CF maintain-storybook
Keep Paperclip stories and their downstream catalog aligned with the feature map and production UI. Use to reconcile story drift, classify prototypes, update fixtures, or maintain feature coverage.
The skill promises to keep Paperclip stories aligned with your feature map and production UI, catching story drift and updating fixtures. In practice—two files with instructions, no automation scripts. The checker found broken references and missing files, which immediately questions whether this thing works at all: if the skill can't resolve its own dependencies, trusting its recommendations is a stretch.
Quality score 65 and process score 18 indicate vague descriptions and shaky internal logic. Never ran on models, never tested in sandbox. Install it if you're ready to manually clean up after it and verify every suggestion against your actual project state.
Keep Paperclip stories and their downstream catalog aligned with the feature map and production UI.
As a process F 18/100 · No process to follow — References files that are not bundled: ../../../maps/storybook-map/README.md, ../../../maps/feature-map/README.md, ../../../DESIGN.md
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../maps/storybook-map/README.md - warning
missing-refreference to a missing file: ../../../maps/feature-map/README.md - warning
missing-refreference to a missing file: ../../../DESIGN.md - note
edit-residuethe text marks something as outdated (lines 70): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 18/100
- 0Tools and files. 3 referenced file(s) missing: ../../../maps/storybook-map/README.md, ../../../maps/feature-map/README.md, ../../../DESIGN.md
- 0Steps. Prose only: no discrete steps
- 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
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1608 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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 197: enough signal without eating the budget
- +4Structure: 3 headings
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.