القائمة
Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | aitask-qa |
| description | Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks |
This is a profile-aware skill stub. Execute these steps in order, then stop:
Resolve active profile. Parse ARGUMENTS for --profile <name>. If
found, use that as <profile> and remove the --profile <name> pair
from ARGUMENTS. Otherwise run:
./.aitask-scripts/aitask_skill_resolve_profile.sh qa
and use the single-line stdout as <profile>.
Render per-profile variant. Run:
./.aitask-scripts/aitask_skill_render.sh aitask-qa --profile <profile> --agent claude
No-op if the per-profile SKILL.md is already up to date.
Dispatch via Read-and-follow. Read the file at
.claude/skills/aitask-qa-<profile>-/SKILL.md and execute its
instructions as if they were this skill, forwarding the (possibly
stripped) ARGUMENTS unchanged.
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
Shadow companion for a followed coding agent — reads its captured terminal output and, in one instruction-driven flow, explains it, helps answer an AskUserQuestion, or critically interrogates a plan. Advisory-only. Spawned by minimonitor; not a task-implementation command.
Draft a manager-facing work report from selected board columns.
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.
