CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Generate format-controlled research reports with evidence tracking, citations, source governance, and multi-pass synthesis. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief. Triggers: "帮我调研一下", "深度研究", "综述报告", "深入分析", "research this topic", "write a report on", "survey the literature on", "competitive analysis of", "技术选型分析", "竞品研究", "政策分析", "行业报告". V6 adds: source-type governance, AS_OF freshness checks, mandatory counter-review, and citation registry. V6.1 adds: source accessibility (circular verification forbidden, exclusive advantage encouraged).

58

Quality

67%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./deep-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

This is an ambitious, comprehensive research methodology skill that suffers from significant verbosity and structural redundancy. The dual pipeline (general P0-P7 and enterprise E1-E7) creates confusion with overlapping descriptions, and the skill inlines extensive detail that should be in reference files while also referencing external files that aren't provided. The core workflow concept is sound but the presentation undermines usability.

Suggestions

Reduce redundancy by removing the duplicate enterprise workflow descriptions — define the enterprise pipeline once and clearly state how it maps to/extends the general P0-P7 pipeline.

Move detailed tables (source governance classifications, quality gates thresholds, registry output format) into the referenced files and keep only summary rules in SKILL.md to cut length by ~40%.

Replace pseudocode examples (like the SendMessage counter-review dispatch) with either actual executable patterns or remove them — they add length without actionability.

Add a clear decision tree or flowchart at the top showing: trigger → mode selection → which pipeline to follow → which reference files to load, so Claude can quickly navigate the skill.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~500+ lines with significant redundancy. Enterprise workflow is described in P0, then repeated in the Enterprise Research Mode section. E3-E5 are described in detail and then summarized again as 'E3-E7'. Source governance rules, quality gates, and anti-patterns contain substantial overlap. Many concepts Claude already understands (what SWOT is, what a PDF is equivalent here being what 'official' vs 'journalism' sources are) are over-explained.

1 / 3

Actionability

The skill provides structured workflows with specific steps, status report templates, and registry output formats, which is good. However, it lacks truly executable code/commands — the bash example for counter-review is pseudocode (SendMessage to fictional agents), there are no actual CLI commands or scripts, and many instructions are procedural descriptions rather than copy-paste-ready guidance. The references to external files that aren't provided also reduce actionability.

2 / 3

Workflow Clarity

The P0-P7 pipeline is clearly sequenced with status checkpoints at each phase, which is strong. However, the Enterprise Research workflow (E1-E7) overlaps confusingly with the general P0-P7 pipeline — it's unclear when to follow which, and the enterprise sections are described twice (once in detail, once as a summary). The relationship between the two workflows creates ambiguity. Validation steps exist (L1/L2/L3, P6 counter-review, P7 verify) but are mostly delegated to external reference files not provided.

2 / 3

Progressive Disclosure

The skill references many external files (subagent_prompt.md, research_notes_format.md, enterprise_analysis_frameworks.md, etc.) with clear tables showing when to load each, which is good structure. However, no bundle files were provided, making it impossible to verify these references work. More critically, the SKILL.md itself is a monolithic wall of text that inlines too much detail (full source governance tables, complete registry format, detailed enterprise workflow) that should be in reference files, while simultaneously pointing to reference files for other content.

2 / 3

Total

7

/

12

Passed

Description

100%

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 is a strong skill description that excels across all dimensions. It provides specific concrete capabilities, comprehensive bilingual trigger terms, explicit 'when to use' guidance, and a distinctive niche that clearly separates it from generic writing or analysis skills. The versioning notes (V6, V6.1) add useful specificity about advanced features, though they slightly increase verbosity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'format-controlled research reports', 'evidence tracking', 'citations', 'source governance', 'multi-pass synthesis', 'source-type governance', 'AS_OF freshness checks', 'mandatory counter-review', 'citation registry', and 'circular verification forbidden'.

3 / 3

Completeness

Clearly answers both 'what' (generate format-controlled research reports with evidence tracking, citations, source governance, multi-pass synthesis) and 'when' (explicit 'This skill should be used when...' clause with specific trigger scenarios and keyword lists).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms in both English and Chinese, including user-facing phrases like 'research this topic', 'write a report on', 'competitive analysis of', '帮我调研一下', '深度研究', '综述报告', plus domain-specific terms like 'literature review', 'market or industry analysis', '技术选型分析', '竞品研究'.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche combining research report generation with specific features like source governance, citation registry, counter-review, and freshness checks. The bilingual trigger terms and specialized vocabulary make it unlikely to conflict with generic writing or analysis skills.

3 / 3

Total

12

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (545 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
daymade/claude-code-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.