Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time.
Install Learning Harvest
$ npx skills add techygarg/lattice --skill learning-harvest -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install techygarg/lattice learning-harvest --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/techygarg/lattice.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learning-harvest .claude/skills/learning-harvest && 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 "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .claude/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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/techygarg/lattice/tree/main/skills/learning-harvestType 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 techygarg/lattice --skill learning-harvest -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install techygarg/lattice learning-harvest --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techygarg/lattice.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/learning-harvest .agents/skills/learning-harvest && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .agents/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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 techygarg/lattice --skill learning-harvest -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install techygarg/lattice learning-harvest --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techygarg/lattice.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/learning-harvest .cursor/skills/learning-harvest && 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 "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .cursor/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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/techygarg/lattice.git --path skills/learning-harvest--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 techygarg/lattice --skill learning-harvest -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install techygarg/lattice learning-harvest --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techygarg/lattice.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/learning-harvest .gemini/skills/learning-harvest && 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 "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .gemini/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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 techygarg/lattice learning-harvestInstalls 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 techygarg/lattice --skill learning-harvest -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/techygarg/lattice.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/learning-harvest .github/skills/learning-harvest && 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 "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .github/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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 techygarg/lattice --skill learning-harvest -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install techygarg/lattice learning-harvest --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techygarg/lattice.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/learning-harvest .opencode/skills/learning-harvest && 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 "learning-harvest" agent skill from https://github.com/techygarg/lattice/tree/main/skills/learning-harvest into .opencode/skills/learning-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-harvest", 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
learning-harvest- GitHub stars
- 199
- Token cost
- ~2.4k tokens
- SKILL.md length
- 1,197 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- MIT
At a glance
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time.
- Works in 4 steps: Check .lattice/config.yaml for… → If set and the file exists at that path… → If set but no file exists there → tell… → …
- A workflow session completes and produced insights worth persisting
- SKILL.md covers Scope Boundary, Config Resolution, Document Structure and Load Behavior, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Learning Harvest is an agent skill from techygarg/lattice. Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes and produced insights worth persisting, when starting a session that should benefit from prior patterns, or when the user says 'harvest learnings', 'what have we learned', 'capture this pattern'…
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts. The licence is MIT.
When your agent uses it
- A workflow session completes and produced insights worth persisting
- Starting a session that should benefit from prior patterns
- The user says harvest learnings
- What have we learned
Example prompts
- “harvest learnings”
- “what have we learned”
- “capture this pattern”
- “/learning-harvest”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Check .lattice/config.yaml for paths.operational_learnings.
- If set and the file exists at that path → use it.
- If set but no file exists there → tell the user which configured path is missing, then use the default…
- If not set → use the default .lattice/learnings/operational-learnings.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4d6c35f. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Learning Harvest loads about 2.4k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 1,197 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from techygarg/lattice at commit 4d6c35f, republished under its MIT licence (© techygarg). 1,197 words, ~2,443 tokens.
Download SKILL.mdSave it as
.claude/skills/learning-harvest/SKILL.md (or your agent's skills folder).- name
- learning-harvest
- description
- Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes and produced insights worth persisting, when starting a session that should benefit from prior patterns, or when the user says 'harvest learnings', 'what have we learned', 'capture this pattern', 'tighten learnings', 'compress learnings', or 'operational learnings'.
Learning Harvest
Scope Boundary
Operational learnings are NOT rules. They are what you learn while applying rules.
| Standards (refiner output, atom defaults) | Operational Learnings (this document) |
|---|---|
| "Domain layer must not import from infrastructure" | "When adding a new aggregate, we keep forgetting to define the repository interface first — design interface before implementation" |
| "Functions should have single responsibility" | "Service classes that start small grow past 500 lines within 3 features — split by command type proactively at ~200 lines" |
| "Value objects must validate in constructor" | "Date range VOs without explicit inclusive/exclusive documentation cause boundary bugs every time — document semantics alongside validation" |
The standard is the rule. The operational learning is what we discovered while applying the rule on this project.
If an entry reads like a rule that should always be followed, it belongs in a standards document (run the relevant refiner). If it reads like "here's what we keep learning the hard way" or "here's an approach that keeps working for us" — it belongs here.
Patterns that recur frequently may graduate to standards via a refiner. That promotion path is part of the Tighten behavior.
Config Resolution
- Check
.lattice/config.yamlforpaths.operational_learnings. - If set and the file exists at that path → use it.
