When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.
83
80%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/interview-kit/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has strong trigger terms and specificity, listing five concrete actions related to interview design and candidate evaluation. Its main weakness is the structural format—it only provides a 'when' clause without a separate 'what this does' statement, making the capability description implicit rather than explicit. The domain is well-defined and distinctive.
Suggestions
Add an explicit 'what' statement before the trigger clause, e.g., 'Designs structured interview processes, generates role-specific questions, builds evaluation scorecards, and supports interviewer calibration. Use when...'
Consider adding a few more natural trigger terms like 'hiring', 'recruiting', 'job candidate', or 'behavioral questions' to broaden keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'design an interview process', 'create interview questions', 'build scorecards', 'calibrate interviewers', 'evaluate candidates'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | The description answers 'when' well ('When the user needs to...') but the 'what does this do' is only implied through the trigger conditions. It lacks an explicit statement of what the skill does (e.g., 'Guides structured hiring processes') before the 'Use when' clause. However, the 'when' clause effectively doubles as both, though the format is slightly inverted from ideal. | 2 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'interview process', 'interview questions', 'scorecards', 'interviewers', 'evaluate candidates', 'role'. These are terms a user would naturally use when seeking help with hiring/interviewing. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around interview design and hiring evaluation. The specific terms like 'scorecards', 'calibrate interviewers', and 'interview process' are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with a well-defined workflow and excellent concrete examples. Its main weakness is length — several reference sections (competency categories, compensation benchmarking, anti-bias techniques) could be extracted into separate files to improve token efficiency. The content is well-organized within the single file but would benefit from progressive disclosure to reduce the token footprint for simpler use cases.
Suggestions
Extract the Frameworks & Best Practices subsections (competency categories, compensation benchmarking, anti-bias techniques) into separate referenced files to reduce the main skill's token footprint.
Trim explanatory text that Claude already understands, such as spelling out what STAR stands for and basic definitions of bias types — focus on the specific behavioral instructions instead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some content Claude would already know (e.g., explaining what STAR stands for, general anti-bias concepts, basic definitions of scorecard levels). Some sections like 'Common Pitfalls' and 'Compensation Benchmarking Framework' add useful but somewhat verbose guidance that could be tightened. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific competency categories by role type, a defined 1-4 scoring scale with anchors, the STAR-B framework with an example question, take-home assignment guidelines with specific time caps, and complete output examples showing what a good interview loop looks like. The examples section demonstrates both a design prompt and a troubleshooting prompt with concrete responses. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit objectives at each step. It includes validation mechanisms (independent scoring before debrief, quarterly recalibration using outcome data, structured debrief instructions). The anti-bias guardrails serve as a verification checkpoint, and the calibration cadence provides a feedback loop for continuous improvement. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, and references related skills (job-description, sourcing-outreach). However, the document is quite long (~150+ lines of substantive content) with detailed frameworks inline that could be split into separate reference files (e.g., competency categories, compensation benchmarking, anti-bias techniques). The monolithic structure means all content loads even when only a subset is needed. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
4ad31b4
Table of Contents
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.