{"id":"466e97ce-c128-45f0-82a8-f49b58824138","entityType":"agent","slug":"clawhub-suifei-lang-migration","name":"编程语言迁移","canonicalUrl":"https://www.xpersona.co/agent/clawhub-suifei-lang-migration","canonicalPath":"/agent/clawhub-suifei-lang-migration","generatedAt":"2026-10-11T16:01:20.177Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T13:08:01.714Z","emptyReason":null},"description":"AI-driven full-project language migration skill. Use this skill whenever the user wants to port, translate, or rewrite a codebase from one programming langua... Skill: 编程语言迁移 Owner: suifei Summary: AI-driven full-project language migration skill. Use this skill whenever the user wants to port, translate, or rewrite a codebase from one programming langua... Tags: latest:1.3.1 Version history: v1.3.1 | 2026-05-18T02:32:46.759Z | user v1.3 — Bug Triage Protocol + Real-World Validation Every P5 test failure now goes through a mandatory 3-step triage before any fix is attempted.","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17cwv8cyfy64wkqte2x67hesn86s5rq:lang-migration","sourceUrl":"https://clawhub.ai/suifei/lang-migration","homepage":"https://clawhub.ai/suifei/skills/lang-migration","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/suifei/lang-migration","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/suifei/skills/lang-migration","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"AI-driven full-project language migration skill. Use this skill whenever the user wants to port, translate, or rewrite a codebase from one programming langua..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:08:01.714Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:08:01.714Z","emptyReason":null},"stars":null,"forks":null,"downloads":1060,"packageName":null,"latestVersion":"1.3.1","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:08:01.642Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T13:08:01.714Z","lastCrawledAt":"2026-10-11T13:08:01.642Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T13:08:01.642Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.1","createdAt":"2026-05-18T02:32:46.759Z","changelog":"v1.3 — Bug Triage Protocol + Real-World Validation Every P5 test failure now goes through a mandatory 3-step triage before any fix is attempted. Only 1 of 5 verdicts leads to modifying the translated function. Four new root cause categories. Validated against a real Python→Go migration (GenericAgent → go-GenericAgent). Learn more → https://github.com/suifei/lang-migration-skill#bug-triage-protocol-classify-before-fix","fileCount":37,"zipByteSize":154634},{"version":"1.2.1","createdAt":"2026-05-15T15:35:23.365Z","changelog":"lang-migration 1.2.1 - Added detailed author attribution and contact section to SKILL.md. - Introduced stricter evidence requirements: mandatory TDD Retrospective protocol at every fix, checklist output, and full suite reruns. - Phase Gate Review (PGR) mechanism integrated: each phase now requires a completed audit report before being marked DONE; added session-start PGR check. - New reference files supporting audit and retrospective protocols: phase-0-bootstrap.md, phase-gate-review.md, tdd-retrospective.md. - Added templates/retrospective-checklist.yaml for structured incident tracking. - Added multilingual documentation (README.zh-CN.md). - Expanded documentation of process, anti-cheating policies, and progress-reporting protocols.","fileCount":36,"zipByteSize":135675},{"version":"1.0.0","createdAt":"2026-05-15T04:24:13.418Z","changelog":"lang-migration 1.0.0 - Initial release: systematic multi-phase workflow for AI-driven, full-project language migration. - Enforces 1:1 structural equivalence, full asset coverage, persistent YAML state, and strict no-mock verification. - Introduces anti-cheating protocols: evidence required at every step, with robust task verification and blocking if human input is needed. - Supports multiple environments (Claude/OpenCode/Editor) with session protocols and detailed pipeline from asset scan to verification. - Includes blocking and gap report protocols for transparent and auditable migration progress.","fileCount":30,"zipByteSize":90821}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17cwv8cyfy64wkqte2x67hesn86s5rq:lang-migration","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T16:01:20.170Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-suifei-lang-migration/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T13:08:01.714Z","emptyReason":null},"readme":"Skill: 编程语言迁移\n\nOwner: suifei\n\nSummary: AI-driven full-project language migration skill. Use this skill whenever the user wants to port, translate, or rewrite a codebase from one programming langua...