openclaw-persona-forge

为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡，输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is well-structured, highly actionable, with a clear sequenced workflow and excellent progressive disclosure via verified reference files. Its only weakness is conciseness: inlined multi-line persona-tone example quotes and the direction table add length that could be offloaded.

Suggestions

Move the per-step multi-line persona voice example quotes ('各步骤的语气参考') into a references file and keep only a one-line pointer in SKILL.md to improve conciseness.

Consider moving the 10-row 虾生方向 table (Step 1) into a reference file, summarizing the categories inline to reduce the core token budget.

Bundle gacha.py into scripts/ (or note its absence) so the '必须执行脚本' instruction has a concrete, present artifact.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic concept padding, but the inlined multi-line persona-tone example quotes ('嗯……这个组合里有一种张力…', '我在这只龙虾身上看到了一道裂缝…') and the 10-row direction table add length that could be tightened or moved to a reference; not score 3 because not every token earns its place, and not score 1 because it avoids explaining things Claude already knows.	2 / 3
Actionability	Gives executable commands ('python3 ${SKILL_DIR}/gacha.py [次数]'), exact temp paths, a safe-name normalization rule, image-skill interface contracts (exit codes, output file), and copy-ready templates in references; fully actionable, not score 2 because guidance is complete rather than pseudocode.	3 / 3
Workflow Clarity	Clear Step 1→6 sequence with a trigger-routing table, explicit degradation matrix ('降级，不中断'), and checkpoints (safe-name normalization before write, retry-once on image failure); not score 2 because validation/feedback steps are explicit.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing to six well-signaled one-level-deep references (identity-tension, boundary-rules, naming-system, avatar-style, output-template, error-handling), all verified to exist; not score 2 because content is appropriately split with clear navigation.	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.

The description is specific, trigger-rich, and complete with explicit use/non-use guidance and a clear, distinctive niche. It is among the strongest descriptions and does not over-claim.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs ('输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词') plus conditional avatar image generation, matching the 'lists multiple specific concrete actions' anchor; not score 2 because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	Explicitly states what it does, what it is for, and adds '不适用于' exclusions alongside an explicit trigger list, clearly answering both what and when; not score 2 because the when-clause is explicit rather than implied.	3 / 3
Trigger Term Quality	Provides rich natural-language triggers users would actually say ('龙虾灵魂、虾魂、养虾灵魂、抽卡、随机龙虾、lobster soul、gacha'), giving good coverage of variations; not score 2 because common natural variants are well covered.	3 / 3
Distinctiveness Conflict Risk	A clear niche (OpenClaw lobster persona forging) with distinct triggers and explicit non-applicability makes conflict with other skills unlikely; not score 2 because the niche and triggers are distinct, not merely 'somewhat specific'.	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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 3 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.