菜单
Analyze and map inter-repository dependencies when multiple codebases are modernization sources. Scans routes and client requests, identifies dangling external links, and validates contract matches. Use when: "joining repositories", "mapping multi-repo interfaces", "verifying inter-app dependencies".
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
Validates the requirements graph against the wicked-estate code graph before the blueprint phase. Checks every requirement's legacy field resolves to a real program node in the graph (not a JCL step), finds uncaptured behavior-bearing nodes with business logic that need requirements, and flags duplicate program references. Blocks if errors are found; warns and requires human review if only gaps remain. Run after extraction/graph-translator, before blueprint. Use when: "validate requirements graph", "audit the graph", "check graph accuracy", "are we missing any programs", "graph audit before dev", "validate before blueprint".
Apply structural lenses to the legacy code graph to identify entry points, domain boundaries, shared data coupling, operational modes (batch vs online), and risk hotspots. Queries the wicked-estate code graph via the helper (never raw SQLite, never legacy_graph.json). Produces an analysis report. Use when: "analyze the legacy code", "identify entry points", "find domain boundaries", "what are the hotspots", "classify the programs".
Pre-build threat modeler — the adversarial half of the Phase Execution Protocol (PEP, AGENTS.md §10). Given a phase plan and its threat surface, generates a structured threat list BEFORE the producer runs so the producer can address each threat in its output rather than discovering the gap post-build. CRITICAL threats block the phase from advancing until the producer acknowledges them (fix or documented waiver). MEDIUM/MINOR are advisory. Distinct from anti-legacy:adversarial-review (which reviews rendered output AFTER production) — the antagonist attacks the plan BEFORE production, while it is still cheap to change. Use when: any phase producer is about to run; "antagonist check"; "threat model this phase"; "what could go wrong"; PEP step 3 in orchestrate.
The anti-legacy pipeline internals SME, and the home of the shared antilegacy_core Python library. Use when: understanding or operating the pipeline core, diagnosing a core module (estate seam, requirements-graph builder, coverage, manifest state machine, validator), checking pipeline readiness, or extending antilegacy_core.
Map the Requirements Graph to a target state architecture blueprint. Defines the modern package structure, API surface (REST/gRPC), database schemas, class boundaries, and repository patterns for the target stack. Produces blueprint.json + blueprint.md. Use when: "design the target architecture", "create the blueprint", "map requirements to target stack", "design the Spring Boot structure", "what does the modern version look like".
Render the full stakeholder DELIVERABLES package once the requirements graph is ready — product requirements (PRD), architecture diagrams, detailed test strategy, functional test scripts, end-to-end migration plan, and the living risk / decisions / evidence logs — into .anti-legacy/deliverables/, then compile an index. Register-only; does not advance the pipeline. Use when: "produce the deliverables", "generate all the deliverables", "the deliverables package", "PRD + diagrams + plan + risk/decision logs".
| name | anti-legacy:semantic-join |
| description | Analyze and map inter-repository dependencies when multiple codebases are modernization sources. Scans routes and client requests, identifies dangling external links, and validates contract matches. Use when: "joining repositories", "mapping multi-repo interfaces", "verifying inter-app dependencies". |
This skill orchestrates Phase 1B (Semantic Repository Join). It matches HTTP and API endpoints across multiple imported legacy repositories, detects dangling calls, and resolves integration questions in-band with the user.
Run the boundary analyzer tool:
python3 .anti-legacy/run.py semantic_join
This generates:
.anti-legacy/requirements/semantic_join_graph.json: A dependency topology map..anti-legacy/requirements/semantic_join_report.md: A validation checklist of matched and unmatched API interfaces.If the report contains dangling client calls, resolve each one in-band with the user before advancing.
For each dangling call, present this single_choice question to the user directly in the conversation and capture their answer:
GAP-{calling_service}-{dest_path_slug}single_choice):
Record the user's chosen option against its question id (e.g. in semantic_join_report.md or your working notes) so Step 3 can assert that every dangling call has an in-band answer.
Based on the user's answer:
nfrs.md.Before recording the gate or advancing, assert that the semantic join actually completed:
semantic_join_report.md exists and is non-empty, AND every dangling call surfaced in
Step 2 has an in-band answer recorded against its question id. If this assertion fails,
do NOT run manifest.py gate and do NOT run advance — surface the specific gap (missing
report, or the still-unanswered dangling-call question ids) to the user and stop. The
gate record and advance below are CONDITIONAL on this assertion passing.
Confirm the report exists and is non-empty:
python3 -c "
import os, sys
report = os.path.join('.anti-legacy', 'requirements', 'semantic_join_report.md')
if not (os.path.isfile(report) and os.path.getsize(report) > 0):
sys.stderr.write('GATE_1B done-gate FAILED: semantic_join_report.md missing or empty\n')
sys.exit(1)
sys.exit(0)
"
Then verify in-band that every dangling call listed in the report has a recorded answer
(one of the three single_choice options) against its GAP-... question id. If any
dangling call is still unanswered, do NOT proceed — return to Step 2, resolve it with the
user, and re-run this done-gate.
The gate's --opinion passed guard content-verifies every cited evidence id: each id
must be a registered artifact, its status must not be failed/pending, the file
must exist on disk, and its recorded checksum must match the file. A bare filename like
semantic_join_report.md is NOT a registered artifact id and will hard-fail the gate.
So FIRST register the real report (produced in Step 1) as the artifact id
semantic-join-report. Register it only after the done-gate above passes, so the file
exists and a live checksum is captured:
python3 .anti-legacy/run.py manifest register semantic-join-report \
--path requirements/semantic_join_report.md \
--format markdown \
--produced-by anti-legacy:semantic-join \
--status final
Then record the gate approval, citing the registered id semantic-join-report:
python3 .anti-legacy/run.py manifest gate GATE_1B_SEMANTIC_JOIN \
--opinion passed \
--evaluator "Architect" \
--rationale "All inter-repository endpoints mapped and dangling boundaries clarified by the user." \
--evidence "semantic-join-report"
Only after the done-gate passed and the gate is recorded:
python3 .anti-legacy/run.py manifest advance semantic-join