\n\nTags: latest:1.3.1\n\nVersion history:\n\nv1.3.1 | 2026-05-18T02:32:46.759Z | user\n\nv1.3 — Bug Triage Protocol + Real-World Validation Every P5 test failure now goes through a mandatory 3-step triage before any fix is attempted. Only 1 of 5 verdicts leads to modifying the translated function. Four new root cause categories. Validated against a real Python→Go migration (GenericAgent → go-GenericAgent). \nLearn more → https://github.com/suifei/lang-migration-skill#bug-triage-protocol-classify-before-fix\n\nv1.2.1 | 2026-05-15T15:35:23.365Z | user\n\nlang-migration 1.2.1\n\n- Added detailed author attribution and contact section to SKILL.md.\n- Introduced stricter evidence requirements: mandatory TDD Retrospective protocol at every fix, checklist output, and full suite reruns.\n- Phase Gate Review (PGR) mechanism integrated: each phase now requires a completed audit report before being marked DONE; added session-start PGR check.\n- New reference files supporting audit and retrospective protocols: phase-0-bootstrap.md, phase-gate-review.md, tdd-retrospective.md.\n- Added templates/retrospective-checklist.yaml for structured incident tracking.\n- Added multilingual documentation (README.zh-CN.md).\n- Expanded documentation of process, anti-cheating policies, and progress-reporting protocols.\n\nv1.0.0 | 2026-05-15T04:24:13.418Z | user\n\nlang-migration 1.0.0\n\n- Initial release: systematic multi-phase workflow for AI-driven, full-project language migration.\n- Enforces 1:1 structural equivalence, full asset coverage, persistent YAML state, and strict no-mock verification.\n- Introduces anti-cheating protocols: evidence required at every step, with robust task verification and blocking if human input is needed.\n- Supports multiple environments (Claude/OpenCode/Editor) with session protocols and detailed pipeline from asset scan to verification.\n- Includes blocking and gap report protocols for transparent and auditable migration progress.\n\nArchive index:\n\nArchive v1.3.1: 37 files, 154634 bytes\n\nFiles: README.md (38606b), README.zh-CN.md (36248b), references/lang-pairs/bun-python.md (8589b), references/lang-pairs/c-python.md (10351b), references/lang-pairs/cpp-python.md (9906b), references/lang-pairs/go-python.md (9013b), references/lang-pairs/python-bun.md (6887b), references/lang-pairs/python-c.md (5313b), references/lang-pairs/python-cpp.md (6420b), references/lang-pairs/python-go.md (12303b), references/lang-pairs/python-rust.md (10798b), references/lang-pairs/python-typescript.md (7993b), references/lang-pairs/python-zig.md (6917b), references/lang-pairs/rust-python.md (10509b), references/lang-pairs/TEMPLATE.md (2267b), references/lang-pairs/typescript-python.md (9786b), references/lang-pairs/zig-python.md (9690b), references/phase-0-bootstrap.md (4489b), references/phase-1-asset-scan.md (5448b), references/phase-2-ecosystem-map.md (8797b), references/phase-3-ipo-analysis.md (15303b), references/phase-4-translation.md (8936b), references/phase-5-verification.md (16210b), references/phase-6-gap-report.md (7933b), references/phase-gate-review.md (22116b), references/schemas.md (7563b), references/tdd-retrospective.md (13980b), scripts/gap_report.py (22904b), scripts/scan_assets.py (8891b), skill-card.md (2722b), SKILL.md (19991b), templates/asset-inventory.yaml (1660b), templates/ecosystem-map.yaml (2563b), templates/ipo-registry.yaml (2679b), templates/migration-state.yaml (2653b), templates/retrospective-checklist.yaml (2221b), _meta.json (133b)\n\nFile v1.3.1:SKILL.md\n\n---\r\nname: lang-migration\r\ndescription: >\r\n AI-driven full-project language migration skill. Use this skill whenever the user wants to\r\n port, translate, or rewrite a codebase from one programming language to another — including\r\n Python→Rust, Python→Go, Python→C, Python→C++, Python→Zig, Python→Bun/TS, or any other pair.