BD dsh-pre-push-checks
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.
This skill picks the smallest test set before pushing to deepseek-harness without running the full repository suite. It promises to filter checks based on changed code and work after gh stack sync. One instruction file with 2650 tokens, no scripts. Grade B: quality 75, process 41. No critical errors, but broken file references—the instruction points to files that don't exist in the folder. Supports all major platforms from Claude to OpenClaw.
Install it if you work with deepseek-harness and verify that all instruction links point to real files first. Otherwise it sends you nowhere. Useless for other repos.
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync…
As a process D 41/100 · Unfinished process — References files that are not bundled: ../dsh-ci-test-reliability/SKILL.md, ../../../packages/test-support/remote-mock/README.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: ../dsh-ci-test-reliability/SKILL.md - warning
missing-refreference to a missing file: ../../../packages/test-support/remote-mock/README.md
Process rating: all ten parameters 41/100
- 0Tools and files. 2 referenced file(s) missing: ../dsh-ci-test-reliability/SKILL.md, ../../../packages/test-support/remote-mock/README.md
- 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
- 30Running it twice. 34 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2729 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (4 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
- +1No license
- +2Single-language instructions
- +3Description length 322: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.