BF debug-app
Use when the user has finished building a mobile app, started Metro with `npm run dev`, and wants the running app monitored for runtime errors AND silent failures (empty lists, blank screens, swallowed network errors) and fixed autonomously. Accepts a free-text symptom (e.g., `/debug-app "todos not appearing on home screen"`) to drive persisted-log diagnostics — injects temporary console.log statements at data-path boundaries, reads the sanitized `.powernative/metro-logs/` log, and cleans up logs after the root cause is fixed. Supports port/platform filtering, configurable clean-cycle and timeout limits, and watch-only `--no-fix` mode. Otherwise polls with a durable byte cursor, fixes inline or routes appropriately, verifies each fix from new output, and exits after the configured clean checks (default 3). Foreground loop — blocks the conversation while running. Run only after the app is loaded.
Use when the user has finished building a mobile app, started Metro with npm run dev, and wants the running app monitored for runtime errors AND silent…
As a process F 49/100 · Will not run — References files that are not bundled: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/skills/add-dataverse/references/dataverse-reference.md, ../add-dataverse/references/dataverse-reference.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Edit Write Grep Glob Bash AskUserQuestion WebFetch mcp__plugin_mobile-app_microsoft-learn__microsoft_docs_search
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 21964 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/shared/shared-instructions.md - warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/skills/add-dataverse/references/dataverse-reference.md - warning
missing-refreference to a missing file: ../add-dataverse/references/dataverse-reference.md - warning
missing-refreference to a missing file: ${PLUGIN_ROOT}/shared/references/javascript-dependency-planning.md - note
edit-residuethe text marks something as outdated (lines 167, 180, 393, 564, 565): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Tools and files. 4 referenced file(s) missing: ${PLUGIN_ROOT}/shared/shared-instructions.md, ${PLUGIN_ROOT}/skills/add-dataverse/references/dataverse-reference.md, ../add-dataverse/references/dataverse-reference.md
- 0Result and completion. Does not say what the result is
- 10Execution cost. Instruction body is 21964 tokens: crowds the task out of the window
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Steps. 201 steps, 4 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (45 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)
- +3Description length 908: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 38 headings
- +3Step-by-step instructions: 201 items
- +4Has examples (37 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.