\r\n Also trigger when user mentions \"精确复刻\", \"语言迁移\", \"port project\", \"translate codebase\",\r\n \"1:1 rewrite\", or \"language conversion\". This skill enforces structural equivalence first,\r\n full asset coverage (no file skipped), persistent YAML state across sessions, and a strict\r\n no-mock verification policy with human-gated blocking.\r\nlicense: MIT\r\n---\r\n\r\n## Author & Attribution\r\n\r\n**Original Author**: flynn \r\n**Contact**: https://github.com/suifei/lang-migration-skill \r\n**Role**: Architect, Developer, Documenter \r\n**Expertise**: Software engineering, programming languages, AI workflow design \r\n**Contributions**: Designed the multi-phase pipeline, defined YAML schemas, implemented blocking protocol, and wrote comprehensive documentation for the skill.\r\n\r\n---\r\n\r\n# Language Migration Skill\r\n\r\nA systematic, multi-session, AI-executable workflow for migrating any open-source project\r\nfrom one programming language to another with 1:1 structural fidelity.\r\n\r\n## Core Principles\r\n\r\n1. **No file is useless** — every file in the source project is analyzed and assigned a migration strategy\r\n2. **Structural equivalence first** — algorithm steps, loop structure, and control flow must mirror the source; behavioral equivalence is only used when the ecosystem gap makes structural impossible\r\n3. **No mock, ever** — tests must use real implementations and real test data\r\n4. **Block, don't skip** — when a decision cannot be made autonomously, stop and ask the human; never label-and-continue\r\n5. **State persists across sessions** — all state lives in YAML files in the workspace, readable by any AI agent or human\r\n6. **Evidence before completion** — every unit of work must produce verifiable evidence of execution before being marked done\r\n\r\n---\r\n\r\n## Global Anti-Cheating Policy\r\n\r\nThis skill operates under the assumption that an AI agent may attempt to mark tasks complete\r\nwithout actually doing the work. Every phase has mechanisms to detect and prevent this.\r\n\r\n**The Three Forms of AI Task Fraud (all prohibited):**\r\n\r\n| Form | Example | Detection |\r\n|---|---|---|\r\n| Batch fabrication | Scripts generate IPO content without reading source | source_lines field will be wrong/empty |\r\n| Silent bulk-confirm | NEEDS_REVIEW → CONFIRMED without evidence | confirmation_evidence field empty |\r\n| Premature phase advance | Marking P3 DONE when entries have empty fields | Self-verification checks fail |\r\n\r\n**Evidence Requirements by Phase:**\r\n\r\n| Phase | Required Evidence |\r\n|---|---|\r\n| P2 | `confirmation_evidence` block per CONFIRMED entry |\r\n| P3 | `READ_EVIDENCE` + `BEHAVIOR_PROOF` per function; `source_lines` in every step; `source_line` on every magic number |\r\n| P4 | Compilation succeeds; IPO entry updated with `target_lines`; **every fix triggers TDD Retrospective** |\r\n| P5 | **TEST OUTPUT EVIDENCE** (actual runner output, not just \"tests pass\"); **every fix triggers TDD Retrospective**; **full suite re-run after each fix**; **Checklist Summary at phase end** |\r\n| Fix | `retrospective-checklist.yaml` entry with RCA → scope_scan_query (defined BEFORE scan) → scope scan results → consistent fix (see `tdd-retrospective.md`) |\r\n| **PGR** | **Full audit report output in response** listing every item checked; each FINDING citing exact artifact (file path, field, value); each FIXED citing same artifact after change; `findings_count: 0` proven by enumerated item list; `phase_gates.PGR_N.passed_at` timestamp set only after zero-findings pass |\r\n\r\n**TDD Retrospective Integration**\r\n\r\nThe **Retrospective Protocol** is mandatory at every fix point:\r\n- **Trigger**: Compilation error, vet failure, structural deviation, test failure\r\n- **Steps**: RCA (root cause analysis) → Checklist rule → Scope scan → Consistent fix\r\n- **Output**: Entry in `retrospective-checklist.yaml` with root cause category and generalized rule\r\n- **Scope scan constraint**: `scope_scan_query` MUST be written before scanning (prevents post-hoc bias)\r\n- **Impact**: After each fix, full test suite is re-run; new failures each trigger independent retrospectives\r\n\r\nSee [Retrospective Protocol](#retrospective-protocol) below and `references/tdd-retrospective.md`.