compost
Run long or repetitive commands (builds, pytest/ctest, SLURM jobs, solver logs) through a clustering summarizer instead of reading raw output; re-runs show only what changed. Use for output likely over ~100 lines or fix-test-fix loops.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 5
- Forks
- 1
01 前言 Front Matter
- name
- compost
- description
- Run long or repetitive commands (builds, pytest/ctest, SLURM jobs, solver logs) through a clustering summarizer instead of reading raw output; re-runs show only what changed. Use for output likely over ~100 lines or fix-test-fix loops.
- allowed-tools
- Bash(${CLAUDE_SKILL_DIR}/bin/compost *), Bash("${CLAUDE_SKILL_DIR}/bin/compost" *)
02 资源文件 23
- 其他.gitignore29 B
- 其他bin/compost731 B
- 参考文档references/profiles.md2.1 KB
- 参考文档references/schema.md4.0 KB
- 脚本scripts/cg_mode.py5.4 KB
- 脚本scripts/co_cluster.py5.3 KB
- 脚本scripts/co_hook.py6.8 KB
- 脚本scripts/co_profiles.py22.3 KB
- 脚本scripts/co_store.py10.5 KB
- 脚本scripts/compost.py29.2 KB
- 其他tests/fixtures/ansi_clang.log699 B
- 其他tests/fixtures/clean_pass.log352 B
- 其他tests/fixtures/gcc_errors.log37.0 KB
- 其他tests/fixtures/ninja_cmake_build.log698 B
- 其他tests/fixtures/opaque_fail.log141 B
- 其他tests/fixtures/pytest_assert.log1.5 KB
- 其他tests/fixtures/pytest_diff_1.log398 B
- 其他tests/fixtures/pytest_diff_2.log398 B
- 其他tests/fixtures/pytest_fail.log12.3 KB
- 其他tests/fixtures/slurm_oom.log362 B
- 其他tests/fixtures/solver_run1.log859 B
- 其他tests/fixtures/solver_run2.log956 B
- 脚本tests/smoke_test.sh20.3 KB
03 SKILL.md 正文
compost
!"${CLAUDE_SKILL_DIR}/bin/compost" mode --banner
Agents that do not expand the line above (e.g. Codex): run
<this-skill-dir>/bin/compost mode --banner first and follow it.
Offline, deterministic: output is parsed and clustered by script (no LLM); the full raw output is always kept on disk. Skip it for short output -- just read that directly.
compost is not on PATH: always use the full <this-skill-dir>/bin/compost
path (or python3 <this-skill-dir>/scripts/compost.py if executables are
not permitted).
- Run:
<this-skill-dir>/bin/compost run -- <command...>(pipes/redirects needbash -c '...'). Prints the root error (first error in user code), secondary failure groups with counts, warnings, numerical summary, and araw_output_id. - Read the summary, not the raw log.
- Re-run the same command the same way: only new/resolved errors and count deltas are printed ("No structural changes." if none).
- Only if the summary is insufficient, use the printed
retrieval_handles(get <id> --lines A:B,event <id> --event N,grep <id> '<pattern>',show <id> --json). They never re-run the command; they read the already-stored raw output. - Existing log file:
bin/compost ingest --file <path>(or--stdin). - The plugin's Bash hook may deny a raw build/test command and name the
compost command to run instead: run that. Need raw output (e.g. to show
the user)? Append
# rawto the command.
Profiles (auto-detected, --profile to override): pytest, ctest, gcc/clang,
cmake, python_traceback, slurm, numerical_solver, generic.
Output fields, statuses, storage and retention: references/schema.md.
Per-profile detection: references/profiles.md.
04 同仓库更多 Skills
file-organizer
Reorganize and rename files into tidy folder structures. Use when asked to sort, organize, or restructure a messy directory of files.
bloated-skill
Safely delete data files (CSV, temp, stale files) from a repository with mandatory user confirmation before every deletion. Use when asked to delete, remove, or clean up data files.
bloated-skill
This skill helps you with various tasks related to code and data. It is designed to assist you in many situations. Use it whenever you need help with things.
weeder
Measure and reduce a Skill's token footprint (always-loaded description + on-trigger SKILL.md body) without regressing routing accuracy or losing instructions. Use when a SKILL.md feels oversized, repeats rules, or has a vague description that might mis-route.
seedbank
Maintain a small, generated AGENTS.md of repository facts (build commands, conventions, invariants, past mistakes) that were rediscovered often or were costly to get wrong. Use at task start to check cached facts, and at task end to log and promote what you had to dig for.
pruner
Pick the smallest set of file:line ranges relevant to a concrete task (bug, compiler error, failing test, change) in a large Python or C/C++ repository, instead of grep-exploring or reading whole files. Skip when the task or traceback already names the file.