菜单
Use when designing or evaluating tensor-grep as an enterprise agentic code-intelligence tool — PATH narrowing for complete graphs, EvidenceReceipts, codemap, multi-repo workspaces, accuracy gates, and world-class readiness gaps.
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
Use when searching code, logs, or repositories with tensor-grep; validating rg or AST parity; using tg MCP tools; checking GPU/search routing; or producing agent-friendly context, source, refs, or blast-radius output.
Use when you need the domain theory behind tensor-grep's search/retrieval behavior, not just the command syntax — ripgrep exit codes (including the exit-2-but-kept partial-results contract)/PCRE2/binary-NUL-detection/-uuu/-- sentinels, ast-grep + tree-sitter routing, BM25 vs the flat no-IDF capsule scorer, PageRank vs in-degree centrality, the trigram index, PyO3 + the GIL, MCP argv surface, LSP 3.17 framing, and Model2Vec/potion-code (SHIPPED as `tg search --semantic`). Load before explaining WHY tg behaves a certain way, reasoning about the protocol/algorithm THEORY underneath a backend/router change (exit-code semantics, scoring math, wire framing), or writing docs that touch these subsystems — for the invariants a backend/router change must not break, use `tensor-grep-architecture-contract` instead (or in addition). Not a how-to-run or how-to-debug guide — see the sibling table below for those.
Use when you need the load-bearing design of tensor-grep and WHY it holds before touching cli/bootstrap.py, rust_core/src/main.rs, backends/, core/result.py, cli/main.py's native-delegation gate, routing, the agent capsule, or before reviewing/planning any change to the front door, command/flag registration, or backend contract. Explains the bootstrap intercept-before-Typer front door, native-vs-Python routing, the 4 command + 2 flag registration sites, the Backend Fail-Closed Contract, the native-delegation forward-or-refuse contract (`_can_delegate_to_native_tg_search` + its field-coverage ratchet), the partial-results `result_incomplete`/`incomplete_reason` envelope, `MatchLine`'s frozen-but-hashable dataclass contract, the ASCII-only CLI output rule, the agent-context moat, the invariants that must hold, and the known-weak points (flat no-IDF scorer, GPU not viable, rg parity gap, FFI not the dir-scan speed path). Read this to build the right mental model; use sibling skills for the how-to of changing, de
Use when asked to deep-dive, audit, fix, or drain tensor-grep backlog — OR investigate/rank next work and produce SPEC/TDD plans (docs/plans/requirements|design|tasks-*.md) without implementing. Triggers: "work the backlog", "what next", "investigate and plan", backlog-completion campaign. META-ORCHESTRATOR — 20-skill library. Semantic-search flagship: tensor-grep-semantic-search-campaign. Scale/hang campaign: tensor-grep-large-repo-scale-campaign. Load tensor-grep-change-control before edit.
Use when about to claim, review, or dispute a speedup/regression in tensor-grep (tg vs rg, hot-cache, AST, agent-workflow, or GPU changes) — which benchmark script to run, how to read check_regression.py, the noise-floor/absolute-jitter rule for sub-10ms rows, the fair-baseline rule (never compare tg against a strawman comparator), and the launcher-attribution rules (tg_launcher_mode, tg_launcher_command_kind, stale-binary refusal) that make a benchmark artifact claim-quality instead of noise.
Use when setting up the tensor-grep dev environment from a fresh clone, rebuilding the Rust/PyO3 extension or standalone `tg` binary after touching `rust_core/`, or debugging a build/toolchain problem — uv install, `maturin develop`, `cargo build`, the pinned 1.96.0 Rust toolchain, Python >=3.11 floor, a "hanging" cargo build, cargo/rustc missing from PATH, ruff CRLF false-alarms, or a dependency upper-cap silently downgrading tensor-grep on a newer Python. Gives exact copy-paste setup commands and the traps that have each cost a real cycle.
| name | tensor-grep-enterprise-agent |
| description | Use when designing or evaluating tensor-grep as an enterprise agentic code-intelligence tool — PATH narrowing for complete graphs, EvidenceReceipts, codemap, multi-repo workspaces, accuracy gates, and world-class readiness gaps. |
Verified against tg 1.71.1 (2026-07-13 workspace dogfood on /mnt/c/dev/projects).
REPO/src (or package root) for tg agent latency. Whole-repo agent works NATIVELY (~26s on tensor-grep, exit 0, valid capsule); the 75s WSL /mnt/c timeout is a 9p-latency artifact (reproduce natively before calling it a regression), NOT a v1.71.1 native regression.REPO/src. Root often returns partial with empty callers and exit 2.tg orient . works (~53s) but per-repo orient is faster (~24s).--glob / --type / --max-depth) or --allow-broad-generated-scan.tg scan --ruleset works again on WSL; still check stderr for skipped-path warnings.| Job | Command |
|---|---|
| Orient | tg orient REPO --ignore … --json |
| Ranked search | tg search PATTERN REPO --rank --json |
| Scoped workspace search | tg search PATTERN . --glob "*.py" --max-depth N --json |
| File deps | tg imports / tg importers (absolute paths) |
| Agent capsule | tg agent REPO/src "task" --json |
| Callers / blast | tg callers REPO/src SYMBOL --deadline 15 --json |
| Evidence | tg evidence emit REPO --capsule … --json |
| Session cache | tg session open → context-render |
| Ruleset scan | tg scan --ruleset auth-safe --path REPO/src --json |
| Browsable map | tg codemap REPO --out /tmp/code-map (slow; optional) |
ambiguity.status == tie_requires_confirmationpartial / result_incomplete / exit 2 on graph cmds (incomplete ≠ absent)tg agent timeouts — narrow PATH before raising budgetstg scan path-skip warnings as coverage lossworld_class_readiness = not_claimed)| Gap | 1.71.1 status |
|---|---|
| Unscoped multi-root refuse | Fixed (fast exit 2 + remediation text) |
Cross-OS / WSL scan runnable | Mostly fixed (PASS; residual path-skip warnings) |
| Whole-repo agent (native) | OK (~26s on tensor-grep, exit 0); WSL /mnt/c amplifies to 75s = 9p artifact, not a native regression |
| Large JS/TS agent trees | Open — agent-studio slow on WSL; needs NATIVE repro before claiming a real timeout |
| Complete callers at repo root | Still prefer src/ |
codemap agent-loop-safe | Fixed (#153 deadline; native ~41s whole-repo, bounded/partial) |
| Agent accuracy gate (top-k / MRR / false-primary) | Missing |
| GPU promotion / LSP proof | Experimental / not claimed -- GPU Phase-0 SHIPPED v1.75.0-v1.75.4 (native assets locally correctness-proven, gated off the public release behind TENSOR_GREP_RELEASE_NATIVE_ASSET_PROFILE), but no speed crossover is proven vs rg/tg_cpu and public-gpu-proof.yml remains unmet (docs/gpu_crossover.md) |
Cold text search vs rg claims | rg remains baseline |
tg doctor --json REPO
tg orient REPO --ignore "node_modules/**" --json
tg search "intent" REPO --rank --json
tg agent REPO/src "task" --json > /tmp/capsule.json
tg evidence emit REPO --capsule /tmp/capsule.json --query "task" --json --agent-id "$AGENT_ID"
tg callers REPO/src SYMBOL --deadline 15 --json
SID=$(tg session open REPO --json | jq -r .session_id)
tg session context-render "$SID" REPO "task" --json