SKILLEMALL.ai
GitHub ↗ RU Sign in

DF create-master

基于佛教经典文献，生成特定高僧大德的 AI 教学角色

The skillemall take

The skill promises to generate AI personas of Buddhist masters from classical texts. The folder contains 80 files, but code quality scores 41 points and execution process scores 30. Internal links are broken, three medium-level findings detected. The body has only 1570 tokens—sparse for a full generator. No model runs, no sandbox tests.

Safety at 97 is solid, but doesn't fix the core issue. The skill sits in the repo and supports many platforms, yet actual functionality remains untested. Installing it is a gamble: odds are the generated personas will either malfunction or not work at all.

xr843/Master-skill Claude Code author: xr843 80 files · 1 script body ≈ 1 570 tokens Open the sourcegithub.com↗ analyzed 10 h ago

基于佛教经典文献，生成特定高僧大德的 AI 教学角色

As a process F 30/100 · No process to follow — References files that are not bundled: references/teaching-modes.md, references/workflow-details.md, references/source-conventions.md

GeneratorSoftware developmentAI and agentsResearchtype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
75/100
safety, quality, tests
Safety 60%
97
Quality 40%
41
Run on models
none yet
Process rating
F
30/100
No process to follow
References files that are not bundled: references/teaching-modes.md, references/workflow-details.md, references/source-conventions.md
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 Risky intent intent-offensive-security CHANGELOG.md:3590
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    privilege escalation. Now `>=9.0.3,<10`; full suite verified unchanged
  • low Dangerous commands cmd-quarantine-file docs/desktop.en.md:10
    Removes the macOS quarantine flag from one file (usual for a downloaded CLI; make sure the file is the intended binary) (quoted — discussed, not commanded)
    **Download**: [Releases](https://github.com/xr843/Master-skill/releases) provides pre-built binaries for Linux (x86_64), Windows (x86_64) and macOS (Apple Silicon / aarch64 only); run them from the ro
    quoted
  • low Dangerous commands cmd-quarantine-file docs/desktop.md:10
    Removes the macOS quarantine flag from one file (usual for a downloaded CLI; make sure the file is the intended binary) (quoted — discussed, not commanded)
    **下载**：[Releases](https://github.com/xr843/Master-skill/releases) 提供 Linux（x86_64）/ Windows（x86_64）/ macOS（仅 Apple Silicon，aarch64）预编译二进制，需在本仓库克隆的根目录运行（它会调用仓库里的 `scripts/` 与 `bin/`）。v0.12.1 起，Linux /
    quoted

Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/teaching-modes.md
  • warning missing-ref reference to a missing file: references/workflow-details.md
  • warning missing-ref reference to a missing file: references/source-conventions.md
  • warning missing-ref reference to a missing file: references/fojin-api.md
  • warning missing-ref reference to a missing file: references/ethics-runtime.md
  • warning missing-ref reference to a missing file: references/traditions.md

Process rating: all ten parameters 30/100

Will not run. References files that are not bundled: references/teaching-modes.md, references/workflow-details.md, references/source-conventions.md
  • 0Tools and files. 6 referenced file(s) missing: references/teaching-modes.md, references/workflow-details.md, references/source-conventions.md
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (create-master) differs from the folder (Master-skill)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 35 steps
  • 100Execution cost. Instruction body is 1570 tokens
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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)
  • +3Description length 26: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -413 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 35 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 41.