\r\n\r\n**Self-Verification is not optional.** Each phase that has a Self-Verification Protocol\r\nmust run it and output the report before advancing. The report must appear in the AI's\r\nresponse — not silently written to a file.\r\n\r\n**The AI must never say \"done\" without evidence.** \"I have completed X\" is not a valid\r\ncompletion statement without accompanying evidence artifacts.\r\n\r\n---\r\n\r\n## Environment Detection\r\n\r\nThis skill runs in Claude Code, Cursor, OpenCode, or GitHub Copilot. At session start, detect the environment:\r\n\r\n```\r\nIF bash tool is available AND can write files → full_mode (Claude Code / OpenCode)\r\nIF only file editing available → editor_mode (Cursor / Copilot)\r\n```\r\n\r\nIn **full_mode**: use bash scripts for scanning, run `scan_assets.py` directly.\r\nIn **editor_mode**: generate file lists manually by reading directory structure; instruct user to run scripts manually if needed.\r\n\r\n**Workspace location**: Always at the project root, in a directory called `migration_workspace/`.\r\n\r\n```\r\n/\r\n├── / ← original project (read-only, never modify)\r\n├── / ← translated output (created by this skill)\r\n└── migration_workspace/\r\n ├── migration-state.yaml ← SESSION ENTRY POINT: read this first every session\r\n ├── asset-inventory.yaml\r\n ├── ecosystem-map.yaml\r\n └── ipo-registry.yaml\r\n```\r\n\r\n---\r\n\r\n## Session Start Protocol\r\n\r\n**Every time you start a new session, do this first — no exceptions:**\r\n\r\n1. Check if `migration_workspace/migration-state.yaml` exists\r\n - YES → read it, understand current phase and `current_task`, resume from there\r\n - NO → this is a new project, run **P0 Bootstrap**\r\n\r\n2. Read `current_task` block. If `status: BLOCKED`, present the block to the user immediately and wait for their input before doing anything else.\r\n\r\n2b. **Check phase gate consistency**: For every phase marked `DONE` in the `phases` block, verify the corresponding `phase_gates.PGR_N.passed_at` is non-empty. If a phase is `DONE` but `passed_at` is empty, the PGR was not completed. Re-run PGR-N for that phase before advancing to the next phase. Load `references/phase-gate-review.md` for the audit criteria.\r\n\r\n3. **Check if the user's opening message is a status/gap question:**\r\n - Triggers: \"还差什么\", \"进度怎样\", \"gap report\", \"show status\", \"还有哪些\", \"差多少\", \"完成了多少\"\r\n - If YES → run P6 Gap Report immediately, output the summary to the user, then ask how to proceed\r\n - If NO → continue to step 4\r\n\r\n4. Load the language pair module: `references/lang-pairs/-.md`\r\n\r\n5. Proceed with the current phase.\r\n\r\n---\r\n\r\n## Five-Phase Pipeline\r\n\r\n```\r\nP0 Bootstrap → Initialize workspace, detect language pair, load lang-pair module\r\nP1 Asset Scan → Inventory every file, assign migration strategy\r\nP2 Ecosystem Mapping → Map all imports/types/stdlib to target equivalents, identify gaps\r\nP3 IPO Analysis → Document every function: Inputs, Process (incl. magic numbers), Outputs\r\nP4 Translation → Translate function by function using IPO registry + ecosystem map\r\nP5 Verification → Structural review + real-data behavioral tests (no mock)\r\nP6 Gap Report → Multi-dimensional completeness audit (invoke at any time)\r\n```\r\n\r\nEach phase has a detailed reference file. Load it when entering that phase:\r\n\r\n| Phase | Reference File |\r\n|-------|----------------|\r\n| P0 | `references/phase-0-bootstrap.md` |\r\n| P1 | `references/phase-1-asset-scan.md` |\r\n| P2 | `references/phase-2-ecosystem-map.md` |\r\n| P3 | `references/phase-3-ipo-analysis.md` |\r\n| P4 | `references/phase-4-translation.md` |\r\n| P5 | `references/phase-5-verification.md` |\r\n| P6 | `references/phase-6-gap-report.md` |\r\n| **Fix** | **`references/tdd-retrospective.md` ← mandatory on every fix in P4/P5** |\r\n| **PGR** | **`references/phase-gate-review.md` ← mandatory between every phase transition** |\r\n\r\n---\r\n\r\n## Phase Gate Review Protocol (PGR)\r\n\r\n**A phase is not complete when the AI says it is complete. A phase is complete when PGR-N passes with zero findings.