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).

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is a well-structured, actionable orchestration guide with strong progressive disclosure via a clear reference table, but it loses conciseness points due to the enterprise workflow being restated multiple times. Consolidating the redundant enterprise sections and deduplicating the lead-in sentences would tighten it noticeably.

Suggestions

Consolidate the three enterprise-workflow treatments (the E1–E7 checklist at lines 127–146, the 'Enterprise Research Mode (Specialized Pipeline)' section at 181–269, and 'E3-E7' at 264–269) into a single authoritative enterprise section to remove restated content.

Remove the duplicated lead-in sentence 'When researching a specific company/enterprise, follow this specialized workflow...' (present at both lines 123 and 183).

Consider moving the source-governance accessibility/typology tables (lines 56–95) into a dedicated reference file already listed (e.g., source_accessibility_policy.md) to further reduce body length while keeping the rules one load away.

DimensionReasoningScore

Conciseness

Largely token-efficient with dense tables, diagrams, and status templates, but the enterprise workflow is restated three times (the E1–E7 overview at lines 127–146, the 'Enterprise Research Mode' section at 181–269, and 'E3-E7' at 264–269), and the 'When researching a specific company/enterprise...' lead-in is duplicated at lines 123 and 183.

3 / 5

Actionability

Provides concrete, executable artifacts throughout — citation registry format blocks, per-phase status report templates ('[P3 complete] {approved}/{total} sources...'), and a bash dispatch example for the counter-review team — with only minor templated-placeholder gaps.

4 / 5

Workflow Clarity

The P0–P7 pipeline is clearly sequenced with explicit validation checkpoints (P6 'Find ≥3 issues' feedback loop, P7 spot-checks and 'Remove/fix non-traceable claims'), though the interleaved general/enterprise workflows and duplicated E3–E7 sections create some navigational friction.

4 / 5

Progressive Disclosure

A well-organized Reference Files table with a 'When to Load' column points one-level-deep to all 14 verified reference files, keeping the body an overview while signaling when to load each detail file; minor gaps come from the duplicated enterprise sections.

4 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: it concisely states concrete capabilities, provides extensive bilingual trigger phrases, and clearly answers both what the skill does and when to use it. It is highly distinct from generic skills with minimal conflict risk.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'evidence tracking, citations, source governance, and multi-pass synthesis' — giving comprehensive coverage of the skill's capabilities rather than vague abstractions.

5 / 5

Completeness

Explicitly answers both 'what' (format-controlled research reports with evidence tracking) and 'when' (when users request a research report, literature review, market/industry analysis, etc.) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides comprehensive natural-language triggers in both English and Chinese ('research this topic', 'write a report on', 'survey the literature on', '帮我调研一下', '深度研究') including synonyms and report-type variants.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — formal multi-pass research reports with citation governance — with distinct trigger phrases, minimal overlap risk, and appropriately third-person voice ('Generate', not 'I/You').

5 / 5

Total

20

/

20

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

skill_md_line_count

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

Warning

Total

15

/

16

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.