๐Ÿ“ฆ

qa

์ฝ˜ํ…์ธ  ๋ฆฌ๋น„์ „ r1 ์ค‘๊ฐ„ ์œ„ํ—˜ โš™๏ธ ์™ธ๋ถ€ ๋ช…๋ น์–ด

Run Reliable Repository Quality Gates

Test failures, type errors, and lint issues can be difficult to classify consistently. This skill runs approved checks, retries failures once, and returns structured evidence.

์ง€์›: Claude Codex Code(CC)
Maintain this Skill? Claim it ๐Ÿ“Š 69 ์ ์ ˆํ•จ

๋‚ด ์—์ด์ „ํŠธ๋กœ ์„ค์น˜

์ด ์š”์ฒญ์„ ์—์ด์ „ํŠธ์— ๋ณต์‚ฌํ•˜์„ธ์š”. ๊ณต์‹ Skill ํŽ˜์ด์ง€์™€ ๋งค๋‹ˆํŽ˜์ŠคํŠธ๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.

์—์ด์ „ํŠธ ์š”์ฒญ
Review the Skillstore skill "qa" from https://skillstore.io/skills/drix10-qa.md and its manifest at https://skillstore.io/api/skills/drix10-qa/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

์—์ด์ „ํŠธ๋Š” ๊ณ„์†ํ•ด์„œ ๊ณ„ํš์„ ํ‘œ์‹œํ•˜๊ณ  ๋ณด์•ˆ ์ •์ฑ…์—์„œ ์š”๊ตฌํ•˜๋Š” ํ™•์ธ์„ ์š”์ฒญํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.

์—์ด์ „ํŠธ๊ฐ€ ์ฝ๊ธฐ ์‰ฌ์šด ๋ฆฌ์†Œ์Šค

AI ์—์ด์ „ํŠธ, ํฌ๋กค๋Ÿฌ, ์Šคํฌ๋ฆฝํŠธ๊ฐ€ ์ „์ฒด ํŽ˜์ด์ง€ ๋Œ€์‹  ์ •๋ฆฌ๋œ ์ปจํ…์ŠคํŠธ๋งŒ ํ•„์š”ํ•  ๋•Œ ์ด ๋งํฌ๋ฅผ ์‚ฌ์šฉํ•˜์„ธ์š”.

ํ…Œ์ŠคํŠธํ•ด ๋ณด๊ธฐ

"qa" ์‚ฌ์šฉ ์ค‘์ž…๋‹ˆ๋‹ค. Run the standard checks for issue 42.

์˜ˆ์ƒ ๊ฒฐ๊ณผ:

Passed: test, typecheck, and lint completed successfully on their first runs. No flaky tests were reported.

"qa" ์‚ฌ์šฉ ์ค‘์ž…๋‹ˆ๋‹ค. Run the test command and verify any failure once.

์˜ˆ์ƒ ๊ฒฐ๊ณผ:

Passed with flaky results: the first test run failed, the retry passed, and the affected test name was recorded.

"qa" ์‚ฌ์šฉ ์ค‘์ž…๋‹ˆ๋‹ค. Run the configured checks where lint fails twice.

์˜ˆ์ƒ ๊ฒฐ๊ณผ:

Failed: lint returned a nonzero exit code on both attempts. The bounded raw output and command durations were retained.

๋ณด์•ˆ ๊ฐ์‚ฌ

์ค‘๊ฐ„ ์œ„ํ—˜

All 12 static findings are false positives caused by Markdown backticks, not Ruby or shell backtick execution. The skill still intentionally executes repository checks and dependency installs, which can run repository-controlled code.

