BC bug-reproduction
Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. Use when: "reproduce this bug," "minimal reproduction," "repro steps," "find the commit that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." Not for: Classifying/deduplicating/severity-routing existing failures without reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation. Related: ai-bug-triage, ai-test-generation, test-reliability, systematic-debugging, qa-project-context.
Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1140 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5462 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 192, 193): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 64/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 40 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5462 tokens
- 100Steps. 57 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- 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
- +3Description length 1140: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 26 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.