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).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A thorough, actionable research skill with a clear gated pipeline, concrete templates, and well-organized reference files. Its main weakness is redundancy from interleaving the parallel Enterprise (E1–E7) and General (P0–P7) pipelines, which inflates length without adding guidance.

Suggestions

De-duplicate the Enterprise pipeline: the intro sentence at the top of 'Enterprise Research Mode' repeats the earlier one, and the 'E3-E7: Enterprise Analysis, Drafting, and Review' summary re-lists E3/E4/E5 already detailed above — collapse these into a single E1–E7 walkthrough.

Consolidate the six-dimension list: it appears in the E2 overview, again in 'Enterprise Research Integration', and implicitly in the methodology reference — keep one canonical list and point the others to it.

Avoid restating the inline Source Accessibility classification table that also lives in source_accessibility_policy.md; keep only the critical-rule summary in the body and defer the full table to the reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance with no basic-concept explanation, but real redundancy bloats it: the enterprise intro sentence is repeated verbatim, E3/E4/E5 are detailed then re-summarized, and the six-dimension list appears multiple times.	2 / 3
Actionability	Highly executable: concrete status-report strings ('[P0 complete] Subagent: {yes/no}...'), a copy-paste citation-registry template, explicit thresholds (≥30% official, ≤25% single-source share), and a bash dispatch block for the counter-review team.	3 / 3
Workflow Clarity	P0–P7 is clearly sequenced with explicit validation checkpoints (mandatory P6 counter-review with 'find ≥3 issues', P7 registry cross-check / spot-check 5+ claims, quality gates, L1/L2/L3) and feedback loops ('re-examine if 0 found', fix-and-revalidate).	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled one-level-deep references (all 14 referenced files verified present), organized into three 'When to Load' tables for easy navigation; detailed methodology/frameworks/checklists are appropriately split into separate files.	3 / 3
	Total	11 / 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.

A strong, well-structured description that states concrete capabilities, gives explicit bilingual 'use when' triggers, and stays in third-person voice. The only mild blemish is the trailing V6/V6.1 versioning line, which is mildly internal but still names real capabilities.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'format-controlled research reports', 'evidence tracking, citations, source governance, and multi-pass synthesis' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Generate format-controlled research reports...') and when ('This skill should be used when users request a research report, literature review... Triggers: ...'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Provides broad bilingual coverage of natural user phrases ('research this topic', 'write a report on', 'competitive analysis of', '深度研究', '综述报告') that users would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (governed, multi-pass research reports with counter-review) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: e5ac7ba

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.