[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ACJ5V7WSX7ZT7N6E316R2R":3,"skill-same:01M6ACJ5V7WSX7ZT7N6E316R2R":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6ACJ5V7WSX7ZT7N6E316R2R","optimize-comet-expression",null,"Use when optimizing the performance of an existing native scalar expression in the datafusion-comet-spark-expr crate (native\u002Fspark-expr\u002F) — casts, string\u002FJSON\u002Farray\u002Fmath kernels that run per-row or per-batch. Covers benchmarking, keeping output bit-identical, and the no-regression gate. Not for adding new expressions (use implement-comet-expression) or wiring upstream functions (use wire-datafusion-function).","apache\u002Fdatafusion-comet","apache","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47359?v=4","01M6AC83E6K4FDKK7HZ8WNMQKE","The Apache Software Foundation","01M6ACHX42TPNCR8TQJEAR8J5J",1322,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Foptimize-comet-expression\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"optimize comet expression","expression","optimize","new","performance","when","wiring","Existing","for","kernels","output","expr","bit","upstream","functions","use","regression","datafusion","batch","run","spark","benchmarking","implement","2026-11-10 10:12:30",false,"---\nname: optimize-comet-expression\ndescription: Use when optimizing the performance of an existing native scalar expression in the datafusion-comet-spark-expr crate (native\u002Fspark-expr\u002F) — casts, string\u002FJSON\u002Farray\u002Fmath kernels that run per-row or per-batch. Covers benchmarking, keeping output bit-identical, and the no-regression gate. Not for adding new expressions (use implement-comet-expression) or wiring upstream functions (use wire-datafusion-function).\nargument-hint: \u003Cexpression-name>\n---\n\n\u003C!--\nLicensed to the Apache Software Foundation (ASF) under one\nor more contributor license agreements.  See the NOTICE file\ndistributed with this work for additional information\nregarding copyright ownership.  The ASF licenses this file\nto you under the Apache License, Version 2.0 (the\n\"License\"); you may not use this file except in compliance\nwith the License.  You may obtain a copy of the License at\n\n  http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\nUnless required by applicable law or agreed to in writing,\nsoftware distributed under the License is distributed on an\n\"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\nKIND, either express or implied.  See the License for the\nspecific language governing permissions and limitations\nunder the License.\n-->\n\nOptimize the native `$ARGUMENTS` scalar expression in `native\u002Fspark-expr\u002F`.\n\n**The methodology, benchmark shapes, technique catalog, correctness traps, and PR conventions\nlive in one place for both humans and agents:\n`docs\u002Fsource\u002Fcontributor-guide\u002Foptimizing_expressions.md`. Read it first — it is the source of\ntruth. This skill only adds the agent execution loop and the discipline that keeps a change from\nbeing a no-op or a regression.**\n\n## Execution loop\n\n1. **Read** `docs\u002Fsource\u002Fcontributor-guide\u002Foptimizing_expressions.md`.\n2. **Locate** the implementation under `native\u002Fspark-expr\u002Fsrc\u002F` and identify the per-row cost\n   (allocation, kernel dispatch per element, UTF-8 decoding, regex compilation, bitmap reads).\n3. **Baseline first.** Add or extend a criterion benchmark in `native\u002Fspark-expr\u002Fbenches\u002F`\n   (register it in `native\u002Fspark-expr\u002FCargo.toml`), covering the shapes from the guide:\n   no-null \u002F sparse-null \u002F dense-null, short \u002F long, valid \u002F invalid, ASCII \u002F non-ASCII. Run it\n   on `main` before touching any source:\n   ```sh\n   cd native && cargo bench --bench \u003Cname> -- --save-baseline main\n   ```\n   The baseline must be **built from unmodified source**. `cargo bench` recompiles from whatever\n   is on disk when it runs, so if your optimization is already in the working tree (or a slow\n   build is still compiling when you start editing), the \"baseline\" measures the optimized code\n   and every speedup looks like zero. Only the benchmark file and `Cargo.toml` bench registration\n   may be present. If you have already edited the expression, `git stash push -- \u003Csource file>`,\n   capture the baseline, then `git stash pop`. Confirm the run finished before editing.\n4. **Optimize**, preserving exact semantics. Pick a technique from the catalog in the guide.\n5. **Prove correctness.** Run the existing unit tests for the function; they must pass unchanged.