Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Install OrcaSlicer 3MF and G-code Workflow
$ npx skills add autonomous-ai/openharness --skill orcaslicer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness orcaslicer --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .claude/skills/orcaslicer && 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 "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .claude/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicerType 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 autonomous-ai/openharness --skill orcaslicer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness orcaslicer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .agents/skills/orcaslicer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .agents/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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 autonomous-ai/openharness --skill orcaslicer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness orcaslicer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .cursor/skills/orcaslicer && 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 "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .cursor/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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/autonomous-ai/openharness.git --path store/agents/orca-slicer/skills/orcaslicer--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 autonomous-ai/openharness --skill orcaslicer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness orcaslicer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .gemini/skills/orcaslicer && 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 "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .gemini/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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 autonomous-ai/openharness orcaslicerInstalls 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 autonomous-ai/openharness --skill orcaslicer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .github/skills/orcaslicer && 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 "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .github/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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 autonomous-ai/openharness --skill orcaslicer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness orcaslicer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/orca-slicer/skills/orcaslicer .opencode/skills/orcaslicer && 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 "orcaslicer" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/orca-slicer/skills/orcaslicer into .opencode/skills/orcaslicer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "orcaslicer", 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
orcaslicer- GitHub stars
- 1.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 779 words
- Files
- 15 (incl. scripts)
- Skills in repo
- 99
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
- Slicing an STL for a specific printer, nozzle and filament
- SKILL.md covers Establish the brief, Build, inspect, revise, Deliver a reusable result and What the checks establish
- Runs JavaScript and Shell scripts from its folder; calls node and sh
- Comparing a few slicing plans before starting a print
What it does
The agent first collects the brief: the mesh, its intended size in millimetres, the real printer model, nozzle, firmware, plate and filament, and the tradeoff that matters most. It saves this into a slice-config.json following a template schema, with a source-file allowlist, expected model size, rotation and scale, profile source, machine temperature limits, and one to four plans with layer heights, walls, infill, supports and brim. Without hardware details it produces a clearly labelled software-only example.
`scripts/slice-part.sh` builds and checks the result. The supported scope is one closed STL, one extruder, Marlin or Marlin 2 firmware and a zero-origin rectangular bed without exclusion zones. Klipper macros, multi-material, belt printers and firmware retraction fail explicitly rather than pass. Node 22 or newer and OrcaSlicer 2.4.2 are the tested versions, configured with the `ORCA_BIN` and `ORCA_PROFILES_DIR` variables.
When your agent uses it
- Slicing an STL for a specific printer, nozzle and filament
- Comparing a few slicing plans before starting a print
- Exporting an editable 3MF project and checked G-code from a mesh
Example prompts
- “Slice bracket.stl for my Marlin printer and PETG filament, and compare a fast plan against a strong one.”
- “Give me an editable 3MF project and G-code for the phone stand mesh with supports off.”
- “Revise the selected plan so the brim is wider, then rerun the checks.”
Requirements
- OrcaSlicer 2.4.2, the tested version
- Node 22 or newer
What it can do on your machine
Read from SKILL.md and the folder at commit 74c2733. 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 14 files in scripts/ (JavaScript and Shell), which the agent can run.
Shell commands in SKILL.md call:
nodesh
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
OrcaSlicer 3MF and G-code Workflow loads about 1.5k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 779 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 autonomous-ai/openharness at commit 74c2733, republished under its MIT licence (© autonomous-ai). 779 words, ~1,519 tokens.
Download SKILL.mdSave it as
.claude/skills/orcaslicer/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.- name
- orcaslicer
- description
- Turn a user's STL and explicit machine/material requirements into compared OrcaSlicer plans, editable 3MF projects, checked G-code and a portable handoff. Use for Orca Slicer harness work.
Strata: mesh to an owned slicing project
Establish the brief
Ask for a mesh, its intended millimetre dimensions and use, and the actual
printer model, nozzle, firmware, plate and filament. Ask which tradeoff matters.
If those details are unavailable, a clearly labelled software-only example is
useful; keep machine.context: "example". No hardware is needed to compare,
inspect, revise or export it. Do not treat the example as the user's printer.