- If set but no file exists there → tell the user which configured path is missing, then use the default
.lattice/learnings/operational-learnings.md. - If not set → use the default
.lattice/learnings/operational-learnings.md.
Backward compatibility: If default path not found, check these legacy paths in order:
.lattice/learnings.md— flat file at root.lattice/learnings/review-insights.md— prior naming convention
If found, offer migration to canonical path and format. If user declines, read as flat input. STOP: do not write to it.
Document Structure
# Operational Learnings
Experiential patterns from practice. Complements standards (what should be) with experience (what we keep learning).
## Design Patterns
<!-- Decomposition, architecture choices, scope decisions that proved good or bad -->
## Implementation Craft
<!-- Coding approaches, library gotchas, design-to-reality gaps -->
## Quality Signals
<!-- Recurring quality issues that keep appearing despite rules -->
## Reliability
<!-- Bug root causes, failure modes, fragile areas, boundary condition gaps -->
## Structural Health
<!-- Architectural drift, debt accumulation, coupling issues, migration lessons -->Entry format: - YYYY-MM-DD [context] Pattern — actionable takeaway
context: type of session (e.g., "design", "implementation", "review", "bug fix", "refactoring"). Not a feature name — learnings are cross-cutting.- Each entry ONE bullet, max 2 lines, scannable in under 10 seconds.
Load Behavior
Invoked at session start. Composing workflow passes a focus hint (relevant categories).
- Resolve file path per Config Resolution.
- If file not found — "No operational learnings yet." Continue. Non-blocking.
- If found — surface relevant entries (3-5 most recent from matching categories) as brief context. Treat as soft guidance, not hard constraints.
Active monitoring: Once loaded, maintain a silent harvest queue throughout the session. When a decision or trade-off passes the cross-cutting test below, add it to the queue. STOP: do not prompt immediately.
Cross-cutting test — a candidate must pass BOTH before queuing:
- It names a pattern or approach, not a feature-specific fact.
- A developer on a completely different feature could apply it without knowing this feature's context.
STOP: if either fails, skip entirely — do not queue.
Before queuing, check against entries loaded at session start. If the same pattern already exists — skip.
When to surface: Surface the queue as a single batch when EITHER condition is true — not at every level or layer:
- Queue reaches 3 candidates, OR
- A major phase completes (all design levels done, a full implementation layer done)
STOP: do not surface at every individual level approval or component completion — that is over-prompting. Once surfaced, clear the queue. Anything remaining at session end goes to Harvest.
"I noted [N] potential harvest candidates — worth a quick review?"
Mid-session interrupt (rare exception): surface a single pattern immediately, outside the queue, only when it would be impossible to reconstruct by session end — a live debate that resolved unexpectedly, a library gotcha caught mid-implementation. If in doubt, queue instead.
Session-end Harvest is the primary mechanism.
Show full SKILL.md (614 more words)Show less
Harvest Behavior
Invoked at session end. Composing workflow passes a session context (what kind of work happened).
Governing principle: STOP: the atom never writes autonomously. Session-end Harvest is the primary capture event — mid-session prompting is the exception.
Steps:
Drain the queue. Collect all candidates from active monitoring queue plus any new ones surfaced by reviewing session decisions and outcomes. Each candidate must have passed the cross-cutting test (active monitoring) or pass it now.
Propose as a batch. Present queued candidates together — not one per message:
Harvest candidates from this session:
- [Category] — [pattern in one line]
- [Category] — [pattern in one line]
Accept, edit, add your own, or skip entirely.
Empty queue and nothing new found? Say so in one line. STOP: do not force output.
Filter — apply before writing confirmed entries. For each entry the user accepts:
Filter Fail if... Evidence No concrete session event — just prior knowledge Cross-cutting Specific to this feature's domain, won't recur Actionable Requires this conversation's context to understand Recurrence No structural reason it will happen again Filter fails on a confirmed entry? Tell the user which filter — offer to reword. STOP: do not silently drop.
User decides. Accept, edit, reject, add their own, or skip all. STOP: do NOT argue for rejected entries.
Write confirmed entries only. Dedup against existing entries (update with a recurrence note if the same pattern exists). Create the file and directory if needed.
Assess health. Count entries per category and total (already read for dedup in Step 5). Any category exceeds ~10 entries, or total exceeds ~35 → note in one line: "Operational learnings is growing dense — say 'tighten learnings' to run Tighten standalone." Pattern recurred 4+ times → note it as a promotion candidate the same way. STOP: do not run Tighten in this session — flag only, never act.