1
์Šค์บ”๋œ ํŒŒ์ผ
53
๋ถ„์„๋œ ์ค„ ์ˆ˜
0
๊ฒ€ํ†  ํ•ญ๋ชฉ
0
์˜คํƒ ๋ฌด์‹œ๋จ

ํ™•์ธ๋œ ๋ณด์•ˆ ์šฐ๋ ค ์‚ฌํ•ญ (1)

์ค‘๊ฐ„
Repository-Controlled Command Execution
The skill runs orchestrator or repository-defined checks and may install dependencies. Those operations can execute repository-controlled code despite worktree mutation controls.
Lines 20 through 22 explicitly direct the agent to load commands, install dependencies when needed, and execute each command.
๊ฐ์‚ฌ์ž: codex
์ด ๋ณด๊ณ ์„œ ๊ณต์œ  ๋ฐ ์ธ์šฉ

๋ฒ„์ „์ด ์ง€์ •๋œ ํ‰๊ฐ€ ๋ณด๊ณ ์„œ, ์ค‘๋ฆฝ ๋ฐฐ์ง€, ์ž„๋ฒ ๋“œ ์นด๋“œ ๋ฐ ์ธ์šฉ์„ ๊ณต์œ ํ•˜์„ธ์š”. Skillstore๋Š” ๊ทผ๊ฑฐ๋ฅผ ๋ณด๊ณ ํ•˜์ง€๋งŒ ์ด Skill์˜ ์•ˆ์ „ ์—ฌ๋ถ€๋ฅผ ํŒ๋‹จํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.

๋ฒ„์ „๋ณ„ ๋ณด๊ณ ์„œ ์—ด๊ธฐ
๋ณด์•ˆ ํ‰๊ฐ€

๋ณด๊ณ ์„œ ๋งํฌ ๋ณต์‚ฌ

https://skillstore.io/skills/drix10-qa/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown ๋ฐฐ์ง€

[![Skillstore security assessment](https://skillstore.io/badges/skills/drix10-qa/security.svg)](https://skillstore.io/skills/drix10-qa?utm_source=security_passport_badge)

HTML ๋ฐฐ์ง€

<a href="https://skillstore.io/skills/drix10-qa?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/drix10-qa/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

์ž„๋ฒ ๋“œ ์นด๋“œ

<iframe src="https://skillstore.io/embed/skills/drix10-qa.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
ํ•™์ˆ  ์ธ์šฉ (APA ยท BibTeX ยท CFF)

APA ์ธ์šฉ

drix10. (2026). qa security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/drix10-qa/audits/1

BibTeX ์ธ์šฉ

@techreport{drix10-drix10-qa-2026, author = {drix10}, title = {qa security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/drix10-qa/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "qa security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "drix10" date-released: "2026-09-27" url: "https://skillstore.io/skills/drix10-qa/audits/1" identifiers: - type: other value: "skillstore:drix10-qa:audit:1" description: "Skillstore immutable audit report identifier"

๋ณ€ํ˜• ๋น„๊ต

์„ค์น˜ ๊ฐ€๋Šฅํ•œ ๋ณ€ํ˜• 2๊ฐœ

๊ฐ ์ž‘์„ฑ์ž์˜ ์Šคํ‚ฌ์€ ๋ณ„๋„์˜ ์„ค์น˜ ํ•ญ๋ชฉ์œผ๋กœ ์œ ์ง€๋ฉ๋‹ˆ๋‹ค. ์ถ”์ฒœ ๋ณ€ํ˜•์€ Skillstore ๊ทผ๊ฑฐ๋กœ ์ˆœ์œ„๊ฐ€ ์ •ํ•ด์ง‘๋‹ˆ๋‹ค.

