CD cordis-styling-nitpicking
Use during code review of DeepSeek Harness Cordis plugins and helpers reachable from their entrypoints, including pull requests, and during focused lifecycle audits. Checks singleton state, unreversed side effects, and cleanup dependencies released before consumers finish; reports substantiated P0 findings with ownership evidence and deterministic verification.
A skill for DeepSeek Cordis code review that checks singletons, unreversed side effects, and resource cleanup. Promises substantiated P0 findings with ownership evidence.
One file, broken references included. Quality score sits at 68 out of 100—decent but not stellar. Zero critical findings, no medium or low issues either. Models never ran, sandbox untouched. Process score of 43 signals the tool hasn't been stress-tested on real data. No lint errors caught, which might just mean the checks stay shallow.
Use as a first-pass filter for Cordis plugin reviews, not as your only gate. Worth adding to CI/CD if automated singleton analysis fits your workflow; otherwise skip it.
Use during code review of DeepSeek Harness Cordis plugins and helpers reachable from their entrypoints, including pull requests, and during focused lifecycle…
As a process D 43/100 · Unfinished process — References files that are not bundled: ../../../AGENTS.md, ../../../docs/cordis-tutorial/02-lifecycle-and-effects.md, ../../../docs/cordis-tutorial/03-services.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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../AGENTS.md - warning
missing-refreference to a missing file: ../../../docs/cordis-tutorial/02-lifecycle-and-effects.md - warning
missing-refreference to a missing file: ../../../docs/cordis-tutorial/03-services.md - warning
missing-refreference to a missing file: ../../../docs/defensive-patterns/general.md - warning
missing-refreference to a missing file: ../../../vendor/cordis/src/fiber.ts - warning
missing-refreference to a missing file: ../../../vendor/cordis/src/reflect.ts
Process rating: all ten parameters 43/100
- 0Tools and files. 6 referenced file(s) missing: ../../../AGENTS.md, ../../../docs/cordis-tutorial/02-lifecycle-and-effects.md, ../../../docs/cordis-tutorial/03-services.md
- 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. 3 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2196 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 363: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.