BF cordis-plugin-development
Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP connection in the current Harness profile, including a shipped plugin that is disabled by default, and for any visual object, decoration, or widget request that names no other destination, which means an installed UI plugin rendered in the Harness Web UI.
A skill for managing plugins in Harness: promises to help design, debug, and configure plugins, bundles, and MCP connections within a profile. Contains 15 modules, two JavaScript scripts, 1922 body tokens. Quality scores are middling: 75 for quality, 33 for process. No critical findings, but broken file references exist. Scripts in sandbox behaved correctly, stayed within their directories.
Low process score hints at documentation or structural gaps. The skill works, but needs vetting before production use—especially if you're configuring mission-critical plugins. Install it, but keep your guard up.
Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP…
As a process F 33/100 · No process to follow — References files that are not bundled: templates/decoration/icon.svg, templates/mcp/icon.svg
How to improve
- 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: 27. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/decoration/icon.svg - warning
missing-refreference to a missing file: templates/mcp/icon.svg
Process rating: all ten parameters 33/100
- 0Tools and files. 2 referenced file(s) missing: templates/decoration/icon.svg, templates/mcp/icon.svg
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1918 tokens
- low The response is described with custom markup (3 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 406: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 8 items
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 2 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
templates/decoration/client.js | ничего за пределами своей папки |
templates/decoration/index.js | ничего за пределами своей папки |
11 Oct 2026