Start from the schema in template/slice-config.json in this package. Save the
brief before running the slicer:
sourceFilesis the explicit portable-source allowlist. Include the config, STL, supporting CAD/notes and all workspace-profile inheritance files. Never add unrelated workspace files or credentials.model.expectedSizeMMis the requirement, not a value copied back from a failed output. STL has no unit metadata.rotationDegreesrotates X, then Y, then Z;scaleis explicit. Orca cannot silently reorient this workflow.profiles.sourceisinstalledorworkspace. Installed paths are relative toORCA_PROFILES_DIRor Orca's bundled profiles directory. Workspace paths are safe relative paths, with inherited JSON parents beside the child. Remove connection credentials and post-processors from exported profiles.machinerecords independent model/nozzle/bed/plate/firmware/material and temperature envelopes. These bounds apply to all nonzero heater commands, including startup targets; they are not measured temperatures.- Save 1–4
plans, aselectedPlan, estimate budgets and a bed inset. Each plan states layer/first-layer heights, walls, infill, top/bottom layers, supports and brim. Changing a prose note does not change a slicing setting.
The current checked scope is one closed STL, one extruder, Marlin or Marlin 2, and a zero-origin rectangular bed without exclusion zones. Unknown fields, unsupported motion/macros and missing profiles fail explicitly. Do not broaden a passing claim to Klipper macros, multi-material, belt/nonrectangular machines or firmware retraction. Unsupported machines need a separately implemented and verified workflow, not an arbitrary flag change.
Build, inspect, revise
sh "$ORCA_SKILLS/orcaslicer/scripts/slice-part.sh"Node 22+ and OrcaSlicer 2.4.2 are tested. Set ORCA_BIN and, where needed,
ORCA_PROFILES_DIR. This helper does not use PrusaSlicer's different CLI.
It creates an isolated Orca data directory and fresh output per plan; no printer
connection is made. Arc fitting, post-processing, spiral mode and infill
combination are disabled. Top/bottom thickness minima are zero so the saved
layer counts are not silently overridden by inherited minimum-thickness values.
Open preview.html in the harness. Compare estimates, inspect the first layer,
isolate layers, show travel and use Full motion to include purge, Z hops and
final parking. The normal layer list includes extrusion heights, not every
travel height. Custom purge may legitimately lie outside the model inset;
review its separately reported full-motion bounds and exact commands.
Use handoff/report.json for the saved source revision, profile names, effective
settings, checks, temperatures and native-reopen evidence. The live verdict is
.harness/verdict.json; a retained preview after a failure is an older success.
.harness/slice.log contains native diagnostics. Never hand-edit checks or
readiness to suppress a failure.
Make revisions in the saved inputs, then rebuild. Check that the requested
change appears in effective settings and actual paths/estimates. Discuss the
tradeoff without promising strength, finish or physical fit from wall counts.
The included model.scad is provenance, not an automatically compiled input:
after CAD changes, re-export its STL before slicing.
Show full SKILL.md (263 more words)Show less
Deliver a reusable result
Each handoff/plans/<id>/ contains actual G-code, native editable project.3mf,
effective JSON and an inspection receipt. part.gcode and part.3mf are the
selected plan. The complete-project ZIP includes declared source, flattened
profiles, all native results and standalone Node helpers. It excludes unrelated
files and the Orca binary. Respect upstream profile notices.
Reopen the chosen 3MF in OrcaSlicer. For a handoff verification, extract the ZIP
into a separate directory and run node rebuild/build.mjs with ORCA_BIN set.
Use node rebuild/serve-preview.mjs . for its loopback viewer; file:// cannot
fetch toolpaths. Downloaded review JSON saves plan/view/notes and restores only
against the matching source and G-code hashes. It is not print authorization.
What the checks establish
The helper measures mesh closure/orientation, dimensions and bed envelope;
checks effective settings against emitted G-code settings and saved constraints;
inspects linear model/support centerlines, layer heights, estimate budgets and
actual heater target commands; requires both heaters off after final extrusion;
and verifies exact embedded G-code plus native 3MF geometry/settings reopening.
The only reopen normalization is absent versus empty upward_compatible_machine
preset metadata. No slicing value is ignored.
Limits: 32 MiB per source/G-code/download, 64 MiB total declared sources, 1,000,000 linear moves, 1,000,000 STL triangles, 4 plans, 128 MiB expanded ZIP. Mesh checks weld at 1e-5 mm; they do not prove no self-intersections. The parser models retraction debt, units and coordinate/extrusion modes, but not actual firmware motion, offsets, leveling, pressure/flow overrides, collisions, thermal behavior, support adequacy or material mechanics. Estimates are not timed prints. No physical print or safety certification is implied. Never upload or print without a separate explicit request and the appropriate machine-specific review.
© autonomous-ai, 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 14 other files (scripts) in store/agents/orca-slicer/skills/orcaslicer of autonomous-ai/openharness.
