oh-my-agent-commandcode 0.0.0-stage → 20.38.3

package/skills/oma-academic-writing/SKILL.md

@@ -0,0 +1,181 @@
+---
+name: oma-academic-writing
+description: Draft and revise academic prose against a rubric, evidence, and
+  citation requirements. Use for essays, reports, literature reviews, or
+  academic style audits.
+---
+
+# Academic Writing: Publication-Grade English Prose
+
+## Scheduling
+
+### Goal
+Produce, revise, and audit publication-grade academic English prose so that every output simultaneously satisfies the Sentence Structure Protocol, Verb Protocol, Hedging Protocol, and Anti-AI Compliance Checklist, with every claim mapped to verifiable evidence.
+
+### Intent signature
+- "draft this abstract / essay / report / executive summary / conclusion / literature review"
+- "rewrite this paragraph in academic English"
+- "polish this draft to top-band quality" / "revise to match the rubric"
+- "run an anti-AI audit on this prose"
+- "check sentence structure variety" / "fix monotonous rhythm"
+- "the prose sounds AI-generated, make it pass"
+- "verify claims against evidence" / "reverse outline this section"
+
+### When to use
+- Drafting or revising academic reports, essays, or analysis sections
+- Writing research abstracts, executive summaries, conclusions, or literature reviews
+- Rewriting AI-sounding prose into natural academic English
+- Polishing draft text to achieve top-band rubric quality (HD, A, top-band, etc.)
+- Reviewing prose for sentence variety, verb quality, hedging, and anti-AI compliance
+- Any task requiring formal academic English output bound by a rubric
+
+### When NOT to use
+- Translation tasks → use `oma-translation`
+- Source discovery, citation gathering, or scholarly literature search → use `oma-scholar`
+- Rubric / assignment-spec parsing and task decomposition → use `oma-pm`
+- Code documentation, README, or API reference text → use the relevant domain skill (`oma-frontend`, `oma-backend`, `oma-mobile`, `oma-db`, etc.)
+- Informal communication, chat, or marketing copy → no skill needed
+- Non-English academic writing → call `oma-translation` for the target language after drafting in English
+
+### Expected inputs
+- `mode`: one of `draft` | `revise` | `review`
+- Optional `rubric_or_constraint`: assignment brief, rubric file, or word/structure limits (path or inline text); draft-only revision/review does not require a rubric
+- `existing_draft`: prior text to revise or audit (path or inline text); required for `revise` and `review`
+- `source_data`: available evidence, figures, citations the writer may use
+- `target_register`: defaults to formal academic English with American spelling (en-US)
+
+### Expected outputs
+- `draft` mode: section heading + drafted prose + Writing Notes (sentence mix, key verbs, anti-AI flags resolved, paragraph lengths) + Claim-Evidence Map
+- `revise` mode: original block, revised block, list of specific changes (verb upgrades, structure variation, anti-AI fixes)
+- `review` mode: PASS/FAIL Compliance Report across Sentence Structure, Verb Quality, Anti-AI, Specificity, Hedging, Paragraph Clarity, Rhythm/Burstiness, Claim-Evidence Alignment, plus recommended fixes
+
+### Dependencies
+- `../_shared/core/anti-ai-prose.md` and `resources/anti-ai-checklist.md`: common diagnostics and academic constraints; load together for prose audits
+- `resources/sentence-structure-reference.md`: four sentence types, contextual rhythm guidance, common errors
+- `resources/academic-verb-tiers.md`: meaning- and evidence-based verb guidance
+- `resources/hedging-guide.md`: calibrated certainty expressions matched to evidence strength
+- `../_shared/core/context-loading.md`: task-relevant resource loading
+- `../_shared/core/quality-principles.md`: shared quality bar
+
+### Control-flow features
+- Mode branching: `draft` vs `revise` vs `review` produce different output formats and pass sequences
+- Rubric constraints: quote supplied assignment requirements before applying them; draft-only revision/review can proceed without inventing a rubric
+- Citation gap branch: when a claim lacks evidence, weaken or remove rather than fabricate; optionally hand off to `oma-scholar`
+- Language branch: non-English target hands off to `oma-translation` after the English pass
+- Iterative AUDIT: every fix loops back through the anti-AI checklist before emit
+
+## Structural Flow
+
+### Entry
+1. Identify the mode (`draft`, `revise`, `review`) and the rubric source.
