CD external-agents
Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native app over MCP, and round-trip artifacts back into the UI with MCP Apps and deep links. Use when adding an action's `link` builder or `mcpApp`, wiring the `/_agent-native/open` route, exposing an "ingest" action to MCP/A2A, or scaffolding apps from an external agent.
Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot…
As a process D 41/100 · Unfinished process — References files that are not bundled: absoluteUrl, templates/mail/actions/manage-draft.ts
The same skill appears in 9 more places: agent-native, agent-native, agent-native, agent-native, agent-native, agent-native, agent-native, agent-native, agent-native
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6995 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: absoluteUrl - warning
missing-refreference to a missing file: templates/mail/actions/manage-draft.ts - note
frontmatter-keyunknown frontmatter key "scope" - note
edit-residuethe text marks something as outdated (lines 268): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 41/100
- 0Tools and files. 2 referenced file(s) missing: absoluteUrl, templates/mail/actions/manage-draft.ts
- 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
- 20When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6995 tokens
- 85Steps. 42 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (8 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 463: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.