SKILLEMALL.ai
GitHub ↗ RU Sign in

BF dataverse-classic-workflow

Read, analyze, compare, edit, copy, and publish Microsoft Dataverse Classic Workflows (the WF4/XAML-based `workflow` table — not Power Automate cloud flows). Use when user says "what does this workflow do", "summarize this workflow", "analyze this workflow against requirements", "compare two workflow XAML files", "diff workflows", "edit this workflow XAML", "add a step to this workflow", "modify a condition in this workflow", "clone this workflow", "copy via Process Template", "scaffold a custom workflow activity", "create a CodeActivity", "write a C# workflow step", "publish this workflow", "activate this workflow", "import this workflow into Dataverse", or works with `mxswa:`/`mcwc:` activities, `mxswa:ActivityReference`, `[bracket]` VB.NET expressions, `pac solution clone`/`unpack`/`pack`/`import`, or spkl `[CrmPluginRegistration]` for workflow assemblies. Capabilities; XAML round-trip-safe edits, ConditionSequence/ConditionBranch/Composite nesting awareness, UserData/VisualBasicValue preservation, Process Template clone workaround for the "Activate" bug, custom workflow activity scaffolding (.NET Framework 4.6.2 + Microsoft.CrmSdk.Workflow), MS Learn citations index, AsyncOperation lifecycle, infinite-loop detection, hierarchical operator dependency analysis, PAC CLI publishing flow. Do NOT use for Power Automate cloud flows (JSON, not XAML), Business Process Flows (workflow category=4), Business Rules (category=2), or general Dataverse plugin development.

ClawHub Agent Skills author: Rick Wilson v1.0.0 MIT-0 14 files body ≈ 2 695 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 43/100 · Will not run — References files that are not bundled: skills/read-workflow/SKILL.md, skills/analyze-workflow/SKILL.md, skills/compare-workflows/SKILL.md

ProcedureInfrastructureSoftware developmentWriting and documentstype 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
83/100
safety, quality, tests
Safety 60%
100
Quality 40%
58
Run on models
none yet
Process rating
F
43/100
Will not run
References files that are not bundled: skills/read-workflow/SKILL.md, skills/analyze-workflow/SKILL.md, skills/compare-workflows/SKILL.md
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. Shorten the description to 1024 characters.
  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 · 0

✓ No critical or high findings

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1484 chars, limit 1024
  • warning missing-ref reference to a missing file: skills/read-workflow/SKILL.md
  • warning missing-ref reference to a missing file: skills/analyze-workflow/SKILL.md
  • warning missing-ref reference to a missing file: skills/compare-workflows/SKILL.md
  • warning missing-ref reference to a missing file: skills/copy-workflow/SKILL.md
  • warning missing-ref reference to a missing file: skills/write-workflow/SKILL.md
  • warning missing-ref reference to a missing file: skills/write-custom-activity/SKILL.md
  • warning missing-ref reference to a missing file: skills/publish-workflow/SKILL.md
  • warning missing-ref reference to a missing file: reference/example-workflow.xaml

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: skills/read-workflow/SKILL.md, skills/analyze-workflow/SKILL.md, skills/compare-workflows/SKILL.md
  • 0Tools and files. 8 referenced file(s) missing: skills/read-workflow/SKILL.md, skills/analyze-workflow/SKILL.md, skills/compare-workflows/SKILL.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 18 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 70Failures and branches. 6 branches
  • 100Steps. 43 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2695 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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

  • +3Description length 1484: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +5Description quotes 17 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 43 items
  • +4Has examples (0 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: clean
This skill gives cautious guidance for managing Dataverse classic workflows and clearly requires user confirmation before file edits or environment-changing commands.
LLM: benign (high) · VirusTotal: benign · 28 May 2026