+2. If assignment constraints were supplied, quote their exact text before applying them. Without a rubric, revise/review the draft using the requested register and evidence; do not invent assignment rules.
+3. If revising or reviewing, read the existing draft in full first; if drafting, confirm available source data and citations.
+4. Index `resources/` and identify any claims that need a more precise verb or hedge.
+5. Apply the literal-first principle before any drafting: prefer direct statement over metaphor and flourish. When a literal phrase is available, use it.
+
+### Scenes
+1. **PREPARE**: load rubric, existing draft, source data; record quoted constraints and note claims whose verbs or hedges need attention.
+2. **ACQUIRE**: read `resources/sentence-structure-reference.md`, `academic-verb-tiers.md`, and `hedging-guide.md` only for the patterns relevant to the current section.
+3. **ACT**: write or revise prose with sentence variety, accurate verb choice, evidence-matched hedging, clear paragraphing, and direct statements. Keep a common verb when it is the clearest accurate choice.
+4. **VERIFY**: apply the shared prose diagnostics and academic checklist; use reverse outlining and the Claim-Evidence Map to identify unsupported claims. In review mode, report findings without rewriting the draft.
+5. **FINALIZE**: read-aloud test, cohesion check, specificity audit, word-count verification, paragraph-length variation, rhythm check; emit per the mode's output format.
+
+### Transitions
+- If a rubric line is ambiguous → quote it back to the user and ask for interpretation; do not infer combined rules.
+- If a claim cannot be supported by available evidence → weaken with hedging or remove; if a citation gap is structural, NOTIFY `oma-scholar`.
+- If the target language is non-English → finish the English pass, then hand off to `oma-translation`.
+- If the same anti-AI flag survives one fix attempt → restructure the surrounding two sentences instead of word-substitution alone.
+- If an output mode mismatch is detected (e.g., user asked for review but supplied a fresh prompt) → confirm the mode before producing output.
+
+### Failure and recovery
+| Failure | Recovery |
+|---------|----------|
+| Word count over / under target | Cut filler adverbs and redundant qualifiers, or expand with supporting evidence; re-run audit |
+| Repeated syntax obscures the argument | Revise the affected sentences for clarity using shared rhythm guidance; preserve clear sentences |
+| Rubric requirement unclear | Quote exact rubric text and ask user; do not combine rules |
+| Claim lacks evidence | Add citation, hedge to match weaker evidence, or remove the claim entirely |
+| Hedging miscalibrated | Replace double hedges; align hedge strength with `resources/hedging-guide.md` evidence-level table |
+| Verb is vague | Name the action, method, result, or evidence only if that makes the claim clearer |
+| Repeated paragraph structure hinders progression | Reorganize the affected argument without inserting a paragraph solely to vary length |
+
+### Exit
+- Success: every protocol PASSes, the Claim-Evidence Map has no unsupported entries, word count complies, and the mode-specific output format is fully populated.
+- Partial success: emit prose with explicit `needs evidence` / `pending citation` markers and report which protocol items remain at risk; flag handoff candidates.
+- Failure: report a material blocker such as required source data being unavailable or contradictory supplied constraints. The absence of an optional rubric alone does not block draft-only revision/review.
