archive-protocol

全局归档协议。只要任务需要写入任何文件（含 PLAN.md、报告、JSON 等归档物），必须按本技能执行 Session→ARCHIVE_ID、TIMESTAMP、双轨路径（根段须为 archives/）、回读校验与状态回执；WebUI 的 archive_grid 必须用 Markdown 中语言标识为 json 的围栏代码块输出。

Quality

88%

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

Quality

Content

100%

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 tight, actionable protocol with executable examples, explicit validation checkpoints, and clear error handling. It is self-contained and well-sectioned, needing no external references for its scope.

Dimension	Reasoning	Score
Conciseness	Lean and directive throughout — it assumes Claude's competence and avoids explaining basic concepts, with every section (path boundaries, archive modes, validation, tool examples) earning its place.	3 / 3
Actionability	Provides copy-paste-ready, executable tool-call JSON examples for both single-file and directory archiving, plus explicit parameter shapes ("kind":"file","sourcePath":"result.json").	3 / 3
Workflow Clarity	Clear sequenced flow for directory archiving with an explicit validation checkpoint ("写入后强制校验…未完成校验前不得声称已成功归档") and a defined error-recovery loop (异常处理 stops on "Archive blocked" and surfaces the reason).	3 / 3
Progressive Disclosure	Single self-contained protocol organized into well-signaled sections with no bundle files to offload; per the simple-skill guidance this structure is sufficient.	3 / 3
	Total	12 / 12 Passed

Description

77%

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 clearly states the protocol's purpose and an explicit trigger, with concrete actions listed. It is somewhat weakened by jargon-heavy trigger terms and a broad activation condition that could overlap with other file-writing skills.

Suggestions

Add plain-language trigger terms users would actually say (e.g. "保存/归档文件、写入 PLAN.md 或报告") alongside the protocol jargon.

Narrow the activation clause from "写入任何文件" to the archiving contexts this skill actually owns to reduce overlap with general file-writing skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Session→ARCHIVE_ID、TIMESTAMP、双轨路径"、"回读校验与状态回执"、"用 Markdown 中语言标识为 json 的围栏代码块输出" — rather than vague language.	3 / 3
Completeness	Answers both what (the archive protocol actions) and when ("只要任务需要写入任何文件…必须按本技能执行"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	"写入任何文件"、"PLAN.md、报告、JSON" are reasonably natural, but the description leans on protocol jargon (Session→ARCHIVE_ID, 双轨路径, archive_grid) and omits common user-facing variations like "保存文件" or "归档".	2 / 3
Distinctiveness Conflict Risk	The archiving niche is fairly specific, but the trigger "写入任何文件" is broad and could overlap with general file-writing skills, so conflict risk is not fully eliminated.	2 / 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: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/ontology/archive-protocol/SKILL.md
Commit: f618458

Reviewed: about 13 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.