CtrlK
BlogDocsLog inGet started
Tessl Logo

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。 Use when creating, designing, or customizing an OpenClaw lobster persona — identity, SOUL.md, name, or avatar prompt.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 overview that pushes detail into real one-level-deep reference files and sequences a clear multi-step workflow with error fallbacks. Its main weakness is mild verbosity in the persona tone-guide examples, which could be tightened without losing the skill's character.

Suggestions

Compress the "对话语气指南" per-step example utterances into one representative template each; the six full sample monologues inflate token cost without proportional guidance value.

Add an explicit verification checkpoint in Step 6 (e.g., confirm SOUL.md/IDENTITY.md were written and re-read them) so the file-generation workflow has a clear feedback loop.

Tighten the optional-依赖 生图 skill section — the interface contract is described twice (here and in Step 5); consolidate to avoid redundancy.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concepts Claude already knows, but the "对话语气指南" section with multiple multi-line example utterances per step is somewhat padded even though it serves the character-driven purpose; minor trimming possible.

4 / 5

Actionability

Provides concrete executable guidance — `python3 ${SKILL_DIR}/gacha.py [次数]`, a 10-row direction table, file-write steps, and linked templates — with only minor gaps (e.g., gacha.py argument edge cases).

4 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced with a trigger-routing table and an error-handling降级 table with retry/fallback; checkpoints are mostly present, though verification of generated files is only implicit in Step 6.

4 / 5

Progressive Disclosure

Well-signaled one-level-deep references — each Step links to a real file in references/ (identity-tension.md, boundary-rules.md, naming-system.md, avatar-style.md, output-template.md, error-handling.md) — with the body acting as a clear overview and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

100%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 is exemplary: it states concrete capabilities, provides extensive natural trigger terms in both Chinese and English, explicitly covers both what and when, and carves out a distinct niche with explicit exclusions. Voice is appropriately third-person.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete outputs — "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 the optional avatar image generation, giving comprehensive coverage of capabilities.

5 / 5

Completeness

Clearly answers both "what" (锻造完整方案 + enumerated outputs) and "when" ("当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用" plus the English "Use when creating, designing, or customizing..."), with explicit concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including Chinese synonyms (龙虾灵魂/虾魂/养虾灵魂), English variants (lobster soul/lobster character), and mode triggers (抽卡/gacha/随机龙虾), matching the level-5 anchor of synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (OpenClaw lobster persona) with an explicit "不适用于" exclusion list (微调已有 SOUL.md / 非 OpenClaw 平台 / 纯工具型 Agent), minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.