+
+## Logical Operations
+
+### Actions
+| Action | SSL primitive | Evidence |
+|--------|---------------|----------|
+| Read rubric / constraint and quote literal text | `READ` | Rubric file or assignment brief |
+| Read existing draft (revise/review modes) | `READ` | Draft file or inline text |
+| Index resources for the current section | `READ` | `resources/{anti-ai-checklist,sentence-structure-reference,academic-verb-tiers,hedging-guide}.md` |
+| Select sentence mix and evidence-appropriate wording | `SELECT` | Sentence-structure and verb guidance |
+| Plan paragraph as Topic-Support-Conclude | `INFER` | Outline notes |
+| Draft / revise prose under all four protocols | `WRITE` | Generated prose |
+| Audit prose against anti-AI checklist | `VALIDATE` | `resources/anti-ai-checklist.md` |
+| Reverse outline + build Claim-Evidence Map | `VALIDATE` | Mapping table |
+| Weaken or remove unsupported claims | `WRITE` | Revised claim line |
+| Compare original vs revised (revise mode) | `COMPARE` | Diff block |
+| Hand off non-English target | `NOTIFY` | `oma-translation` |
+| Hand off citation gap | `NOTIFY` | `oma-scholar` |
+| Hand off ambiguous rubric / spec | `NOTIFY` | `oma-pm` |
+| Emit per mode output format | `WRITE` | Final artifact |
+| Report compliance status | `NOTIFY` | PASS/FAIL summary or Writing Notes block |
+
+### Tools and instruments
+- `Read` / `Edit` / `Write` for draft and rubric files
+- `resources/anti-ai-checklist.md`, `sentence-structure-reference.md`, `academic-verb-tiers.md`, `hedging-guide.md`
+- Topic-Support-Conclude paragraph template (inline)
+- Claim-Evidence Map (inline 3-column table: Claim / Evidence / Status)
+- Output-format blocks per mode (Draft / Revision / Review)
+
+### Canonical workflow path
+1. **READ** the draft and any supplied rubric; quote actual assignment constraints and pin their requirements. If no rubric is supplied, use the requested revision/review scope without inventing constraints.
+2. **PLAN** each paragraph as Topic-Support-Conclude; identify where evidence strength or a vague claim calls for a more precise verb. For research abstracts, use `resources/abstract-guide.md` to select motivation, approach, measured results, and a supported contribution within the venue's format.
+3. **DRAFT** prose with sentence variety, clear verb choice, hedging, and Topic-Support-Conclude structure.
+4. **AUDIT** with `../_shared/core/anti-ai-prose.md` and `resources/anti-ai-checklist.md`. Fix supported defects in draft/revise mode; in review mode, quote the passage, identify the defect, and recommend a local fix without a full rewrite or AI-authorship estimate.
+5. **REVERSE-OUTLINE** the section and build the Claim-Evidence Map; weaken or remove any unsupported claim.
+6. **POLISH** with read-aloud, cohesion, specificity, word-count, rhythm, and paragraph-length-variation checks; emit in the mode's output format.
+
+### Resource scope
+| Scope | Resource target |
+|-------|-----------------|
+| `LOCAL_FS` | Rubric, existing draft, generated prose output |
+| `CODEBASE` | Task-relevant `resources/` files, `_shared/core/{context-loading,quality-principles}.md` |
+| `MEMORY` | Mode, quoted constraints, wording decisions, anti-AI flags resolved, Claim-Evidence Map |
+
+### Preconditions
+- A rubric / constraint or an existing draft (or both) is provided.
+- The target register is academic English. If the final deliverable is non-English, the user has agreed to a downstream `oma-translation` handoff.
+- The source data needed to support claims is available, or unsupported claims are explicitly allowed to be weakened or removed.
+
+### Effects and side effects
+- Writes drafted, revised, or reviewed prose to the user's working location (file or inline).
+- Does not modify `resources/` reference files.
+- Does not fetch external citations; defers to `oma-scholar` when discovery is required.
+- May NOTIFY adjacent skills but does not auto-spawn them; user or workflow drives the actual handoff.
+
+### Guardrails
+1. Every sentence must be verifiable; never fabricate data, statistics, or citations.
+2. Quote supplied rubric constraints before judging compliance. Without a rubric, explain prose/evidence findings against the requested scope rather than inventing assignment criteria.
+3. Never combine distinct rules to invent a new constraint; apply rules exactly as written.
+4. Choose verbs for their exact meaning and support. Keep common verbs when they are accurate and natural; replace a vague verb only when the new wording states a relevant distinction without inflating the claim.
+5. Review repeated structure and sentence length in context. Change rhythm where it improves clarity or emphasis; do not force sentence-type quotas or rewrite clear prose merely to vary it.
+6. Match hedge strength to evidence strength per `hedging-guide.md`; never use absolute claim words (`definitely`, `clearly`, `obviously`) outside mathematical facts; never first-person `I think` / `I believe`.
+7. Apply common prose diagnostics with the academic checklist's evidence and register exceptions. Vocabulary counts trigger contextual review, not automatic replacement of precise terms.
