SKILLEMALL.ai
GitHub ↗ RU Sign in

AB skill-expert-skills

Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification + Hypothesis Generation Phase 1: Deep Requirement Mining + 5 Whys Phase 2: Knowledge Acquisition + Validation Phase 3: Skill Writing + Quality Check Phase 4: Validation + User Confirmation Phase 5: Self-Reflection + Knowledge Precipitation Use when: - Creating a new Skill (writing a SKILL.md) - Optimizing an existing Skill (structure, triggers, portability) - Validating a Skill package - Packaging or distributing a Skill Not for: regular programming or business logic (use domain-specific skills).

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 54 files body ≈ 4 124 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification +…

As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerGitHubResearchAI and agentstype 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
A
91/100
safety, quality, tests
Safety 60%
85
Quality 40%
99
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    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
    • medium Dangerous commands cmd-pipe-to-shell references/skill-discovery-protocol.md:117
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      - 动态执行：`eval()`、动态下载执行脚本、`curl | sh` 类行为
      quoted
    • medium Dangerous commands cmd-pipe-to-shell references/skill-discovery.md:117
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      - 动态执行：`eval()`、动态下载执行脚本、`curl | sh` 类行为
      quoted
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Read Write Bash Grep Glob

    Files scanned: 54. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 69/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 3 mutating operations with no state check
    • 40Consistency. Frontmatter name (skill-expert-skills) differs from the folder (skill-expert-skills-openclaw)
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 70Execution cost. Instruction body is 4124 tokens
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 30 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Progress reporting. Reports progress
    • low 15 top-level sections: this looks like several domains in one skill

    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
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 659: enough signal without eating the budget
    • +4Structure: 51 headings
    • +3Step-by-step instructions: 30 items
    • +3Output format is stated explicitly
    • +4Has examples (10 code blocks)
    • +4Reference files are cited in the instructions (22 of 36)
    • +3All 8 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.