research

为给定问题挑选“最适合回答的人”的专家角色，并用该角色给出回答（含选择理由与行动清单）

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research/SKILL.md

Quality

Content

56%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 instruction skill with explicit gates and a feedback loop, but it is noticeably verbose due to repeated restatement of the same gate rules and lacks any progressive disclosure into separate files.

Suggestions

Consolidate the gate logic into one authoritative section (阶段门槛) and have 执行步骤 and the Answer stage reference it instead of restating it, cutting significant tokens.

Collapse the three footer variants into one rule with conditional path placeholders to remove redundancy.

Consider moving the plan-file template and output-format spec into a referenced file under references/ so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The same gate logic is restated three times ("阶段门槛", "执行步骤 4. 门槛判断", and the Answer-stage rules) and the footer is spelled out in three near-identical variants, which is noticeable padding; it does not reach 3 because the redundancy is substantial rather than a single trimmable section.	2 / 5
Actionability	Concrete file paths (docs/plans/YYYY-MM-DD-research-<slug>-plan.md), a 9-item plan template, a slug rule, and a fixed output-format structure give mostly executable guidance with only minor gaps; it is not 5 because some steps remain high-level ('提炼主题、成功标准、约束条件') without a worked example.	4 / 5
Workflow Clarity	The sequence has explicit gates (stop at Checklist if待确认问题非空) and a genuine feedback loop (二次澄清→Follow-up Checklist→重答) with a termination condition, matching the 'clear sequence with most checkpoints' anchor; it is not 5 because the redundant restatements slightly muddy the single authoritative flow.	4 / 5
Progressive Disclosure	There are no bundle files and no external references; the ~120-line body inlines the plan template and output format under decent section headers, fitting 'some structure but content that could be separate is inline'; the over-50-lines simple-skill exception does not apply, so it stays at 3 rather than higher.	3 / 5
	Total	13 / 20 Passed

Description

42%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 conveys a clear 'what' but omits any 'when to use it' trigger guidance, which caps completeness and leaves trigger terms generic. It is distinguishable but would benefit from explicit usage triggers.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks a question and wants an expert-style answer with rationale and an action plan.'

Replace generic terms ('问题', '专家角色') with phrases users actually say, such as 'ask an expert', 'who would best answer this', or 'expert opinion with action steps'.

Tighten specificity by stating the output shape concretely (e.g. 'produces an expert persona, a rationale, and a 3–5 item action checklist').

Dimension	Reasoning	Score
Specificity	Names the domain (expert-role selection) and several concrete deliverables — "挑选专家角色", "给出回答", "含选择理由", "行动清单" — but the actions stay high-level without specifying what kind of answer or output, so it falls at the 3 anchor rather than 4.	3 / 5
Completeness	It clearly states the 'what' (pick an expert role and answer with rationale + action checklist) but provides no 'when' / trigger guidance, which per the judging guidelines caps completeness at 3; it is not 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Only generic keywords ("问题", "专家角色") appear and there is no "Use when..." clause; the phrasing describes capability rather than natural phrases a user would actually say, matching the 'one or two generic keywords' anchor and not reaching 3 which requires more relevant coverage.	2 / 5
Distinctiveness Conflict Risk	The expert-persona-answering niche is somewhat specific and unlikely to collide with file-handling skills, but the generic 'answer a question' framing could still overlap with general Q&A or research skills, fitting the 'somewhat specific but could overlap' anchor.	3 / 5
	Total	11 / 20 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: Leo-stone-dot/my_life_agent
Path: skills/research/SKILL.md
Commit: ae15870

Reviewed: ~24 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.