Run available lint, type-check, test, and build commands and report results before pull request creation.
From claude-dev-ecosystemnpx claudepluginhub oiranca/claude-dev-ecosystemThis skill is limited to using the following tools:
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
Use this skill to run available project validation checks before opening a pull request.
The skill executes local validation commands and reports their status. This skill does not fix failures.
Validate that the repository passes its core quality checks:
.agent-cache/skill_budget_state.json before rerunning (Max 2 broader validation runs per cycle; max 1 run per skill per cycle)..agent-cache/locks/qa.lock when present before starting overlapping validation.As context is isolated, the Team Lead must ensure access to these paths:
.agent-cache/AGENT_STATE.json.docs/STACK_PROFILE.md (Command discovery source).docs/INVENTORY.md.docs/QA_REPORT.md (If exists).Do not read source files.
docs/STACK_PROFILE.md.SKIP.Run checks in the following sequence. Continue execution even if earlier checks fail:
Classify each check as:
Inspect CI configuration files if present (e.g., .github/workflows/*.yml, gitlab-ci.yml, circle.yml).
The qa-engineer is the owner of the validation results. Upon completion:
docs/QA_REPORT.md.docs/DECISIONS.md including the timestamp.FAIL or TIMEOUT status.