SKILLEMALL.ai
GitHub ↗ RU Sign in

BF add-workiq

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotchatmcp), then wires up a production-ready McpSession wrapper for AI-powered, knowledge-grounded search and chat. Use when integrating Microsoft 365 Copilot search/chat. The CopilotChat tool searches internal Microsoft 365 content (documents, emails, chats, sites, files) across your organization — prefer workload-specific tools (SharePoint, OneDrive, Teams, Mail) when the workload is explicit; do not use it for general knowledge, news, public web, or external information.

microsoft/power-platform-skills Agent Skills author: microsoft 1 file body ≈ 5 385 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shareda365copilotchatmcp), then wires up a production-ready…

As a process F 48/100 · Will not run — References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/cli-binary.md

ProcedureSoftware developmentAI 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
B
85/100
safety, quality, tests
Safety 60%
95
Quality 40%
70
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/cli-binary.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Edit Write Grep Glob Bash LSP TaskCreate TaskUpdate TaskList TaskGet AskUserQuestion Skill

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5385 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ${PLUGIN_ROOT}/shared/shared-instructions.md
  • warning missing-ref reference to a missing file: ${PLUGIN_ROOT}/shared/cli-binary.md

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/cli-binary.md
  • 0Tools and files. 2 referenced file(s) missing: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/shared/cli-binary.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 20 mutating operations with no state check
  • 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
  • 70Execution cost. Instruction body is 5385 tokens
  • 85Steps. 31 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress

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
  • -212 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 593: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 31 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)

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