CtrlK
BlogDocsLog inGet started
Tessl Logo

research-deep

Read research outline, launch independent agent for each item for deep research. Disable task output.

58

Quality

66%

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-deep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 skill body is highly actionable with an executable prompt template and clear step sequencing, but it carries verbatim duplication in its example and leaves the validation failure-recovery loop undescribed for a batch operation. Tightening the example and adding a retry-on-failure step would raise conciseness and workflow clarity.

Suggestions

Collapse the 'One-shot Example' to only the parts that differ from the prompt template (e.g., the filled-in {item_related_info} and resolved paths) instead of repeating the full template.

Add an explicit error-recovery loop: if validate_json.py fails, describe fixing the JSON and re-running validation before marking the item complete.

Clarify batch failure handling in Step 4 (what happens to failed items within a batch before launching the next).

DimensionReasoningScore

Conciseness

The body is mostly efficient with no concept over-explanation, but the 'One-shot Example' duplicates the prompt template's Field Definitions, Output Requirements, Output Path, and Validation blocks verbatim, which could be tightened.

2 / 3

Actionability

Provides an executable Python f-string prompt template with fully specified variables, a concrete slugify rule, and a real validation command, making it copy-paste ready.

3 / 3

Workflow Clarity

The five-step sequence and embedded validation gate are clear, but the skill does not describe the error-recovery feedback loop (fix and re-validate) for this batch operation, leaving the validation checkpoint's recovery path implicit.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; content is cleanly organized into Trigger, Workflow, and Agent Config sections, satisfying the well-organized-sections criterion for a self-contained skill.

3 / 3

Total

10

/

12

Passed

Description

60%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 concrete actions and a distinct niche, but it omits explicit trigger guidance and relies on mechanism-focused wording rather than natural user phrasing. Adding a 'Use when...' clause would lift both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants deep research across a list of items defined in an outline.yaml file.'

Include natural trigger keywords users would say (e.g., 'deep research', 'research each item', 'batch research') alongside the existing technical phrasing.

Reframe to emphasize the user-facing outcome (structured research results per item) rather than the internal mechanism ('Disable task output').

DimensionReasoningScore

Specificity

Names multiple concrete actions ('Read research outline', 'launch independent agent for each item', 'Disable task output'), matching the anchor for listing several specific actions.

3 / 3

Completeness

Clearly states what the skill does but omits any explicit 'when to use' guidance; per the rubric a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant terms ('research outline', 'deep research') but lacks a natural trigger clause and common variations; phrasing leans technical ('launch independent agent').

2 / 3

Distinctiveness Conflict Risk

The outline-driven batch-agent niche is fairly specific, but 'deep research' alone overlaps with general research skills and absent explicit triggers leave some conflict risk.

2 / 3

Total

9

/

12

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
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.