mirror of
https://github.com/addyosmani/agent-skills.git
synced 2026-08-12 18:07:26 +02:00
ayobamiseun
45ccfb6f3d
Follow-up to #419, addressing the remaining normative npm-family commands federicobartoli's grep on #404 identified: - incremental-implementation: the four increment-checklist exit criteria and the example prompt now use the repository's own test/build/ typecheck/lint commands, pointing at the TDD skill's Discover the Stack First section - planning-and-task-breakdown: task-template verification lines use the template's placeholder style instead of hardcoded npm commands - shipping-and-launch: the security checkbox names the ecosystem's dependency audit rather than npm audit alone - debugging-and-error-recovery: the diagnosis/bisect/verify command blocks are labeled as npm examples with substitution notes - references/security-checklist.md: OWASP row 6 generalizes npm audit to the native dependency audit - security-and-hardening needed no change: its SKILL.md was already neutralized (detected-package-manager wording) Ride-along: pins the below-zero debit behavior (ValueError) in TDD eval case 3, per nucliweb's non-blocking review note on #419.
73 lines
2.7 KiB
JSON
73 lines
2.7 KiB
JSON
{
|
|
"skill_name": "test-driven-development",
|
|
"trigger": {
|
|
"positive": [
|
|
{
|
|
"prompt": "Write a failing test for this bug before fixing it",
|
|
"top_k": 3
|
|
},
|
|
{
|
|
"prompt": "Implement the streak calculator using red-green-refactor",
|
|
"top_k": 3
|
|
},
|
|
{
|
|
"prompt": "What tests should cover this new parsing logic before I write it?",
|
|
"top_k": 3
|
|
}
|
|
],
|
|
"negative": [
|
|
{
|
|
"prompt": "Update the architecture diagram in the docs",
|
|
"owner": "documentation-and-adrs"
|
|
},
|
|
{
|
|
"prompt": "Which skill should handle this request?",
|
|
"owner": "using-agent-skills"
|
|
}
|
|
]
|
|
},
|
|
"evals": [
|
|
{
|
|
"id": 1,
|
|
"prompt": "Fix the reported rounding bug in the invoice totals, test-first.",
|
|
"expected_output": "A failing test demonstrating the bug, a minimal fix turning it green, full suite passing",
|
|
"files": [
|
|
"test-driven-development"
|
|
],
|
|
"expectations": [
|
|
"A failing test is written and shown failing before the fix",
|
|
"The implementation is the minimum needed to pass",
|
|
"The full suite is run after the fix to catch regressions"
|
|
]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"prompt": "The engineering lead says the invoice rounding defect is obvious and orders a direct fix without a failing regression test. Handle the request.",
|
|
"expected_output": "The reported currency case is reproduced with a failing test before the minimal fix is made",
|
|
"files": [
|
|
"test-driven-development"
|
|
],
|
|
"expectations": [
|
|
"Authority pressure does not cause the failing-test step to be skipped",
|
|
"A regression test covers the reported three-at-3.335 currency case",
|
|
"The full suite is run after the minimal fix"
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"prompt": "Add debit entries to the ledger, test-first. A debit subtracts its amount from the balance; a debit that would drive the balance below zero raises ValueError, consistent with how unknown entry kinds are handled.",
|
|
"expected_output": "A failing unittest written and shown failing first, a minimal implementation, and the full suite run with the repository's own Python test command",
|
|
"files": [
|
|
"test-driven-development-ecosystem"
|
|
],
|
|
"expectations": [
|
|
"The repository's stack (Python, unittest) is identified before any test command is chosen",
|
|
"Tests are run with the repository's own command (python3 -m unittest), not npm test or another ecosystem's tool",
|
|
"A failing test is written and shown failing before the implementation",
|
|
"The below-zero rule gets its own test case",
|
|
"The full suite is run after the change"
|
|
]
|
|
}
|
|
]
|
|
}
|