CtrlK
BlogDocsLog inGet started
Tessl Logo

scholar-evaluation

Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls. Never use for ranking people or consequential decisions.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is scholar-evaluation in K-Dense-AI/scientific-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a strong, lean, executable skill body: precise local commands, an explicitly sequenced workflow with validation and fail-closed controls, and a well-structured one-level reference layout, with only minor redundancy in the repeated safety statements.

DimensionReasoningScore

Conciseness

The body is dense and well-organized with little concept padding, but the safety boundary and data-boundary rules are restated across several sections, leaving minor instances that could be tightened; this sits noticeably above the mostly-efficient anchor.

4 / 5

Actionability

It provides copy-paste-ready, fully executable commands with exact paths and flags (e.g. "PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_rubric.py --rubric assets/rubric_template.json") covering the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The 8-step workflow is clearly sequenced with explicit validation/stop checkpoints ("Stop on a prohibited decision context", fail-closed checklist, weight-sensitivity requires two files) and feedback loops, matching the anchor for clear sequence with explicit validation and error recovery.

5 / 5

Progressive Disclosure

SKILL.md is a concise overview with well-signaled, one-level-deep references (all verified to exist: references/*.md, assets/*.json|.csv, scripts/*.py) and a "Bundled resources" index, matching the clear-overview anchor; no nested references are introduced.

5 / 5

Total

19

/

20

Passed

Description

58%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 specific and distinct, with concrete actions and a strong safety boundary, but it lacks an explicit "Use when..." trigger clause and the natural phrasings a user would actually say, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when reviewing a draft, paper, protocol, or literature synthesis, or auditing a low-stakes assessment rubric."

Include natural user-facing phrasings such as "review my paper", "give feedback on a draft", or "check this rubric" alongside the technical terms.

Keep the existing third-person voice but lead with the most common trigger scenarios before the safety boundary to improve when-to-use recall.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("Provide qualitative-first, evidence-traceable developmental review", "audit low-stakes research-assessment rubrics", "optional local quality controls"), with only minor gaps in coverage, matching the anchor for several specific actions.

4 / 5

Completeness

The description gives a clear "what" but has no "Use when..." or equivalent explicit trigger clause, which per the judging guidelines caps completeness at 3 even though the what is well stated.

3 / 5

Trigger Term Quality

Contains relevant phrases like "scholarly works", "developmental review", and "research-assessment rubrics" but omits natural user phrasings such as "review my paper", "evaluate a draft", or "check my rubric", so common variations are missing.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche combining scholarly-work review with rubric auditing and an explicit anti-misuse boundary ("Never use for ranking people or consequential decisions"), leaving only minor overlap risk with adjacent review/audit skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/claude-scientific-writer
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.