**\r\n\r\nAfter every phase finishes, the AI enters an autonomous self-auditing loop before advancing to the next phase. This loop requires no human involvement.\r\n\r\n### Updated Pipeline with PGR Gates\r\n\r\n```\r\nP0 Bootstrap → [PGR-0] → P1 Asset Scan → [PGR-1] → P2 Ecosystem Map → [PGR-2]\r\n → P3 IPO Analysis → [PGR-3] → P4 Translation → [PGR-4] → P5 Verification → [PGR-5] → DONE\r\n```\r\n\r\n### How PGR Works\r\n\r\nEach PGR-N runs an **enumerate → audit → fix → re-audit** loop:\r\n\r\n1. **Enumerate** — list every expected output of the completed phase\r\n2. **Audit** — check each output against phase-specific criteria; record any FINDING with artifact evidence\r\n3. **Tally** — if `findings_count == 0`, advance; if `findings_count > 0`, proceed to Fix\r\n4. **Fix** — fix each FINDING autonomously; record artifact evidence of each fix\r\n5. **Re-audit** — return to Step 1 (full re-enumeration required after every fix pass)\r\n6. **Pass** — when zero findings: set `phase_gates.PGR_N.status: PASSED`; only then set `phases.PN_xxx: DONE`\r\n\r\n### Core Rule\r\n\r\nThe phase status `DONE` in `migration-state.yaml` must NEVER be set directly at the end of a phase.\r\nIt is only set by PGR-N as the final action of a passed audit. Any session that finds a phase marked\r\n`DONE` without a corresponding `phase_gates.PGR_N.passed_at` timestamp must re-run PGR-N before\r\nadvancing (see Session Start Protocol).\r\n\r\n### PGR Reference\r\n\r\n| Gate | Triggered After | Reference |\r\n|------|----------------|-----------|\r\n| PGR-0 | P0 Bootstrap | `references/phase-gate-review.md#pgr-0` |\r\n| PGR-1 | P1 Asset Scan | `references/phase-gate-review.md#pgr-1` |\r\n| PGR-2 | P2 Ecosystem Map | `references/phase-gate-review.md#pgr-2` |\r\n| PGR-3 | P3 IPO Analysis | `references/phase-gate-review.md#pgr-3` |\r\n| PGR-4 | P4 Translation | `references/phase-gate-review.md#pgr-4` |\r\n| PGR-5 | P5 Verification | `references/phase-gate-review.md#pgr-5` |\r\n\r\nFor the full protocol including per-phase audit criteria, finding formats, and anti-cheating rules,\r\nsee: `references/phase-gate-review.md`\r\n\r\n---\r\n\r\n## P0 Bootstrap (New Project)\r\n\r\nWhen `migration-state.yaml` does not exist:\r\n\r\n1. Ask the user:\r\n - Source language and directory path\r\n - Target language\r\n - Any known constraints or priorities\r\n\r\n2. Determine language pair key (e.g., `python-rust`). If the file `references/lang-pairs/.md` does not exist, load `references/lang-pairs/TEMPLATE.md` and tell the user this pair needs a new module — offer to draft one before continuing.\r\n\r\n3. Copy all five template files from `templates/` into `migration_workspace/`:\r\n - `migration-state.yaml` → fill in meta block\r\n - `asset-inventory.yaml` → empty, ready for P1\r\n - `ecosystem-map.yaml` → empty, ready for P2\r\n - `ipo-registry.yaml` → empty, ready for P3\r\n - `retrospective-checklist.yaml` → empty, ready for first P4/P5 fix\r\n\r\n4. Set `phases.P0_bootstrap: DONE` and `phases.P1_asset_scan: IN_PROGRESS`\r\n\r\n5. Immediately proceed to P1.\r\n\r\n---\r\n\r\n## Blocking Protocol\r\n\r\nWhen you cannot proceed without a human decision:\r\n\r\n1. Write to `migration-state.yaml`:\r\n ```yaml\r\n current_task:\r\n status: BLOCKED\r\n block_reason: \"\"\r\n human_input_required: \"\"\r\n ```\r\n\r\n2. Output to the user:\r\n ```\r\n ⛔ BLOCKED — Human decision required\r\n\r\n Phase: \r\n Item: \r\n\r\n Problem: \r\n\r\n Required decision: \r\n\r\n Options considered:\r\n A)