CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

candidate-evaluation

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

Quality

78%

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

Fix and improve this skill with Tessl

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

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 compact and actionable with real gh api commands and concrete output formats, but the workflow lacks any validation or error-recovery steps and its single declared reference file is missing from the bundle. It also leaves key scoring mechanics (fit score, skill-level bars) undefined.

Suggestions

Add validation checkpoints to the workflow: how to handle empty search results, API rate limits, and private/nonexistent profiles before generating a profile.

Fix the dangling 'AGENTS.md' reference — either ship the file (ideally under references/) or remove the Reference Files section.

Define how the 1-10 fit score and the 1-5 skill-level bars in the skills matrix are derived from the gathered data (e.g., weighting rules per criterion).

DimensionReasoningScore

Conciseness

The body is largely efficient — criteria are terse bullet lists and the gh api commands are compact with no padding or explanations of concepts Claude already knows. Minor over-explanation/trimmable material remains ('Use ASCII box art for visual appeal', the 'Example Queries' and 'When to Use' sections partially duplicate the frontmatter description), which fits the 'efficient, minor instances that could be trimmed' anchor rather than the fully lean 5.

4 / 5

Actionability

Provides concrete, mostly executable guidance: real `gh api` commands with `--jq` filters and a concrete output template. Minor gaps remain — commands use an unsubstituted `{username}` placeholder, 'Gather Data via GitHub MCP' names no MCP tool, and neither the 1-10 fit score nor the 1-5 skill-level bars have a defined derivation, keeping it below the fully copy-paste-ready 5.

4 / 5

Workflow Clarity

A clear four-step sequence exists (gather data → analyze repos → check contributions → generate profile), but there are no validation checkpoints or error-recovery loops: no handling for empty search results, rate limits, private/nonexistent profiles, or verification of data before scoring. This matches the 'steps listed but validation gaps, checkpoints missing' anchor, not 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

The body is reasonably sectioned, but the only reference it declares ('AGENTS.md - Project guidelines and contributor attribution' under 'Reference Files') does not exist in the bundle — no references/, scripts/, or assets/ directories are present, so the reference is dangling. The evaluation criteria and output templates could also live in a reference file for this ~114-line body, matching the 'some structure, references present but not clearly usable' anchor.

3 / 5

Total

14

/

20

Passed

Description

82%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 third-person description with an explicit 'Use when...' clause and concrete, natural trigger phrases. Its only weakness is that the 'what' side is somewhat thin — a single bundled action rather than a list of specific capabilities.

DimensionReasoningScore

Specificity

The description names the domain ('MLOps/engineering roles', 'GitHub contributors') and one or two concrete actions ('Evaluate GitHub contributors', 'updating CONTRIBUTORS.md with hiring assessments'), but does not enumerate several specific capabilities, matching the 1-2 concrete actions anchor. It is above a 2 because the actions are concrete rather than generic, but below a 4 because coverage is not broad.

3 / 5

Completeness

It explicitly answers both parts: 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. This matches the anchor-5 example structure; it is not a 4 because the 'when' clause is explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

Triggers include natural phrases users would actually say: 'analyzing candidates', 'researching GitHub profiles', 'updating CONTRIBUTORS.md', 'hiring assessments'. Good keyword coverage with only a few natural variations missing (e.g., 'screen a candidate', 'recruiting'), which fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (GitHub contributor evaluation for MLOps hiring at Pollinations) with distinct triggers ('CONTRIBUTORS.md', 'hiring assessments', 'GitHub profiles') that are unlikely to fire for unrelated skills. Minimal conflict risk matches the anchor-5 description.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.