auto-research

Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 well-sequenced and highly actionable, with clear phases, checkpoints, and ready-to-use templates. The main weaknesses are redundancy of the emerging-tech guidance across multiple sections and the absence of progressive disclosure — large templates that could live in reference files are inlined.

Suggestions

Factor the emerging-tech guidance into a single shared block (e.g. a reference file) and reference it from each phase to remove the repeated restatements.

Move the agent prompt template and the synthesis document-structure template into separate reference files (e.g. agent-prompt.md, synthesis-template.md) and link to them from SKILL.md to improve progressive disclosure.

Trim or consolidate the example decomposition, which repeats the emerging-tech framing already covered in Phase 1.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient process instruction, but the 'emerging tech & architectures' guidance is restated across Phase 1, the agent prompt, Phase 3, and the example, adding redundancy that could be tightened; it is not a 1 because it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	It provides copy-paste-ready agent prompt and document-structure templates, explicit parameters ('run_in_background: true'), a naming convention ('research-[thread-slug]'), and concrete save paths, giving fully actionable guidance.	3 / 3
Workflow Clarity	The four phases are clearly sequenced with explicit checkpoints — a user course-correction gate before launching agents, a completion gate before synthesis — plus error-recovery (retry once, document the gap) and fallback behavior, satisfying the validation/checklist anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent), so all content is inline; the large agent-prompt and document-structure templates are content that could be split into separate reference files but is not, matching the 'could be better organized / content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinctive, clearly conveying what the skill does through three concrete actions. Its main weakness is the absence of an explicit 'when to use' trigger clause and limited natural-language trigger variation, which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause to the description, e.g. 'Use when the user asks for strategic research, an investigation, or a deep dive into market, competitive, or technology dynamics.'

Broaden trigger terms in the description to include natural variations users say, such as 'investigate', 'deep dive', and 'strategic analysis'.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural keywords ('strategic research', 'research', 'strategic analysis') but omits common variations a user would say (e.g. 'investigate', 'deep dive'), which appear only in the body, not the description.	2 / 3
Distinctiveness Conflict Risk	'Deep strategic research engine' carves a clear niche with distinct triggers that are unlikely to collide with other skills, matching the distinct-niche anchor.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Commit: 5e9851c

Reviewed: 14 days 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.