Skip to content

angushushu/shu-academic-writing-skill / core/engineer-argument

engineer-argument

Verified

Diagnose why a draft will not land with its readers, using Larry McEnerney's framework — value over clarity, reader-driven prose, instability and cost, community codes. Use when someone shares a paper, abstract, introduction, dissertation chapter, literature review, grant or research proposal, or conference submission and wants feedback, review, critique, or "does this work?" — and when they ask why their writing gets rejected, desk-rejected, ignored, or called boring or unconvincing, how to make an argument compelling, whether their contribution is significant enough, or how to write a stronger intro or abstract. This is the top-down structural review: value, problem, movement, code, and the sentence patterns that follow. For a pure line-level pass on prose whose argument is already settled, read `core/polish-prose/SKILL.md` instead. Default behavior is diagnosis and coaching, never rewriting.

FileKindSize
SKILL.mdskill md12.8 KB
references/argument-patterns.mdmarkdown4.2 KB
references/diagnostics.mdmarkdown10.6 KB
references/drills.mdmarkdown6.1 KB
references/genres.mdmarkdown9.2 KB
references/principles.mdmarkdown16.2 KB
references/sentence-patterns.mdmarkdown5.1 KB

references/sentence-patterns.md

View on GitHub
# Sentence Patterns (condensed, for the last section of a review)

This is the short list. A structural review earns a *small* sentence section — three patterns
at most — because the author cannot act on fifteen findings at once, and because sentence work
is the most comfortable way to avoid a value problem. If the author's argument is already
settled and they want a real line-level pass, the `core/polish-prose` module goes ten patterns
deep with mechanisms, signatures, and drills. Hand off rather than doing a thin version here.

**How to report each one:** quote 2–3 instances → give the mechanism (what a reader must do at
that point) → illustrate the move on neutral content from another field → assign the search.
Never repair their sentences. The mechanism is the part that transfers; a rule without it
produces an author who fixes the quoted instances and reproduces the pattern everywhere else.

Order below is by cost. The first two govern whether a reader can build a mental model at all;
the rest are cheaper problems that happen to be more visible.

---

## 1. Characters as subjects, actions as verbs

Readers understand a sentence fastest when its grammatical subject is the story's main
character and its verb is that character's action.

**Mechanism:** readers build a model of who-does-what. When the action sits inside an abstract
noun and the subject is a concept, they must reconstruct the actors before they can evaluate
the claim — attention a skimming expert will not spend.

**Signature:** clusters of *-tion, -ment, -ance, -ence, -ity, -ness* nouns carried by weak
verbs (*is, are, has, provides, results in, leads to, plays a role in*).

> Weak: "The determination of soil composition variability was performed through the
> application of a sampling procedure by the research team."
> Strong: "The research team sampled the soil and found the composition varied."

Some nominalizations are correct — technical terms, or a concept that genuinely is the topic
("selection pressure"). It's the clusters that hurt.

## 2. Old before new

Begin sentences with information already in the reader's head; end with what's new.

**Mechanism:** readers attach incoming information to something they already hold. A sentence
opening with unfamiliar material gives them nothing to attach to, so they hold it in suspense
until the connection arrives — or give up.

**Signature:** consecutive sentences beginning with different, unconnected subjects; a
paragraph you have to reread backwards to understand.

> Choppy: "Ocean acidification threatens shell formation. Larval mortality in oyster hatcheries
> rose sharply after 2007. Aragonite saturation is the mechanism."
> Connected: "Ocean acidification threatens shell formation. That threat became visible in
> 2007, when larval mortality in oyster hatcheries rose sharply. The mechanism is aragonite
> saturation."

Nothing was added — the known material simply moved to the front of each sentence.

## 3. The stress position

The end of a sentence is where emphasis lands. Put there the idea you want carried forward.

**Signature:** sentences ending in "(Smith 2019)", "in this context," "as discussed above,"
"to some extent." The most interesting word sitting in the middle.

> Wasted: "Enrollment fell by 40% after the policy change, according to district records
> compiled in the appendix."
> Used: "According to district records, enrollment fell 40% after the policy change."

## 4. Short subject, early verb

**Mechanism:** English readers can't evaluate a subject until the verb tells them the
relationship. A 25-word subject is 25 words of suspended judgment.

**Signature:** the first comma arriving 15+ words in; openings like "The question of whether…",
"The extent to which…"; stacked prepositional phrases before the verb.

## 5. Throat-clearing

Openers that announce rather than assert: *It is important to note that, It should be
emphasized that, There are several factors which.* They consume the sentence's opening — the
highest-attention position — with no content.

Signposting that helps a reader navigate a long document earns its space. What to flag is
metadiscourse that *substitutes* for the claim.

## 6. Hedge stacking

Individually defensible hedges that together announce no claim is being made: "may possibly
suggest that there could be a tendency toward." Field-dependence is real — some venues require
heavy modality — but the stack is never idiomatic anywhere.

## 7. Passive voice, fairly

Passive is a tool, not an error, and blanket "avoid the passive" advice marks a reviewer who
isn't reading. It's **right** when the recipient is the paragraph's topic, the agent is
irrelevant, or you need the agent in the stress position. It's **wrong** when it hides an agent
the reader needs — especially a person making a choice. "It was decided that three sites would
be excluded" hides who decided and why, which is exactly what a skeptical reader wants.

## 8. Rhythm

Uniform sentence length flattens emphasis. Readers register a short sentence after several long
ones as a point of arrival — it's how a claim lands. If the paper's central claim runs 45 words
across three subordinate clauses, it isn't landing.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall