菜单
ADR-053 unified entry skill for running the complete API test chain (feat→apiplan→manifest→spec) with acceptance traceability. Orchestrates sub-skills via Skill tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
ADR-047 governed skill for initializing an API coverage manifest (api-coverage-manifest.yaml) from an api-test-plan, with capability × dimension expansion and four-dimensional status fields.
ADR-047 governed skill for generating structured API test specs from coverage items in api-coverage-manifest.yaml, with evidence_required, anti_false_pass_checks, and cleanup requirements.
ADR-047 governed skill for initializing an E2E coverage manifest (e2e-coverage-manifest.yaml) from an e2e-journey-plan, with four-dimensional status fields and journey-based coverage items.
ADR-047 governed skill for generating structured E2E journey specs from coverage items in e2e-coverage-manifest.yaml, with user steps, UI states, network events, anti_false_pass_checks, and evidence requirements.
ADR-047 governed skill for transforming one frozen FEAT into an API test plan (api-test-plan.md) with capability extraction, dimension matrix, and priority-based cut rules.
ADR-047 governed skill for deriving user journeys from a frozen prototype (or feat) and generating an E2E journey plan (e2e-journey-plan.md) with main journeys and minimum exception journeys.
| name | ll-qa-api-from-feat |
| description | ADR-053 unified entry skill for running the complete API test chain (feat→apiplan→manifest→spec) with acceptance traceability. Orchestrates sub-skills via Skill tool. |
| version | 1.0 |
| adr | ADR-047, ADR-052, ADR-053 |
| category | qa |
| chain | api-test |
| phase | full-chain |
| supersedes | [] |
One-shot skill that runs the complete API test chain from a frozen FEAT document.
feat_freeze_package: directory path from ll-product-epic-to-feat (must be frozen)feat_ref: the specific FEAT identifierssot/tests/api/{feat_id}/api-test-plan.md — Contains Acceptance Traceability tablessot/tests/api/{feat_id}/api-coverage-manifest.yaml — Generated by ll-qa-api-manifest-initssot/tests/api/{feat_id}/api-test-spec/SPEC-*.md — Generated by ll-qa-api-spec-genll-qa-feat-to-apiplan — FEAT → api-test-plan (with Acceptance Traceability)ll-qa-api-manifest-init — api-test-plan → api-coverage-manifestll-qa-api-spec-gen — api-coverage-manifest → api-test-specs--preview: Only run up to api-test-plan, stop before manifest-init--no-spec: Stop after api-coverage-manifest, skip spec-gen--target P0|P1|P2: Filter by prioritySTART → APIPLAN_RUNNING → TRACEABILITY_VALIDATING → MANIFEST_RUNNING → SPEC_RUNNING → COMPLETE
/ll-qa-feat-to-apiplan with feat_freeze_package + feat_ref/ll-qa-api-manifest-init with api-test-plan output path/ll-qa-api-spec-gen with api-coverage-manifest output patherror_handling:
strategy: fail-fast
failure_at:
apiplan: abort
manifest_init: abort
spec_gen: continue # preserve manifest on spec_gen failure
artifacts_on_failure: keep
retry: disabled
validation:
acceptance_traceability:
check_mandatory_mapping: true # each capability must have AC mapping
check_complete_coverage: true # each AC must have at least one capability coverage
fail_on_incomplete: true
validation_point: before_manifest_init
ll-qa-feat-to-apiplan (input validation, acceptance traceability)ll-qa-api-manifest-init (cut rules, four-dimensional status)ll-qa-api-spec-gen (spec completeness)evidence/execution-evidence.schema.jsonevidence/supervision-evidence.schema.json