Tighten Behavior
Invoked standalone only — Harvest may flag that tightening is due, but never launches it.
- Read full document.
- Identify: consolidation opportunities (same pattern, different words), noise (one-off, never recurred), promotion candidates (recurred 4+ times — suggest refiner), stale entries (project has changed).
- Present each candidate individually — consolidation, noise, promotion, and staleness are different judgment calls. Accept / edit / reject per candidate, not as one batch.
- Apply only what user confirms.
Self-Validation Checklist
Before writing any entry, verify ALL. STOP: if any fails, do not write.
- User confirmed — STOP: Explicit user approval for every entry. No exceptions.
- Evidence grounded — STOP: Produced by a specific session event, not prior knowledge.
- Experiential, not prescriptive — STOP: Reads like "what we learned" not "what the rule should be." If it's a rule, it belongs in standards via a refiner.
- Cross-cutting — STOP: Applies beyond this feature. Feature-specific decisions belong in context anchor doc.
- Actionable standalone — STOP: a developer on a different feature can act on this without this conversation's context. Confidence level is not a gate — the user decides if it is worth capturing.
- Not redundant — STOP: Not already in standards, atom defaults, or existing learnings. At most, add recurrence note.
- Concise — STOP: Scannable in 10 seconds. Two lines max.
All checks pass on an entry → write it.
Standalone Invocation
When invoked directly — not composed by a molecule — match the user's phrase to exactly one behavior. STOP: if ambiguous, ask — never guess.
| User says | Run |
|---|---|
| "tighten learnings", "compress learnings", "clean up learnings", "/learning-harvest tighten learnings" | Tighten Behavior |
| "harvest learnings", "capture this pattern", "log this learning" | Harvest Behavior |
| "what have we learned", "load learnings", bare "operational learnings" with no verb | Load Behavior |
STOP: if the phrase doesn't clearly map to one row, ask — "Load recent entries, harvest something new, or tighten the document?" — before running anything.
© techygarg, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/learning-harvest of techygarg/lattice.
Open the folder on GitHubat commit 4d6c35f
Compare with similar skills
Learning Harvest 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 |
|---|---|---|---|---|---|---|
| Learning Harvest this skilltechygarg/lattice | 199 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from techygarg/lattice
All 33 skills in this repoArchitecture Compass
techygarg/lattice
Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a…
Lattice Init
techygarg/lattice
Guided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority…
Skill Align
techygarg/lattice
Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory.
Skill Validate
techygarg/lattice
Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners.
Architecture Refiner
techygarg/lattice
Facilitate a structured conversation to define architecture principles for a repository.
Clean Code Refiner
techygarg/lattice
Facilitate a structured conversation to define clean code principles for a repository.
Related
Categories
Questions about Learning Harvest
What does Learning Harvest do?
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Learning Harvest is an agent skill from techygarg/lattice. Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time.
When should I use Learning Harvest?
Learning Harvest fits situations like: A workflow session completes and produced insights worth persisting; starting a session that should benefit from prior patterns; the user says harvest learnings; what have we learned.
How do I install Learning Harvest in Claude Code?
Run `npx skills add techygarg/lattice --skill learning-harvest -a claude-code`. Or copy the skill folder (skills/learning-harvest in techygarg/lattice) into .claude/skills/learning-harvest in your project. Claude Code loads it when a task matches its description.
How do I install Learning Harvest in Codex?
Run `npx skills add techygarg/lattice --skill learning-harvest -a codex`. Or copy the skill folder (skills/learning-harvest in techygarg/lattice) into .agents/skills/learning-harvest in your project. Codex loads it when a task matches its description.
Can I use Learning Harvest 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 techygarg/lattice --skill learning-harvest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learning-harvest, .gemini/skills/learning-harvest, .github/skills/learning-harvest and .opencode/skills/learning-harvest in your project.
What does Learning Harvest need to run?
SKILL.md names no scripts, command-line tools or credentials: Learning Harvest is instructions for the agent only.
Does Learning Harvest 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 Learning Harvest 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. Review the folder before installing.
What licence does Learning Harvest use?
Learning Harvest 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 Learning Harvest use?
About 2.4k tokens (SKILL.md is roughly 9.8k 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 Learning Harvest?
Skills that share tags, products or a category with Learning Harvest: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Learning Harvest?
techygarg (a GitHub user) maintains it in techygarg/lattice, which has 199 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 6, 2026.
Source: techygarg/lattice on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.