\n   Output must be bit-identical to `main` (values, null buffer, errors). There is no differential\n   fuzz harness in this repo — the unit tests are the gate. If coverage is thin, add tests (or run\n   `audit-comet-expression`) before claiming correctness.\n6. **Re-measure.** `cargo bench --bench \u003Cname> -- --baseline main`. Criterion's \"change\" compares\n   two separate process runs, so a small (±a few %) flag on a shape can be cross-run system noise\n   (thermal, background load), not a real effect. Before trusting any flagged regression, take a\n   **second independent sample** (`--baseline main` again) — real changes reproduce, noise does\n   not. A shape whose code path you did not touch cannot truly regress: if it flags, it is noise,\n   and the fix is another sample, not abandoning the change.\n7. **Apply the no-regression gate** (below) before writing any PR.\n8. **Finish:** `make format`, build, `cargo clippy --all-targets --workspace -- -D warnings`.\n   PR title ``perf: optimize `$ARGUMENTS` (Nx faster)``, paste the criterion output for every\n   shape.\n9. **Record the performance audit.** Add a dated `Performance (tuned ...)` line under the\n   expression's heading on the relevant page in\n   `docs\u002Fsource\u002Fcontributor-guide\u002Fexpression-audits\u002F` (naming the technique, speedup, PR, and\n   benchmark file) so contributors can see what has already been tuned. Check this page before\n   starting, too — it tells you whether the expression was already optimized.\n\n## The gate: what blocks a submission\n\n- **A shape got meaningfully and reproducibly slower.** Do NOT submit. Even a 90%-faster-no-nulls\n  win does not justify a 30%-slower-dense-nulls loss. Either gate the fast path behind a per-batch\n  runtime check that picks the right path, or abandon the change. A Comet PR was closed for exactly\n  this. \"Reproducibly\" matters: confirm a flagged regression on a second sample first (step 6) —\n  a ~2% flag on a code path you did not touch is noise, not a blocker.\n- **No meaningful speedup on any shape.** There is nothing to submit. A change inside criterion's\n  noise threshold is not an improvement.\n- **Output differs from `main`** on any input, including null placement or error behavior.\n- **You only benchmarked one shape.** You have not shown the absence of a regression.\n\n## Red flags — STOP\n\n- \"It's obviously faster, I don't need to benchmark all shapes\" → dense nulls \u002F long values \u002F the\n  error path are where fast paths regress. Benchmark them.\n- \"The values are right, I'll assume nulls are fine\" → null-buffer bugs are the most common\n  correctness failure. Diff the null buffer.\n- \"I'll apply the fallible conversion to every slot\" → a garbage value under a null must not raise\n  an error Spark does not. Use `try_unary` or skip null slots.\n- \"One benchmark improved, ship it\" → re-read the gate. One improvement plus one regression is not\n  a win.\n\n## Rationalization table\n\n| Excuse                                                               | Reality                                                                                                                                                                                              |\n| -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| \"Measuring the baseline is overhead, I'll benchmark once at the end\" | Without a `main` baseline you cannot report a change %, and you cannot tell a win from noise. Baseline first.                                                                                        |\n| \"Dense-null regression is an edge case\"                              | Real columns have dense nulls. A regression there is a regression. Gate the path or drop it.                                                                                                         |\n| \"Existing tests are enough proof, no need to check the null buffer\"  | Tests may not assert null placement. Confirm bit-identical output explicitly.                                                                                                                        |\n| \"This trades a bit of the null case for a big win elsewhere\"         | That is a trade-off, not an optimization. Only submit a strict improvement (or a correctly-gated per-batch path).                                                                                    |\n| \"I'll edit the code, then run the baseline\"                          | `cargo bench` compiles from disk. A baseline built with your change already applied measures the optimized code and hides the real speedup. Baseline on unmodified source; stash the edit if needed. |\n| \"One shape flagged a 2% regression, abandon it\"                      | Criterion compares separate runs; small flags on an untouched code path are cross-run noise. Take a second sample before deciding — real regressions reproduce.                                      |\n\n## Related skills\n\n- `audit-comet-expression` — shore up test coverage before optimizing when the gate is thin.\n- `implement-comet-expression` — for a brand-new expression, not an existing one.\n- `wire-datafusion-function` — for wiring an existing upstream function.\n","\u003C!--\nLicensed to the Apache Software Foundation (ASF) under one\nor more contributor license agreements.  See the NOTICE file\ndistributed with this work for additional information\nregarding copyright ownership.  The ASF licenses this file\nto you under the Apache License, Version 2.0 (the\n\"License\"); you may not use this file except in compliance\nwith the License.  You may obtain a copy of the License at\n\n  http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\nUnless required by applicable law or agreed to in writing,\nsoftware distributed under the License is distributed on an\n\"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\nKIND, either express or implied.  See the License for the\nspecific language governing permissions and limitations\nunder the License.\n-->\n\nOptimize the native `$ARGUMENTS` scalar expression in `native\u002Fspark-expr\u002F`.\n\n**The methodology, benchmark shapes, technique catalog, correctness traps, and PR conventions\nlive in one place for both humans and agents:\n`docs\u002Fsource\u002Fcontributor-guide\u002Foptimizing_expressions.md`. Read it first — it is the source of\ntruth. This skill only adds the agent execution loop and the discipline that keeps a change from\nbeing a no-op or a regression.**\n\n## Execution loop\n\n1. **Read** `docs\u002Fsource\u002Fcontributor-guide\u002Foptimizing_expressions.md`.\n2. **Locate** the implementation under `native\u002Fspark-expr\u002Fsrc\u002F` and identify the per-row cost\n   (allocation, kernel dispatch per element, UTF-8 decoding, regex compilation, bitmap reads).\n3. **Baseline first.** Add or extend a criterion benchmark in `native\u002Fspark-expr\u002Fbenches\u002F`\n   (register it in `native\u002Fspark-expr\u002FCargo.toml`), covering the shapes from the guide:\n   no-null \u002F sparse-null \u002F dense-null, short \u002F long, valid \u002F invalid, ASCII \u002F non-ASCII. Run it\n   on `main` before touching any source:\n   ```sh\n   cd native && cargo bench --bench \u003Cname> -- --save-baseline main\n   ```\n   The baseline must be **built from unmodified source**. `cargo bench` recompiles from whatever\n   is on disk when it runs, so if your optimization is already in the working tree (or a slow\n   build is still compiling when you start editing), the \"baseline\" measures the optimized code\n   and every speedup looks like zero. Only the benchmark file and `Cargo.toml` bench registration\n   may be present. If you have already edited the expression, `git stash push -- \u003Csource file>`,\n   capture the baseline, then `git stash pop`. Confirm the run finished before editing.\n4. **Optimize**, preserving exact semantics. Pick a technique from the catalog in the guide.\n5. **Prove correctness.** Run the existing unit tests for the function; they must pass unchanged.\n   Output must be bit-identical to `main` (values, null buffer, errors). There is no differential\n   fuzz harness in this repo — the unit tests are the gate. If coverage is thin, add tests (or run\n   `audit-comet-expression`) before claiming correctness.\n6. **Re-measure.** `cargo bench --bench \u003Cname> -- --baseline main`. Criterion's \"change\" compares\n   two separate process runs, so a small (±a few %) flag on a shape can be cross-run system noise\n   (thermal, background load), not a real effect. Before trusting any flagged regression, take a\n   **second independent sample** (`--baseline main` again) — real changes reproduce, noise does\n   not. A shape whose code path you did not touch cannot truly regress: if it flags, it is noise,\n   and the fix is another sample, not abandoning the change.\n7. **Apply the no-regression gate** (below) before writing any PR.\n8. **Finish:** `make format`, build, `cargo clippy --all-targets --workspace -- -D warnings`.\n   PR title ``perf: optimize `$ARGUMENTS` (Nx faster)``, paste the criterion output for every\n   shape.\n9. **Record the performance audit.** Add a dated `Performance (tuned ...)` line under the\n   expression's heading on the relevant page in\n   `docs\u002Fsource\u002Fcontributor-guide\u002Fexpression-audits\u002F` (naming the technique, speedup, PR, and\n   benchmark file) so contributors can see what has already been tuned. Check this page before\n   starting, too — it tells you whether the expression was already optimized.