SKILLEMALL.ai
GitHub ↗ RU Sign in

AB workflow-to-skill

Converts a proven, repeated professional workflow into a portable and inspectable AI Skill with clear triggers, inputs, steps, outputs, verification, recovery, and limits. Use when a user asks to make a workflow reusable, package a process as a Skill, or preserve a successful multi-step method. Do not use for speculative processes that have not been performed or concretely specified.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 3 files body ≈ 747 tokens Open the sourcegithub.com↗ analyzed 70 min ago

Converts a proven, repeated professional workflow into a portable and inspectable AI Skill with clear triggers, inputs, steps, outputs, verification…

As a process B 73/100 · Nearly there — weak spots: consistency, progress reporting

ProcedureAI and agentstype 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
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
91
Run on models
none yet
Process rating
B
73/100
Nearly there
Progress reporting w 2
0
Consistency w 8
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 3. 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 73/100

    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (workflow-to-skill) differs from the folder (workflow-to-skill-adrian-lerer)
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 19 steps
    • 100Execution cost. Instruction body is 747 tokens
    • 100Running it twice. Mutating operations check current state

    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
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 386: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 19 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.