SKILLEMALL.ai
RU Sign in

BF cjg-skill-forge

技能锻造炉 / Skill Forge —— 元技能：**创建、升级、重铸、审计**一个「全球最牛」的 WorkBuddy / AI 技能，并让它越用越强。**锻造**模式：从零打造新技能（带版本反馈环、真实素材覆盖审计、外部标杆对比、自我迭代、生产签批、真机验证）；**审视**模式：10 维加权评分尺，给任何技能（含它自己）打分，判断够不够好；**重铸**模式：审计并整合本机重叠技能、合并同类、整理技能库，给出重铸计划与推荐基座；还能让技能更 AI 易读（清晰化）。当你想"做到最牛"、创建一个 XX 技能、升级我的技能、review this skill、整理技能、合并同类、skill 怎么改、SKILL.md 怎么写、怎么制作一个 AI 技能时，用它。 Meta-skill to forge, upgrade, review, recast and refactor world-class WorkBuddy/AI skills — create a new skill from scratch, score any skill with a 10-dimension rubric, consolidate overlapping skills, and make skills more AI-readable. Use when building, improving, auditing, merging, or organizing agent skills.

ClawHub Agent Skills author: J-levee v3.1.2 MIT-0 68 files body ≈ 1 694 tokens Open the sourceclawhub.ai↗ analyzed 24 h ago

技能锻造炉 / Skill Forge —— 元技能：创建、升级、重铸、审计一个「全球最牛」的 WorkBuddy / AI 技能，并让它越用越强。锻造模式：从零打造新技能（带版本反馈环、真实素材覆盖审计、外部标杆对比、自我迭代、生产签批、真机验证）；审视模式：10…

As a process F 35/100 · Will not run — References files that are not bundled: references/*, scripts/*.py, scripts/run_verified.py

AnalyzerAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
97
Quality 40%
66
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/*, scripts/*.py, scripts/run_verified.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • low Dangerous commands cmd-pipe-to-shell references/yunding-security-audit.md:13
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
    | 典型检查 | config.json 去 email、`__pycache__` 不进包、死链修复 | `curl | bash`、未固定版本全局安装、读 `~/.ssh` 外送 |
    tablesecurity skill
  • low Dangerous commands cmd-pipe-to-shell references/yunding-security-audit.md:48
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
    | 自动下载+执行远程脚本（`curl | bash`） | 固化到本地或加 checksum 校验（仍有固有风险，建议人工确认） |
    tablesecurity skill

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 60. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/*
  • warning missing-ref reference to a missing file: scripts/*.py
  • warning missing-ref reference to a missing file: scripts/run_verified.py
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/*, scripts/*.py, scripts/run_verified.py
  • 0Tools and files. 3 referenced file(s) missing: references/*, scripts/*.py, scripts/run_verified.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1694 tokens
  • 100Progress reporting. Reports progress
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -36 of 22 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 645: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 20 items
  • +4Reference files are cited in the instructions (20 of 21)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This is a real skill-building toolkit, but it bundles broad local telemetry, cloud-sync behavior, and unsafe validation paths that users should review before installing.
LLM: suspicious (high) · 27 Aug 2026