\n\n## The gate: what blocks a submission\n\n- **A shape got meaningfully and reproducibly slower.** Do NOT submit. Even a 90%-faster-no-nulls\n  win does not justify a 30%-slower-dense-nulls loss. Either gate the fast path behind a per-batch\n  runtime check that picks the right path, or abandon the change. A Comet PR was closed for exactly\n  this. \"Reproducibly\" matters: confirm a flagged regression on a second sample first (step 6) —\n  a ~2% flag on a code path you did not touch is noise, not a blocker.\n- **No meaningful speedup on any shape.** There is nothing to submit. A change inside criterion's\n  noise threshold is not an improvement.\n- **Output differs from `main`** on any input, including null placement or error behavior.\n- **You only benchmarked one shape.** You have not shown the absence of a regression.\n\n## Red flags — STOP\n\n- \"It's obviously faster, I don't need to benchmark all shapes\" → dense nulls \u002F long values \u002F the\n  error path are where fast paths regress. Benchmark them.\n- \"The values are right, I'll assume nulls are fine\" → null-buffer bugs are the most common\n  correctness failure. Diff the null buffer.\n- \"I'll apply the fallible conversion to every slot\" → a garbage value under a null must not raise\n  an error Spark does not. Use `try_unary` or skip null slots.\n- \"One benchmark improved, ship it\" → re-read the gate. One improvement plus one regression is not\n  a win.\n\n## Rationalization table\n\n| Excuse                                                               | Reality                                                                                                                                                                                              |\n| -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| \"Measuring the baseline is overhead, I'll benchmark once at the end\" | Without a `main` baseline you cannot report a change %, and you cannot tell a win from noise. Baseline first.                                                                                        |\n| \"Dense-null regression is an edge case\"                              | Real columns have dense nulls. A regression there is a regression. Gate the path or drop it.                                                                                                         |\n| \"Existing tests are enough proof, no need to check the null buffer\"  | Tests may not assert null placement. Confirm bit-identical output explicitly.                                                                                                                        |\n| \"This trades a bit of the null case for a big win elsewhere\"         | That is a trade-off, not an optimization. Only submit a strict improvement (or a correctly-gated per-batch path).                                                                                    |\n| \"I'll edit the code, then run the baseline\"                          | `cargo bench` compiles from disk. A baseline built with your change already applied measures the optimized code and hides the real speedup. Baseline on unmodified source; stash the edit if needed. |\n| \"One shape flagged a 2% regression, abandon it\"                      | Criterion compares separate runs; small flags on an untouched code path are cross-run noise. Take a second sample before deciding — real regressions reproduce.                                      |\n\n## Related skills\n\n- `audit-comet-expression` — shore up test coverage before optimizing when the gate is thin.\n- `implement-comet-expression` — for a brand-new expression, not an existing one.\n- `wire-datafusion-function` — for wiring an existing upstream function.\n",{"name":5,"description":7,"argument-hint":47},"\u003Cexpression-name>","main","7deeba21a42e4a9cd34f43e7ed6e960e4e851b26",".ai\u002Fskills\u002Foptimize-comet-expression",418,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet","https:\u002F\u002Fdatafusion.apache.org\u002Fcomet","https:\u002F\u002Fgithub.com\u002Fapache","https:\u002F\u002Fwww.apache.org\u002F","2026-11-15 03:15:20",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add apache\u002Fdatafusion-comet --skill optimize-comet-expression",{"tool":63,"command":64},"bunx","bunx skills add apache\u002Fdatafusion-comet --skill optimize-comet-expression",{"tool":66,"command":67},"pnpm","pnpm dlx skills add apache\u002Fdatafusion-comet --skill optimize-comet-expression","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Foptimize-comet-expression\u002FSKILL.md",true,[],[72,95,121,142,159,170],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":83,"publishedAt":42},"01M6ACJR50ZS7F1QX58JEKCGVM","wire-datafusion-function","Use when wiring an existing DataFusion or datafusion-spark function into Comet for a Spark expression. Identifies the right wiring pattern (one-line passthrough, datafusion-spark UDF registration, or custom serde with input massaging \u002F restrictions), applies the Scala serde, registers the UDF in jni_api when needed, and adds SQL file tests. Assumes the function already exists upstream — if not, switch to `implement-comet-expression`.