candidate-evaluation

Evaluate GitHub contributors for MLOps/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/candidate-evaluation/SKILL.md

Quality

Content

65%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 content is well-structured and actionable with real gh api commands, but it lacks validation checkpoints for its batch/write operations and underuses progressive disclosure. The two ASCII visual formats add mild redundancy.

Suggestions

Add a validation step before writing to CONTRIBUTORS.md (e.g., confirm the candidate is not already listed and verify the GitHub profile resolves), which would lift workflow_clarity above the batch-operation cap of 3.

Define how the fit score (1-10) and the skill-level bars (1-5) are computed so the output format is fully reproducible rather than left to judgment.

Remove the duplicate 'Example Queries' section (it restates 'When to Use' triggers) and collapse the ASCII box and skills matrix into one visual format to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with executable commands and no teaching of known concepts, but the dual ASCII box-plus-matrix formats and the 'Example Queries' section (which duplicates 'When to Use' triggers) are trimmable.	4 / 5
Actionability	Concrete, executable `gh api` commands and a fully specified output format provide mostly copy-paste-ready guidance, but the fit-score (1-10) and skill-level bar (1-5) mappings are not defined.	4 / 5
Workflow Clarity	The four-step process is clearly sequenced, but there are no validation checkpoints despite batch `gh api` calls and a repo-mutating write to CONTRIBUTORS.md, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Sectioning is clean, but the only reference (AGENTS.md) is a plain mention with no link and no bundled file behind it, and the detailed criteria/process are not split into one-level-deep references.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

The description is strong: it clearly states the skill's purpose and provides explicit, natural trigger phrases tied to a distinct hiring-evaluation niche. The only slight gap is that the action list is not quite as granular as the most comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Names the MLOps/engineering hiring domain and several concrete actions (evaluate, analyze candidates, research GitHub profiles, update CONTRIBUTORS.md), sitting just below the comprehensive five-action anchor.	4 / 5
Completeness	Explicitly answers what ('Evaluate GitHub contributors for MLOps/engineering roles') and when ('Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases like 'candidates', 'GitHub profiles', 'hiring assessments', and 'CONTRIBUTORS.md' are present, but coverage of synonyms and variations is not exhaustive enough for a 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (hiring assessment of GitHub contributors for MLOps roles) with a distinct artifact (CONTRIBUTORS.md) and specific triggers yields minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: pollinations/pollinations
Path: .claude/skills/candidate-evaluation/SKILL.md
Commit: 2099cdf

Reviewed: 3 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.