メニュー
Gate a cross-language port for correctness — composes port-scoped behavioral equivalence, contract parity, and port-manifest drift into a port-correctness verdict. Use to verify that a ported function matches its source before marking the port done.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Audit whether an AI agent edit to a file is safe — composes secret-surface, taint-flow, change-impact, and API-surface analysis into an agent-edit safety report. Use before letting an agent modify a sensitive or high-blast-radius file.
Execute structural decompositions based on an architectural analysis report. Use when breaking circular dependencies, splitting god classes, reducing coupling between modules, extracting interfaces at seam boundaries, or executing any large-scale structural change identified in an architectural analysis. Requires a prior architecture audit (the architecture-audit skill) that produced project-map.md and a run report.
Use when asked to audit architecture, produce a comprehensive architectural overview, get the full structural picture of a codebase, assess overall health and porting readiness, find module boundaries, circular dependencies, coupling hotspots, dead code, or code patterns. Depth 3 — full audit with hypothesis-driven investigation. Optionally enriches the structural audit with runtime and git evidence (coverage, churn, co-change coupling, ownership) when those overlays are available. Replaces the architectural-analysis and architecture-audit-plus skills.
Use when looking for extraction candidates, planning a module split, analyzing module boundaries, or before decomposing a large component. Also use when asked "where should I split this?" or "find natural module boundaries". Depth 2 — investigate. Produces extraction candidates with cut costs, layer violations, interface width assessment, orphan types, and a recommended decomposition sequence.
Use before modifying a file or symbol, or when asked "what breaks if I change X?". Depth 0 — fast, no follow-up queries, returns immediately. Two modes: inline (no artifacts, default for agent-initiated use) and artifact (writes to docs/act/, triggered for human-initiated requests or Critical risk verdicts).
Traverse large repositories efficiently using act's query tools. Use when exploring unfamiliar code, mapping dependencies, understanding API surfaces, analyzing side effects before modifying functions, or following call chains across files. Avoids reading entire files by querying only the structure needed.
| name | port-verify |
| description | Gate a cross-language port for correctness — composes port-scoped behavioral equivalence, contract parity, and port-manifest drift into a port-correctness verdict. Use to verify that a ported function matches its source before marking the port done. |
A port-correctness gate: confirm a ported function behaves like its source and that the port manifest is not drifting. Composes two Enterprise verification ops with the port inventory.
This is a structural/contract comparison (v1), not execution-based differential
testing. verify_port_parity and verify_behavioral_equivalence (scope=port)
compare only dimensions BOTH grammars model — a dimension modeled by one side
only is reported unknown, never falsely preserved/diverged. Each result
carries modeled_kinds; an empty set for either grammar means that dimension is
uncovered. Per-grammar degradation across the source/target language pair is the
norm — name both languages and the uncovered dimensions. Verdicts are advisory.
Enterprise. verify_behavioral_equivalence at scope:"port",
verify_port_parity, and the port_* manifest/inventory tools are all
Enterprise and enforce the tier themselves.
| Step | Tool | What it answers |
|---|---|---|
| 1 | verify_behavioral_equivalence (scope:"port") | Do the source and ported functions have an equivalent control-flow shape under cross-language normalization? |
| 2 | verify_port_parity | Do signature arity, return presence, effect-kind set, CFG shape, and raise count match across the language pair? |
| 3 | port_inventory | Is the manifest consistent — is this symbol marked ported, and is the target verified? Surfaces drift. |
verify_behavioral_equivalence with scope:"port", the source
target/file and the ported version (via before/after or the manifest
mapping). equivalent confirms shape held; changed lists which dimensions
diverged; unknown means a dimension could not be normalized across the pair
— do not claim parity on it.verify_port_parity with source_file/source_target and
ported_file/ported_target. Read the verdict (preserved/diverged/
unknown), the dimensions_checked, and every mismatch. A diverged
dimension is a hard gate failure.port_inventory to check manifest state for the file: is it marked
ported, are ported/stubbed symbols recorded, does target verification pass?
A symbol that is structurally equivalent but absent/stubbed in the manifest
is drift — the manifest and reality disagree.equivalent (port scope) AND parity preserved with
≥1 jointly-modeled dimension AND the manifest marks the symbol ported with a
verified target.changed or parity diverged on any modeled
dimension; report the exact dimension and the mismatch.unknown/empty modeled_kinds on a
dimension; name the source+target languages and the uncovered dimension.
Never present UNKNOWN as VERIFIED.Per ported symbol: the equivalence result, the parity verdict with
dimensions_checked + mismatches, the manifest status, and the gate verdict.
Quote modeled_kinds for both languages on any UNKNOWN.