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Fwire-datafusion-function\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[36,84,85,86,41,39,87,88,27,32,89,20,90,34,26,24,91,92,25,93,94],"wire datafusion function","sql","scala","registration","switch","custom","tests","file","api","with","name",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":42},"01M6ACJPDDPND6FHE2PC1CJ4D3","suggest-native-expression","Use when picking the next Spark expression to implement natively in Comet, or when asked whether a specific codegen-dispatched expression is worth a native Rust implementation. Scores the candidate on how likely a native path can be 100% Spark-compatible and how much throughput or allocation it would save versus the JVM codegen dispatcher, records the verdict in the per-expression audit log so disqualified candidates are not re-litigated, and files a GitHub issue for the recommendation.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Fsuggest-native-expression\u002FSKILL.md",[],[102,20,103,104,105,106,41,39,107,108,24,109,110,111,112,113,114,115,116,117,118,119,120],"suggest native expression","native","dispatcher","github","rust","re","files","candidate","log","jvm","next","how","audit","audit log","allocation","issue","throughput","path","save",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":42},"01M6ACJMHPEN7E76VPKC3P4X6C","review-comet-shuffle-pr","Use when reviewing a DataFusion Comet pull request that touches native or JVM columnar shuffle, the shuffle writers and readers, partitioning, the Arrow IPC block format, shuffle compression, or the Celeborn integration. Load alongside review-comet-pr.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Freview-comet-shuffle-pr\u002FSKILL.md",[],[128,129,130,131,132,36,133,34,134,24,135,136,111,103,137,138,139,140,141],"review comet shuffle pr","pr","review","pull","pull request","arrow","load","ipc","number","request","format","integration","block","compression",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":42},"01M6ACJHX8BES7ZNNRNVCQ4QWE","review-comet-pr","Use when reviewing a DataFusion Comet pull request. Covers the workflow that applies to every PR and routes to the area-specific review skills for expressions, FFI, memory management, shuffle, Iceberg writes, and documentation. Provides guidance to a human reviewer rather than posting comments.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Freview-comet-pr\u002FSKILL.md",[],[129,130,149,131,150,132,151,36,152,153,24,136,154,155,137,156,27,34,157,158],"review comet pr","iceberg","memory","workflow","documentation","reviewer","human","posting","review skills","comments",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":42},"01M6ACJFM0QS61Z1RW516HXN2M","review-comet-memory-pr","Use when reviewing a DataFusion Comet pull request that touches memory pools, memory reservations, spilling, the Spark TaskMemoryManager bridge, allocators, or memory-related configuration. Load alongside review-comet-pr.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Freview-comet-memory-pr\u002FSKILL.md",[],[129,151,166,130,131,132,36,39,167,168,34,134,24,136,137,169],"review comet memory pr","bridge","reservations","configuration",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":42},"01M6ACJCV64V0FZPMVXDE2K3DX","review-comet-iceberg-write-pr","Use when reviewing a DataFusion Comet pull request that touches Iceberg writes, the split-operator write plan (IcebergWriteStrategy, IcebergWriteExec, IcebergCommitExec), the native Iceberg writer (CometIcebergWriteExec, iceberg_write.rs, iceberg_partition_path.rs), its eligibility gate (CometIcebergNativeWrite), or the iceberg-rust pin. Load alongside review-comet-pr.","https:\u002F\u002Fgithub.com\u002Fapache\u002Fdatafusion-comet\u002Fblob\u002Fmain\u002F.ai\u002Fskills\u002Freview-comet-iceberg-write-pr\u002FSKILL.md",[],[129,150,177,130,178,131,132,36,106,179,180,181,34,134,182,24,136,183,184,103],"review comet iceberg write pr","write","writer","write plan","partition","pin","split","plan"]