Box
asgeirtj/system_prompts_leaks
Search, read, upload, download, move, rename, delete, restore, and share Box content; manage comments and metadata.
A skill your agent uses for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture…
MITAuto-check passed
Install Geometry And Evaluation
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .claude/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .claude/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .agents/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .agents/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .cursor/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .cursor/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .gemini/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .gemini/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .github/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .github/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill geometry-and-evaluation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation .opencode/skills/geometry-and-evaluation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "geometry-and-evaluation" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation into .opencode/skills/geometry-and-evaluation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "geometry-and-evaluation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
geometry-and-evaluation- GitHub stars
- 330
- Token cost
- ~1.2k tokens
- SKILL.md length
- 515 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture…
- Works in 7 steps: Normalize every box array to an explicit… → Check dimensions are positive, row… → For corners, use center_to_corner_box3d… → …
- CPU-safe SECOND box geometry
- SKILL.md covers Operating boundary, Safe workflow, API and failure routing and Verification status and…
- Runs Python scripts from its folder; calls python
What it does
Geometry And Evaluation is an agent skill from VectorSpaceLab/AREX-Skill. Use for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture validation.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/api-reference.md`, `references/coordinate-systems.md` and `references/evaluation.md`).
The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- CPU-safe SECOND box geometry
- Coordinate conversion
- Encoding and target assignment
- IoU/NMS decisions
Example prompts
- “/geometry-and-evaluation”
Requirements
- Python 3
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Normalize every box array to an explicit shape and convention. Internal lidar
- Check dimensions are positive, row counts agree, calibration matrices are
- For corners, use center_to_corner_box3d with lidar axis=2 and the correct
- For regression, pair each target with its anchor ([N,7]), select linear
- For assignment, inspect feature-map order [D,H,W], class-specific anchor
- Treat NMS as a separate backend decision. The axis-aligned nms_jit
- For KITTI, validate annotation keys, class spelling, dimensions, camera/lidar
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Geometry And Evaluation loads about 1.2k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 515 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its MIT licence (© VectorSpaceLab). 515 words, ~1,164 tokens.
Download SKILL.mdSave it as
.claude/skills/geometry-and-evaluation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- geometry-and-evaluation
- description
- Use for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture validation.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Geometry and evaluation
Use this route when a task mentions lidar or camera boxes, corners, yaw, encode/decode, anchors, target assignment, IoU, NMS, KITTI labels/AP, NuScenes result JSON, or coordinate transforms. This is a static/CPU-safe operating route. It does not prove detector execution.
Operating boundary
Prefer NumPy-only geometry and fixture checks. Read api-reference.md for signatures, shapes, and source-faithful dimension order.
Read coordinate-systems.md before converting KITTI camera boxes, internal lidar boxes, or NuScenes boxes.
Read evaluation.md before building annotations, interpreting AP, or writing NuScenes submissions.
Run the bundled helper before changing box conventions:
bash python skills/disco/second-pytorch/sub-skills/geometry-and-evaluation/scripts/geometry_smoke.py --help python skills/disco/second-pytorch/sub-skills/geometry-and-evaluation/scripts/geometry_smoke.pyExpected output contains four
[PASS]checks andgeometry smoke: PASS; the helper imports only NumPy and never imports the detector, spconv, Numba CUDA, or Torch.
Safe workflow
- Normalize every box array to an explicit shape and convention. Internal lidar
boxes are normally
[N, 7] = [x, y, z, w, l, h, rz]; preserve any velocity or custom values only after documenting their trailing columns. - Check dimensions are positive, row counts agree, calibration matrices are homogeneous-compatible, and labels/scores have the same first dimension.
- For corners, use
center_to_corner_box3dwith lidaraxis=2and the correct origin; usecenter_to_corner_box2dfor[x, y, w, l, rz]. Never silently swapw,l,hwith KITTIl,h,w. - For regression, pair each target with its anchor (
[N,7]), select linear dimensions or log dimensions consistently, and compare decoded centers, dimensions, and angle modulo the selected period. Vector-angle coding has code size 8 rather than 7. - For assignment, inspect feature-map order
[D,H,W], class-specific anchor ranges, thresholds, and label semantics (1+positive,0negative,-1ignore). Use a tiny overlap matrix before sampling positives. - Treat NMS as a separate backend decision. The axis-aligned
nms_jitalgorithm is CPU NumPy/Numba math, but its historical module may import legacy spconv transitively; rotated CPU NMS depends on the same helpers. GPU NMS and rotated IoU use legacy Numba CUDA/spconv interfaces and are not verified. - For KITTI, validate annotation keys, class spelling, dimensions, camera/lidar
convention, and
z_axis/z_centerbefore calling evaluation. For NuScenes, validate sample tokens, class mapping, quaternion andwlhorder, range filtering, and required devkit availability before invoking the evaluator.
