CtrlK
BlogDocsLog inGet started
Tessl Logo

research

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

52

Quality

57%

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 ./skills/research-codex-en/research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a concrete prompt template and specified outputs, but it is held back by a duplicative one-shot example, the absence of explicit validation steps in the workflow, and a bulky single-file structure with no reference offload. It is a competent workflow spec that would benefit from tightening and splitting.

Suggestions

Collapse the one-shot example into a compact 'filled variables only' snippet rather than re-stating the full template, to remove the duplication.

Add an explicit validation checkpoint after Step 4 (e.g., verify outline.yaml/fields.yaml parse and required keys exist) with a fix-and-retry loop.

Move the full prompt template and one-shot example into a reference file (e.g., references/prompt-template.md) and link to it, leaving SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The content is mostly efficient and actionable, but the one-shot example largely duplicates the prompt template structure (same Task/Goals/Output Requirements blocks), which is padding that could be tightened; not verbose enough to score 1 and not lean enough for 3.

2 / 3

Actionability

Provides a copy-paste prompt template with explicit variable substitution, a concrete one-shot example, specified YAML output structures (outline.yaml/fields.yaml with field definitions), and exact follow-up commands, matching the fully executable/copy-paste-ready anchor.

3 / 3

Workflow Clarity

Five steps are clearly sequenced with user-confirmation checkpoints (request_user_input at steps 1-5), but there is no explicit validation/verify-fix-retry step or checklist for the generated outputs, so it stops at the 'checkpoints present but gaps' anchor rather than 3.

2 / 3

Progressive Disclosure

The file is well-organized into clear sections with no deep nesting, but it is a single monolithic document over 50 lines with substantial inline content (full prompt template plus a duplicate one-shot example) that is not offloaded to reference files; the over-50-line simple-skill exception does not apply.

2 / 3

Total

9

/

12

Passed

Description

50%Weight 40%Scale 1-3

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 conveys the skill's purpose and a few use domains, but is terse and lacks an explicit 'Use when...' trigger clause, leaving every dimension at the mid-level anchor. It is clear enough to avoid being generic yet not specific or trigger-rich enough to score high.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger phrases (e.g., 'Use when starting a literature review, benchmarking tools, or selecting technologies').

Replace the vague 'etc.' with concrete scenario terms users would actually say to broaden trigger coverage.

Enumerate more granular actions (e.g., 'build an item list, define a field framework, scaffold a research outline') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain and two actions ('Conduct preliminary research', 'generate research outline') but they are general rather than the multiple granular concrete actions of the score-3 anchor; not vague enough for 1.

2 / 3

Completeness

States what it does and lists terse scenario triggers, but lacks a 'Use when...' clause and ends with vague 'etc.'; per the guidelines a missing explicit trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant natural terms ('research', 'academic research', 'benchmark research', 'technology selection') but offers limited variation and no common phrasings a user would naturally say, matching the 'some keywords, missing variations' anchor.

2 / 3

Distinctiveness Conflict Risk

'Preliminary research' plus named domains gives a niche, but the broad 'research' term and the coexisting '/research-deep' skill mean it could still overlap with similar skills.

2 / 3

Total

8

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
Weizhena/Deep-Research-skills
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.