research-add-fields

向现有调研outline补充字段定义。

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-zh/research-add-fields/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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 lean, well-structured four-step workflow that respects the token budget and assumes Claude's competence, with clear sectioning for a simple self-contained skill. Its weaknesses are concentrated in execution detail: appended-field format/schema and a technical validation checkpoint before the destructive in-place file write.

Suggestions

Show the fields.yaml schema/format (or a concrete appended-field example including 分类 and detail_level) so the append step is copy-paste ready rather than implied.

Add an explicit validation checkpoint after saving — e.g., re-read fields.yaml, confirm it parses and new fields conform to the existing schema, and retry on failure — to convert the destructive write into a validate-fix-retry feedback loop.

Specify how the chosen source maps to output: for option B, state what the web-search-agent should return and how its results are normalized into the fields.yaml format.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean and assumes Claude's competence, with no concept padding (no explanation of what fields.yaml or web search is) and one line per step; every section earns its place, matching 'lean and efficient; every token earns its place'.	3 / 3
Actionability	It provides concrete guidance (the `*/fields.yaml` glob, the named `web-search-agent`, appending to fields.yaml) but omits key details — no fields.yaml schema/format for appended fields and no representation of `detail_level`/分类 — fitting 'some concrete guidance but incomplete; missing key details'; not 1 (not abstract) and not 3 (not copy-paste ready).	2 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–4) with a user-confirmation checkpoint (Step 3 + output '需用户确认'), but the destructive in-place write of fields.yaml lacks explicit technical validation (e.g., verify the YAML parses / fields conform to the existing schema) or an error-recovery loop; per the rubric, missing validation for destructive operations caps this at 2.	2 / 3
Progressive Disclosure	This is a self-contained, under-50-line skill with no need for external references, and its sections (触发方式 / 执行流程 Steps 1–4 / 输出) are well-organized; per the simple_skills note such a skill scores 3 on progressive disclosure with just well-organized sections.	3 / 3
	Total	10 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 a single concise sentence that names a specific action and domain, but it omits any 'Use when...' trigger guidance and lists only one action. It is clearly above the vague baseline yet stops short of the explicit-trigger, multi-action standard the rubric rewards at the top level.

Suggestions

Add a 'Use when...' trigger clause (e.g., 'Use when the user wants to add or supplement field definitions in an existing research outline / fields.yaml') to lift completeness and trigger_term_quality.

List multiple concrete actions (e.g., locate, search, draft, confirm, append) so specificity reaches the multi-action anchor at score 3.

Surface natural trigger keywords users would actually say ('调研outline', 'fields.yaml', '加字段', '补充字段') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('补充字段定义') on a clear domain ('现有调研outline'), matching 'names domain and some actions, but not comprehensive'; it is more specific than 'Helps with documents' (1) but lists only one action rather than multiple specific actions (3).	2 / 3
Completeness	It clearly states WHAT ('向现有调研outline补充字段定义') but provides no WHEN/'Use when' trigger guidance; per the rubric a missing explicit trigger clause caps completeness at 2, while a 1 would lack the 'what' entirely.	2 / 3
Trigger Term Quality	Contains relevant terms ('调研outline', '字段定义') a user might say, but offers no explicit trigger list and misses common variations, fitting 'some relevant keywords but missing common variations'; it is not jargon-only (1) and lacks the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The niche (supplementing research-outline field definitions) is fairly specific and unlikely to broadly conflict, but absent explicit distinct triggers it could overlap with other research/survey skills, matching 'somewhat specific but could still overlap'; not a 3 because it lacks distinct explicit triggers.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (19 chars), consider making it more detailed	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: Weizhena/Deep-Research-skills
Path: skills/research-zh/research-add-fields/SKILL.md
Commit: e5479f8

Reviewed: 11 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.