+8. Em dashes ≤ 1 per paragraph; semicolons ≤ 2 per 1000 words; sentence-case headers; no didactic disclaimers (`It is important to note`) or summary phrases (`In summary`, `Overall`).
+9. Every claim must map to evidence in the Claim-Evidence Map; weaken or remove unsupported claims rather than emit them.
+10. Read aloud before emit; if a sentence does not flow naturally, restructure it.
+11. Apply the shared mannered-prose guidance with the academic checklist's literal-statement requirement.
+
+## References
+- Research abstract guidance: `resources/abstract-guide.md` (load when drafting, revising, or reviewing an abstract)
+- Common prose diagnostics: `../_shared/core/anti-ai-prose.md` (load with the academic checklist for prose audits)
+- Academic audit constraints: `resources/anti-ai-checklist.md`
+- Sentence-structure reference: `resources/sentence-structure-reference.md`
+- Academic verb tiers: `resources/academic-verb-tiers.md`
+- Hedging guide: `resources/hedging-guide.md`
+- Shared context loading: `../_shared/core/context-loading.md`
+- Shared quality principles: `../_shared/core/quality-principles.md`

package/skills/oma-academic-writing/resources/abstract-guide.md

@@ -0,0 +1,51 @@
+# Research abstracts
+
+Use for drafting, revising, or reviewing a research abstract. Follow the supplied
+venue requirements, structured headings, and word limit before these defaults.
+
+## Content selection
+
+- Open with the concrete research problem and why it matters to the intended
+  reader. Name the affected activity or decision. General claims that a topic is
+  growing or important do not establish motivation. Strengthen an existing
+  motivation when needed rather than declaring it absent without checking.
+- Explain the approach and the mechanism needed to understand its contribution.
+  Select the relevant mechanism rather than listing every feature.
+- Include the most informative measured results available. Prefer outcomes that
+  answer the research question over counts of tests or implementation components.
+  For a tool demonstration, regression counts and observed protocol behavior may
+  support implementation validation; they do not establish user benefit or
+  effectiveness on real workloads.
+- State what each number measures, with its unit, denominator, comparison, and
+  experimental setting where needed to interpret it. Use only reported evidence.
+  Do not invent percentages, combine overlapping test counts, or imply that more
+  tests establish stronger real-world effectiveness. If quantitative results are
+  unavailable or inappropriate, report the supported qualitative contribution.
+- End with the contribution supported by those results. Follow venue instructions
+  for availability or demonstration links. Avoid generic claims of significance.
+
+## Framing and scope
+
+- Describe what the method does and what the evaluation found. Remove repeated
+  defensive statements and lists of capabilities that were not evaluated.
+  Preserve negative or null findings when they are substantive results, and use
+  negative wording when it states the problem accurately.
+- Keep detailed limitations and future work in the body by default. Retain a
+  limitation in the abstract when the venue requires it or its omission would
+  materially mislead the reader. Do not apply a blanket ban on limitations.
+- Keep essential scope next to the result: for example, a scripted fixture, a
+  simulation, a fixed callback, or a small observational sample. Removing a
+  disclaimer must not turn local validation into a claim about autonomous
+  operation, causality, productivity, or general effectiveness.
+- State comparative outcomes fairly, including parity when relevant. A blocked
+  task is not a successful repair; a planning result is not an executed outcome;
+  fewer executed checks alone do not establish lower total cost.
+
+## Revision evidence
+
+For each proposed change, identify the original passage, the specific issue, and
+the evidence supporting the replacement. Trace every abstract result to the body
+and retained data using the skill's Claim-Evidence Map. Distinguish required fixes
+from stylistic preferences; reviewer feedback is not a universal venue rule.
+When updating a submission, keep the manuscript and portal abstracts consistent
+within the user's authorized scope and verify the final word count.

package/skills/oma-academic-writing/resources/academic-verb-tiers.md

@@ -0,0 +1,42 @@
+# Academic verb guidance
+
+Choose a verb for its meaning, evidence strength, and the conventions of the field. Plain verbs
+are often the best choice. Do not replace a natural verb merely to sound academic.
