BD setup-code-maintenance-bot
Set up a Paperclip agent and routine that applies a selected code-maintenance skill to a repository and opens pull requests. Use for nightly maintenance bots, scheduled code gardening, or webhook-driven maintenance, using an existing agent or a new hire.
This skill promises to set up a Paperclip agent for automatically applying code-maintenance skills to repositories and opening pull requests on schedule or via webhook. The package contains four files, but broken_references flags missing links—parts of the instructions aren't in place. Quality score 78 and process score 39 suggest the logic works, though imperfectly.
No critical errors, safety at 100, but model testing wasn't run and sandbox didn't verify execution. Supports many platforms including Claude and Cursor. Worth installing if you're prepared to manually locate and restore missing instruction pieces—this isn't a turnkey solution.
Set up a Paperclip agent and routine that applies a selected code-maintenance skill to a repository and opens pull requests.
As a process D 39/100 · Unfinished process — References files that are not bundled: <verified-web-url>
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: <verified-web-url>
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: <verified-web-url>
- 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
- 30Running it twice. 4 mutating operations with no state check
- 75Steps. 3 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1610 tokens
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 254: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 3 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.