์ด ๋ณ€ํ˜•์ด 1์œ„์ธ ์ด์œ 

Skillstore ์ ์ˆ˜๊ฐ€ ๊ฐ€์žฅ ๋†’์Œ
mattpocock ๊ถŒ์žฅ

mattpocock-qa

Skillstore ์ ์ˆ˜ 77
์ฆ๊ฑฐ ์‹ ๋ขฐ๋„ ์ค‘๊ฐ„
Skillstore ์‚ฌ์šฉ๋Ÿ‰ 8
์—…๋ฐ์ดํŠธ๋จ

2026-09-09

drix10 ํ˜„์žฌ

drix10-qa

Skillstore ์ ์ˆ˜ 69
์ฆ๊ฑฐ ์‹ ๋ขฐ๋„ ์ค‘๊ฐ„
Skillstore ์‚ฌ์šฉ๋Ÿ‰ 6
์—…๋ฐ์ดํŠธ๋จ

2026-10-02

Skillstore ์ ์ˆ˜

์ด ์ ์ˆ˜์˜ ์ด์œ  ์ฆ๊ฑฐ ์‹ ๋ขฐ๋„: ์ค‘๊ฐ„
55
์•„ํ‚คํ…์ฒ˜
85
์œ ์ง€๋ณด์ˆ˜์„ฑ
87
์ฝ˜ํ…์ธ 
65
์ปค๋ฎค๋‹ˆํ‹ฐ
83
์‚ฌ์–‘ ์ค€์ˆ˜

๋งŒ๋“ค ์ˆ˜ ์žˆ๋Š” ๊ฒƒ

Validate an approved change

Run repository checks after review and return evidence for the final merge decision.

Classify intermittent failures

Retry failed checks once and identify tests that pass only on the second run.

Collect structured check results

Capture bounded command output, timing, and exit codes for downstream orchestration.

์ด ํ”„๋กฌํ”„ํŠธ๋ฅผ ์‚ฌ์šฉํ•ด ๋ณด์„ธ์š”

Run the standard quality gate
Run the QA gate for issue {issue_number} in {worktree_path}. Use the configured test, typecheck, and lint commands.
Run specified checks
In {worktree_path}, run these approved commands: {commands}. Retry each failure once and return the required structured result.
Verify a suspected flaky test
Run the approved test command for issue {issue_number}. Retry it once after failure and list first-run tests that pass on retry.
Audit a large verification suite
Run all approved checks in {worktree_path}. Record durations and exit codes, redact credentials, and apply the documented output limits exactly.

๋ชจ๋ฒ” ์‚ฌ๋ก€

  • Provide explicit, reviewed commands through the orchestrator.
  • Run the skill inside the intended restricted QA environment.
  • Review redacted raw output before making a merge decision.

ํ”ผํ•˜๊ธฐ

  • Do not ask the skill to edit code or update snapshots.
  • Do not use commands copied from untrusted test output.
  • Do not treat a single failed run as conclusive when retry data exists.

์ž์ฃผ ๋ฌป๋Š” ์งˆ๋ฌธ

Does this skill fix failing tests?
No. It runs checks and reports results without changing the repository.
How does it identify flaky tests?
It retries each failing command once and records tests that pass only during the retry.
Which commands does it run?
It uses orchestrator-provided commands or configured test, typecheck, and lint commands from AGENTS.md.
Can it install dependencies?
It may perform a clean lockfile-based install when dependencies are missing.
How does it handle long output?
It keeps the first 150 and last 150 lines and marks the omitted section.
How does it protect credentials?
It replaces detected token, key, and password values with a redaction marker.

๊ฐœ๋ฐœ์ž ์„ธ๋ถ€ ์ •๋ณด

์ž‘์„ฑ์ž

drix10

๋ผ์ด์„ ์Šค

MIT

Skillstore ๋ฆฌ๋น„์ „

r1

๋ฒ„์ „ ์•ˆ๋‚ด

์ž‘์„ฑ์ž๊ฐ€ ๋ฒ„์ „์„ ์„ ์–ธํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.

์ฐธ์กฐ

8b5ad1599e7c55e9b6c627bca3f556f6e9061cb1

์œ ์ง€๋ณด์ˆ˜ ์ตœ์‹ ์„ฑ

2026. 9. 30.

์‚ฌ์šฉ๋Ÿ‰

0 ๋‹ค์šด๋กœ๋“œ ยท 0 ์กฐํšŒ

ํŒŒ์ผ ๊ตฌ์กฐ

๐Ÿ“„ SKILL.md