+
+## Use precise verbs when precision helps
+
+| Purpose | Useful verbs | Use with care |
+|---|---|---|
+| Report evidence | show, indicate, demonstrate, illustrate, report | `demonstrate` can overstate weak evidence |
+| Describe methods | use, apply, employ, conduct, measure | name the method when it matters |
+| State findings | find, observe, identify, estimate, compare | distinguish an observation from a causal claim |
+| Make an argument | argue, propose, suggest, contend | match the verb to the support provided |
+| Explain a result | explain, account for, relate to, affect | avoid implying causation without evidence |
+| Define scope | include, focus on, examine, address | say what is included or excluded |
+| Describe change | increase, reduce, develop, vary, remain | quantify the change when data permits |
+
+## Editing decisions
+
+Keep `show`, `use`, `find`, `help`, `have`, and similar common verbs when they are accurate,
+clear, and fit the register. Revise only when the verb hides a needed distinction. For example:
+
+- `The table shows the distribution` is clear when the table directly displays it.
+- `The experiment used a control group` is clear when method detail is sufficient.
+- `The analysis found a difference` should become `estimated`, `identified`, or `observed` only
+  when that word states how the result was obtained or how certain it is.
+- `The intervention helped participants` should name the measured outcome if the evidence supports
+  a more specific claim.
+
+Avoid inflated substitutions such as `utilize` for `use` or `serves as` for `is`. Prefer a direct
+verb unless a more specific one improves the claim.
+
+## Evidence and certainty
+
+| Evidence | Suitable wording |
+|---|---|
+| Direct, well-supported result | `shows`, `demonstrates`, `is associated with` |
+| Observational or mixed evidence | `indicates`, `suggests`, `is consistent with` |
+| Proposal or interpretation | `may explain`, `could reflect`, `hypothesizes` |
+
+Read `hedging-guide.md` when certainty is material. This guide offers choices; it does not set a
+required vocabulary or a frequency target.

package/skills/oma-academic-writing/resources/anti-ai-checklist.md

@@ -0,0 +1,52 @@
+# Academic prose audit
+
+Read `../../_shared/core/anti-ai-prose.md` with this resource. It owns common
+patterns and the evidence-based editing/review contract. This file adds academic
+constraints; the rubric and required publication format take precedence.
+
+## Evidence and register
+
+- Map each major claim to its source in the Claim-Evidence Map. Weaken, remove, or
+  flag unsupported claims; never invent citations or numbers to satisfy specificity.
+- Preserve technical terms, definitions, operational details, and evidence-matched
+  hedging. Apply `hedging-guide.md` when certainty is material.
+- Prefer literal statements. Retain a metaphor only when it adds precision that a
+  literal formulation cannot provide and its connotations are controlled.
+- Keep a required abstract, conclusion, research question, or synthesis. Shared
+  ending and rhetorical-setup diagnostics remove empty rhetoric, not these academic functions.
+- Review mode reports concrete passages and fixes, without a full rewrite or an
+  AI-authorship estimate. Use the skill's academic compliance report.
+
+## Vocabulary clustering
+
+Flag three or more potentially inflated terms in one paragraph for contextual
+review. Examples include `Additionally`, `Furthermore`, `Moreover`, `crucial`,
+`delve`, `leverage`, `foster`, `intricate`, `multifaceted`, `pivotal`,
+`robust`, `seamless`, `showcase`, `tapestry`, `underscore`, and `groundbreaking`.
+Replace empty emphasis with plain wording. Retain accurate disciplinary terms;
+frequency alone neither establishes a defect nor identifies the author.
+
+## Formatting
+
+- Use sentence-case headings except for proper nouns or a required publication style.
+- Limit em dashes to one per paragraph and semicolons to two per 1000 words.
+- Prefer grammatical connections to decorative punctuation.
+- Under the default academic style, reserve colons for formal definitions, block
+  quotations, ratios, and times; express inline lists and explanations in prose.
+- Use tables for quantitative comparisons or reference data, not short prose.
+- Apply shared formatting and chatbot-artifact diagnostics.
+
+## Rhythm and sentence structure
+
+Use `sentence-structure-reference.md` for academic sentence types and opener guidance.
+Check five or more consecutive sentences in a narrow length range and four or more
+paragraphs of similar length for monotonous structure. Revise when the repetition
+hinders the argument; a count alone does not establish AI authorship.
