google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
ln-500-story-quality-gate
Story-level quality gate with 4-level verdict (PASS/CONCERNS/FAIL/WAIVED) and Quality Score. Use when Story is ready for quality assessment.
Full skill instructions
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Ifshared/is missing, fetch files via WebFetch fromhttps://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.
Type: L2 Coordinator Category: 5XX Quality
Runtime-backed gate coordinator. Owns fast-track routing, quality/test summaries, final Story verdict, and branch finalization.
| Input | Required | Source | Description |
|---|---|---|---|
storyId | Yes | args, git branch, kanban, user | Story to process |
Resolution: Story Resolution Chain.
Status filter: To Review
ln-510-quality-coordinatorln-520-test-planner when neededPASS | CONCERNS | FAIL | WAIVEDDone only on passing outcomes.hex-skills/story-gate/runtime/MANDATORY READ: Load shared/references/environment_state_contract.md, shared/references/storage_mode_detection.md, shared/references/input_resolution_pattern.md
MANDATORY READ: Load shared/references/coordinator_runtime_contract.md, shared/references/story_gate_runtime_contract.md, shared/references/coordinator_summary_contract.md, shared/references/loop_health_contract.md
MANDATORY READ: Load shared/references/git_worktree_fallback.md
MANDATORY READ: Load references/minimum_quality_checks.md
Runtime CLI:
node shared/scripts/story-gate-runtime/cli.mjs start --story {storyId} --manifest-file .hex-skills/story-gate/manifest.json
node shared/scripts/story-gate-runtime/cli.mjs status
node shared/scripts/story-gate-runtime/cli.mjs record-quality --payload '{...}'
node shared/scripts/story-gate-runtime/cli.mjs record-test-status --payload '{...}'
node shared/scripts/story-gate-runtime/cli.mjs record-stage-summary --story {storyId} --payload '{...}'
node shared/scripts/story-gate-runtime/cli.mjs checkpoint --phase PHASE_6_VERDICT --payload '{...}'
node shared/scripts/story-gate-runtime/cli.mjs advance --to PHASE_7_FINALIZATION
| Verdict | Meaning | Action |
|---|---|---|
PASS | All checks passed | Story -> Done |
CONCERNS | Minor issues, accepted risk | Story -> Done with comment |
FAIL | Blocking issues found | Create follow-up tasks; Story does not go to Done |
WAIVED | User-approved exception | Story -> Done with waiver evidence |
storyId and task_provider..hex-skills/runtime-artifacts/runs/*/story-quality/{storyId}.json:
verdict=FAIL, load payload.metadata.rework_hint as previous_cycle context.cycle_number (1-based, incremented from prior artifact count).story_idtask_providerproject_rootworktree_dirbranchfast_track_policynfr_policytest_task_policyprevious_cycle (null or loaded rework_hint)cycle_numberPHASE_0_CONFIG.PHASE_1_DISCOVERY.fast_track=true only when readiness explicitly allows it.PHASE_2_FAST_TRACK with:
fast_trackchildRunId = {parent_run_id}--ln-510--{storyId}childSummaryArtifactPath = .hex-skills/runtime-artifacts/runs/{parent_run_id}/story-quality/{storyId}.jsonnode shared/scripts/quality-runtime/cli.mjs start --story {storyId} --manifest-file .hex-skills/story-gate/ln-510--{storyId}_manifest.json --run-id {childRunId}PHASE_3_QUALITY_CHECKS with:
child_run.worker=ln-510child_run.run_id={childRunId}child_run.summary_artifact_path={childSummaryArtifactPath}child_run.phase_context=quality_checksln-510-quality-coordinator with managed transport inputs:
Skill(skill: "ln-510-quality-coordinator", args: "{storyId} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")Skill(skill: "ln-510-quality-coordinator", args: "{storyId} --fast-track --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")--previous-cycle-focus "{blocking_categories}" when previous_cycle is not nullstory-quality artifact only, then record-quality.PHASE_3_QUALITY_CHECKS with the recorded quality summary.PHASE_6_VERDICT.ln-520ln-520Done | SKIPPED | VERIFIED) -> checkpoint as reusedln-520, compute:
childRunId = {parent_run_id}--ln-520--{storyId}childSummaryArtifactPath = .hex-skills/runtime-artifacts/runs/{parent_run_id}/story-tests/{storyId}.jsonnode shared/scripts/test-planning-runtime/cli.mjs start --story {storyId} --manifest-file .hex-skills/story-gate/ln-520--{storyId}_manifest.json --run-id {childRunId}PHASE_4_TEST_PLANNING with:
child_run.worker=ln-520child_run.run_id={childRunId}child_run.summary_artifact_path={childSummaryArtifactPath}child_run.phase_context=test_planningln-520-test-planner with managed transport inputs:
Skill(skill: "ln-520-test-planner", args: "{storyId} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")Skill(skill: "ln-520-test-planner", args: "{storyId} --simplified --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")story-tests artifact only, then record-test-status.PHASE_4_TEST_PLANNING.Done, pause runtime:
phase = PAUSEDresume_action = wait for test task completionDone, SKIPPED, or VERIFIEDPHASE_5_TEST_VERIFICATION with:
test_task_statusquality_score.AC- prefixed issue. Common failures: infrastructure exists but nothing exposes it (missing segment 2), mechanism exists but the actor's system can't find it (missing segment 3), mechanism is discoverable but the actor's system doesn't know when or how to use it (missing segment 4). If any AC- issue is found: verdict MUST be FAIL; create fix tasks for the missing segments.FAIL:
DonePHASE_6_VERDICT with:
final_resultquality_scorenfr_validationfix_tasks_createdFor PASS | CONCERNS | WAIVED:
Done.For FAIL:
PHASE_7_FINALIZATION with status=requires_rework.After finalization, write a Stage 3 coordinator artifact with:
summary_kind=pipeline-stagestage=3story_idstatus=completedfinal_resultstory_statusverdictquality_scorewarningsmetadata.rework_hint — when verdict is FAIL, include:
rework_tasks: list of created follow-up task IDsblocking_categories: list of issue categories that caused FAIL (e.g. ac_gap, security, regression)suggested_focus: concise one-line description of what the rework cycle should prioritizeBuild final checklist from runtime state:
ln-510Checkpoint PHASE_8_SELF_CHECK with pass=true|false.
Complete runtime only after pass=true.
| Phase | Worker | Purpose |
|---|---|---|
| 3 | ln-510-quality-coordinator | Code quality, agent review, regression, log analysis |
| 4 | ln-520-test-planner | Research/manual/auto test planning |
childRunId = "{parent_run_id}--ln-510--{storyId}"
childSummaryArtifactPath = ".hex-skills/runtime-artifacts/runs/{parent_run_id}/story-quality/{storyId}.json"
node shared/scripts/quality-runtime/cli.mjs start --story {storyId} --manifest-file .hex-skills/story-gate/ln-510--{storyId}_manifest.json --run-id {childRunId}
node shared/scripts/story-gate-runtime/cli.mjs checkpoint --phase PHASE_3_QUALITY_CHECKS --payload '{"child_run":{"worker":"ln-510","run_id":"{childRunId}","summary_artifact_path":"{childSummaryArtifactPath}","phase_context":"quality_checks"}}'
Skill(skill: "ln-510-quality-coordinator", args: "{storyId} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")
childRunId = "{parent_run_id}--ln-520--{storyId}"
childSummaryArtifactPath = ".hex-skills/runtime-artifacts/runs/{parent_run_id}/story-tests/{storyId}.json"
node shared/scripts/test-planning-runtime/cli.mjs start --story {storyId} --manifest-file .hex-skills/story-gate/ln-520--{storyId}_manifest.json --run-id {childRunId}
node shared/scripts/story-gate-runtime/cli.mjs checkpoint --phase PHASE_4_TEST_PLANNING --payload '{"child_run":{"worker":"ln-520","run_id":"{childRunId}","summary_artifact_path":"{childSummaryArtifactPath}","phase_context":"test_planning"}}'
Skill(skill: "ln-520-test-planner", args: "{storyId} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")
- Start ln-500 runtime (pending)
- Load Story/test-task metadata (pending)
- Decide fast-track mode (pending)
- Start ln-510 child runtime, checkpoint child_run, and record quality summary (pending)
- Start or reuse ln-520 child runtime, checkpoint child_run, and record test-planning summary (pending)
- Verify test task readiness (pending)
- Calculate final verdict (pending)
- Finalize Story/branch state and Stage 3 artifact (pending)
- Run runtime self-check and complete (pending)
ln-510 and ln-520 are consumed only through summary JSON artifacts.FAIL is a valid terminal gate result if follow-up actions are recorded correctly.ln-1000 consumes the Stage 3 coordinator artifact, not free-text stage output.Done only on PASS, CONCERNS, or WAIVED.ln-510 summary recorded in runtimeln-520 summary recorded or reused deterministicallyDone only for passing outcomes, or follow-up tasks created for FAILMANDATORY READ: Load shared/references/meta_analysis_protocol.md
Skill type: execution-orchestrator. Run after phases complete. Output to chat using the execution-orchestrator format.
shared/references/coordinator_runtime_contract.mdshared/references/story_gate_runtime_contract.mdshared/references/coordinator_summary_contract.mdreferences/minimum_quality_checks.md../ln-510-quality-coordinator/SKILL.md../ln-520-test-planner/SKILL.mdVersion: 7.0.0 Last Updated: 2026-02-09
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.