- SKILL.md
- scripts/LICENSE
- scripts/archive.mjs
- scripts/build.mjs
- scripts/contract.mjs
- scripts/files.mjs
- scripts/gcode.mjs
- scripts/mesh.mjs
- scripts/native.mjs
- scripts/preview.css
- scripts/preview.html
- scripts/preview.js
- scripts/profiles.mjs
- scripts/serve-preview.mjs
- scripts/slice-part.sh
Open the folder on GitHubat commit 74c2733
Compare with similar skills
OrcaSlicer 3MF and G-code Workflow 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 |
|---|---|---|---|---|---|---|
| OrcaSlicer 3MF and G-code Workflow this skillautonomous-ai/openharness | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Manim Video Productionbrowser-use/video-use | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| Algorithmic Art with p5.jsanthropics/skills | 180k | 38 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Canvas Designanthropics/skills | 180k | 52 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill | 134k | 1 repos | ~3.5k | Automated safety check: Pass | MIT | |
| HyperFrames Animationheygen-com/hyperframes | 59k | 3 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Algorithmic Art with p5.js
anthropics/skills
Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.
- Official
Canvas Design
anthropics/skills
Creates original posters and static art as PNG or PDF by first writing a short design philosophy, then expressing it visually on a canvas.
Brand and Design Toolkit
nextlevelbuilder/ui-ux-pro-max-skill
Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.
HyperFrames Animation
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
- Official
Slack GIF Creator
anthropics/skills
Provides Slack size and frame limits, Python animation helpers and validators for building animated GIFs sized for emoji and messages.
More from autonomous-ai/openharness
All 99 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
CAD Viewer Launcher
autonomous-ai/openharness
Starts a local CAD Viewer server for a directory of CAD, robot-description or DXF files and returns a live review link, reusing a running instance when one already serves that directory.
Related
Categories
Questions about OrcaSlicer 3MF and G-code Workflow
What does OrcaSlicer 3MF and G-code Workflow do?
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff. The agent first collects the brief: the mesh, its intended size in millimetres, the real printer model, nozzle, firmware, plate and filament, and the tradeoff that matters most.json following a template schema, with a source-file allowlist, expected model size, rotation and scale, profile source, machine temperature limits, and one to four plans with layer heights, walls, infill, supports and brim.
When should I use OrcaSlicer 3MF and G-code Workflow?
OrcaSlicer 3MF and G-code Workflow fits situations like: slicing an STL for a specific printer, nozzle and filament; comparing a few slicing plans before starting a print; exporting an editable 3MF project and checked G-code from a mesh.
How do I install OrcaSlicer 3MF and G-code Workflow in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill orcaslicer -a claude-code`. Or copy the skill folder (store/agents/orca-slicer/skills/orcaslicer in autonomous-ai/openharness) into .claude/skills/orcaslicer in your project. Claude Code loads it when a task matches its description.
How do I install OrcaSlicer 3MF and G-code Workflow in Codex?
Run `npx skills add autonomous-ai/openharness --skill orcaslicer -a codex`. Or copy the skill folder (store/agents/orca-slicer/skills/orcaslicer in autonomous-ai/openharness) into .agents/skills/orcaslicer in your project. Codex loads it when a task matches its description.
Can I use OrcaSlicer 3MF and G-code Workflow 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 autonomous-ai/openharness --skill orcaslicer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orcaslicer, .gemini/skills/orcaslicer, .github/skills/orcaslicer and .opencode/skills/orcaslicer in your project.
What does OrcaSlicer 3MF and G-code Workflow need to run?
Going by SKILL.md and its folder, OrcaSlicer 3MF and G-code Workflow needs JavaScript and a shell for the scripts in its folder and the command-line tools its instructions call (node and sh). Our summary lists: OrcaSlicer 2.4.2, the tested version; Node 22 or newer.
Does OrcaSlicer 3MF and G-code Workflow 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 OrcaSlicer 3MF and G-code Workflow 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 OrcaSlicer 3MF and G-code Workflow use?
OrcaSlicer 3MF and G-code Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does OrcaSlicer 3MF and G-code Workflow use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to OrcaSlicer 3MF and G-code Workflow?
Skills that share tags, products or a category with OrcaSlicer 3MF and G-code Workflow: Manim Video Production (browser-use/video-use, 28k stars), Algorithmic Art with p5.js (anthropics/skills, 180k stars), Canvas Design (anthropics/skills, 180k stars) and Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 134k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains OrcaSlicer 3MF and G-code Workflow?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,194 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 9, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.