Show full SKILL.md (165 more words)Show less
API and failure routing
- Use api-reference.md for box math, anchors, target assignment, similarity, point-in-box, and NMS signatures.
- Use coordinate-systems.md for axes, origins, angle periods, calibration direction, and visualization conventions.
- Use evaluation.md for KITTI schemas, metric output shapes, NuScenes JSON fields, and minimal perfect-match fixtures.
- Use troubleshooting.md when imports, optional dependencies, malformed arrays/configs, CLI/API calls, or evaluator output fail.
Verification status and historical caveats
This checkout has no setup metadata. The model path uses legacy spconv and Numba
APIs; modern spconv 2.x is not proven compatible. The inspection environment had
NumPy, Numba, Torch, spconv, Fire, tensorboardX, nuscenes-devkit, and related
packages, and an A100 CUDA smoke was available, but detector execution was not
accepted as verified. In particular, the installed spconv did not expose the
legacy non_max_suppression/VoxelGeneratorV2 interfaces. Do not claim that GPU
NMS kernels, modern spconv NMS, or the full detector runtime executed successfully.
For new detector work, treat this route as historical guidance and prefer a
maintained SECOND implementation rather than extending the deprecated runtime.
© VectorSpaceLab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/coordinate-systems.md
- references/evaluation.md
- references/troubleshooting.md
- scripts/geometry_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Geometry And Evaluation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Geometry And Evaluation this skillVectorSpaceLab/AREX-Skill | 330 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Boxasgeirtj/system_prompts_leaks | 69k | — | ~1.1k | Automated safety check: Pass | CC0-1.0 | |
| Arize Evaluatorgithub/awesome-copilot | 40k | 1 repos | ~8.1k | Automated safety check: Notes | MIT | |
| LLM Evaluationdavila7/claude-code-templates | 32k | 12 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Agent Evaluationsickn33/agentic-awesome-skills | 47k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Modeling Conversion MetricsPostHog/posthog | 40k | — | ~1.4k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Arize Evaluator
github/awesome-copilot
Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and…
LLM Evaluation
davila7/claude-code-templates
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
Agent Evaluation
sickn33/agentic-awesome-skills
Evaluate agent behavior with versioned cases and explicit verifiers.
- Official
Modeling Conversion Metrics
PostHog/posthog
Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.
Evaluators
Arize-ai/phoenix
Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output.
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Questions about Geometry And Evaluation
What does Geometry And Evaluation do?
A skill your agent uses for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture…. Geometry And Evaluation is an agent skill from VectorSpaceLab/AREX-Skill. Use for CPU-safe SECOND box geometry, coordinate conversion, encoding and target assignment, IoU/NMS decisions, KITTI or NuScenes evaluation, result conversion, and tiny-fixture validation.
When should I use Geometry And Evaluation?
Geometry And Evaluation fits situations like: CPU-safe SECOND box geometry; coordinate conversion; encoding and target assignment; ioU/NMS decisions.
How do I install Geometry And Evaluation in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation in VectorSpaceLab/AREX-Skill) into .claude/skills/geometry-and-evaluation in your project. Claude Code loads it when a task matches its description.
How do I install Geometry And Evaluation in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a codex`. Or copy the skill folder (skills/repositories/repo-skills/second-pytorch/sub-skills/geometry-and-evaluation in VectorSpaceLab/AREX-Skill) into .agents/skills/geometry-and-evaluation in your project. Codex loads it when a task matches its description.
Can I use Geometry And Evaluation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill geometry-and-evaluation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/geometry-and-evaluation, .gemini/skills/geometry-and-evaluation, .github/skills/geometry-and-evaluation and .opencode/skills/geometry-and-evaluation in your project.
What does Geometry And Evaluation need to run?
Going by SKILL.md and its folder, Geometry And Evaluation needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Geometry And Evaluation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Geometry And Evaluation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Geometry And Evaluation use?
Geometry And Evaluation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Geometry And Evaluation use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.2k tokens, read only when the agent opens those files.
What are the alternatives to Geometry And Evaluation?
Skills that share tags, products or a category with Geometry And Evaluation: Box (asgeirtj/system_prompts_leaks, 69k stars), Arize Evaluator (github/awesome-copilot, 40k stars), LLM Evaluation (davila7/claude-code-templates, 32k stars) and Agent Evaluation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Geometry And Evaluation?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.