Install
$ agentstack add skill-evolplus-talos-qa-author-by-us ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
QA Author By-US
Use
Use this skill for QA-Author by-us mode. Load test-case-author first for TC format and coverage rules, then ui-test-execution for executable spec conventions.
Inputs
- Signed-off
docs/SRS.md - Per-US files at
docs/user-stories/.md - Linked FR files as needed
- Optional scope filter of US IDs
- Pass number:
1or2
Pass 1 Procedure
- For each in-scope US, read its Description, Main Flow, Business Rules, Post-conditions, and Acceptance Scenarios.
- Write
docs/test-cases/by-us//functional.md. - Cover:
- happy path Main Flow;
- every Business Rule;
- every Post-condition;
- negative cases for auth, payments, integrations, retries, and background jobs.
- Fill each TC's
Executable:path. - Author executable spec scaffolding at the
Executable:path. Use one test per TC ID and keep the TC ID at the start of the runner test name. - For non-UI tests, write full assertions.
- For UI tests:
- Use selectors from
docs/instrumentation-contract.mdwhen available. - If a needed selector is missing, write a literal
TODO: instrumentation-contract --marker in the framework's comment syntax and file a paireddocs/open-issues.mdentry withCategory: selector-pending-contract.
- Emit
plan-update.jsonnotes with selector TODO count.
Pass 2 Procedure
- Read
docs/instrumentation-contract.md. - For every dispatched TC/spec carrying
TODO: instrumentation-contract, replace the marker with the declared selector. - If a selector is still missing from the contract, keep the marker and raise/update an open issue against SA.
- Reverse-check coverage: every contract ID for the affected surface should appear in at least one spec. File
instrumentation-coverage-gapfor unused IDs. - Resolve paired
selector-pending-contractissues that were fully backfilled. - Emit
plan-update.jsonnotes with selectors backfilled and issues resolved.
Marker Syntax
Use the literal marker so QA-Exec can grep it:
| Runner | Marker | |---|---| | Playwright / Detox / Patrol / XCUITest / Espresso / AltTester | // TODO: instrumentation-contract -- | | Maestro YAML | # TODO: instrumentation-contract -- |
Hard Rules
- Translate signed-off Acceptance Scenarios; do not invent new scenarios.
- Do not invent selectors.
- Pass 1 specs with TODO markers are intentionally unrunnable.
- Every executable TC must have a spec file.
- Commit before signaling done.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: evolplus
- Source: evolplus/talos
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.