovery pass... fetch a shortlisted job's body with detail") and documented failure behavior (429/5xx retry with backoff, non-zero exits with clear messages, the REGION_VALUE_UNKNOWN diagnostic that is explicitly not an error). No destructive or batch operations exist, so no validation cap applies, and the simple-skill exception holds.

5 / 5

Progressive Disclosure

No bundle files exist, and everything is one level deep with well-organized, clearly headed sections (Scope, Dependency, When to use, Commands, Examples, Output formats, Partial data, Notes) — good structure with nothing buried. It falls short of anchor 5 because ~150 lines of CLI flag and API reference (facet vocabularies, query-operator semantics, endpoint details) are inlined in SKILL.md where a skill of this size would typically offload them to a references/ file; it stays above anchor 3 because the structure is clean and navigable, not a wall of reference text.

4 / 5

Total

18

/

20

Passed

Description

86%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: it explicitly answers both what and when, includes an unusually thorough natural-language trigger list, and honestly scopes itself to tech roles. Its only weakness is capability specificity — it lists just two actions and leaves its filtering abilities (seniority, category, skills, recency) implicit rather than stated as things it can do.

DimensionReasoningScore

Specificity

The description names the domain and exactly two concrete actions — "search live software / tech / data / engineering job listings" and "look up a specific posting" — with no broader capability list (filtering by seniority/skills is only mentioned as a caveat, not claimed). This matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, which requires several specific listed actions.

3 / 5

Completeness

Both halves are explicit: what ("search live... job listings across many countries and markets (and remote) via the freehire.me aggregator's public API, or to look up a specific posting") and when ("Use this skill to..." plus a concrete "Trigger phrases:" list). This matches anchor 5's what-and-when-with-concrete-triggers pattern; it is above anchor 4 because the when is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

It gives an explicit, comprehensive trigger list with synonyms and a natural templated phrase: "find a tech job, software job search, developer jobs, engineering vacancies, data/ML jobs, DevOps roles, remote developer jobs, 'are there any <tech role> jobs in <place>', look up this freehire job posting" — exactly the natural-language variation anchor 5 asks for (no file extensions are relevant to a search skill).

5 / 5

Distinctiveness Conflict Risk

The freehire-specific trigger ("look up this freehire job posting") and tech-first scoping create a clear niche, but broad triggers like "find a tech job" and "developer jobs" would also fire sibling job-portal skills in the same family (e.g. the linkedin-search pattern this body references) — mostly distinct with minor overlap risk against closely related skills, i.e. anchor 4 rather than 5.

4 / 5

Total

17

/

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/freehire-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.