+Preserve clear sentences and required paragraph structure. Do not insert a token
+short sentence or emphasis paragraph merely to satisfy a rhythm check.
+
+## Audit result
+
+Record supported findings against the shared patterns, then check academic evidence,
+register, punctuation, sentence structure, and word limits. Distinguish an unsupported
+claim from an optional stylistic preference. Mark pending citations explicitly.

package/skills/oma-academic-writing/resources/hedging-guide.md

@@ -0,0 +1,132 @@
+# Hedging guide for academic English
+
+Academic writing requires calibrated certainty: neither overclaiming nor excessive caution.
+
+## Evidence-to-hedge mapping
+
+| Evidence Strength | Description | Hedge Level | Example Constructions |
+|-------------------|-------------|-------------|----------------------|
+| Definitive | Mathematical proof, logical necessity, definitional truth | None | "X **is** Y", "The data **confirm** that..." |
+| Strong | Large-N replicated studies, meta-analyses, established consensus | Minimal | "The data **demonstrate** that...", "The evidence **establishes** that..." |
+| Moderate | Single well-designed study, consistent preliminary findings | Moderate | "The findings **suggest** that...", "The results **indicate** that..." |
+| Exploratory | Pilot study, limited sample, emerging trends | Strong | "This **may indicate** that...", "Preliminary evidence **points toward**..." |
+| Interpretive | Author's own analysis without external validation | Attribution | "This pattern **appears to** reflect...", "One possible interpretation is that..." |
+| Speculative | No direct evidence; inference from adjacent domains | Maximal | "It is **conceivable** that...", "**If** this trend continues, X **could** occur." |
+
+## Hedging devices
+
+### Modal verbs (ordered by certainty)
+
+| Certainty Level | Modals |
+|----------------|--------|
+| High | will, must, is (certain to) |
+| Moderate | would, should, is likely to |
+| Low | may, might, could, can |
+| Speculative | would potentially, might conceivably |
+
+### Hedging verbs
+
+| Certainty Level | Verbs |
+|----------------|-------|
+| High | demonstrate, confirm, establish, verify, prove |
+| Moderate | suggest, indicate, imply, point to, appear |
+| Low | hint at, raise the possibility, appear to, tend to |
+
+### Hedging adverbs
+
+| Certainty Level | Adverbs |
+|----------------|---------|
+| High | clearly, definitively, conclusively, unequivocally (rule 7: mathematical or logical certainties only) |
+| Moderate | generally, typically, largely, predominantly |
+| Low | possibly, potentially, perhaps, arguably, presumably |
+| Speculative | conceivably, hypothetically, tentatively |
+
+### Hedging nouns
+
+possibility, tendency, likelihood, indication, suggestion, assumption, interpretation, speculation
+
+### Hedging prepositional phrases
+
+according to, on the basis of, in light of, given the limitations of, with reference to, from the perspective of
+
+## Rules
+
+### 1. Match hedge to evidence
+
+Every claim in academic writing must carry the appropriate degree of certainty.
+
+**Strong evidence → assertive language:**
+> "The regression analysis **demonstrates** a statistically significant correlation (p < .001) between match duration and surface type."
+
+**Moderate evidence → moderate hedge:**
+> "The findings **suggest** that match duration **tends to** increase on clay surfaces."
+
+**Limited evidence → strong hedge:**
+> "Preliminary data **may indicate** a relationship between surface type and match duration, although further investigation is warranted."
+
+### 2. Never over-hedge strong evidence
+
+If the data clearly support a claim, do not weaken it with unnecessary hedges.
+
+- Bad: "The data **might possibly seem to** suggest that the correlation **could potentially** exist."
+- Good: "The data **demonstrate** a strong correlation."
+
+### 3. Never under-hedge weak evidence
+
+If the evidence is limited, do not present claims as established fact.
+
+- Bad: "Surface type **determines** match duration." (stated as fact from limited data)
+- Good: "Surface type **appears to** influence match duration."
+
+### 4. Avoid double hedging
+
+Using two hedge devices where one suffices weakens the claim unnecessarily.
+
+- Bad: "It **might possibly** be the case that..."
+- Good: "It **may** be the case that..."
+
+- Bad: "The results **seem to suggest** that..."
+- Good: "The results **suggest** that..." or "The results **appear to** support..."
+
+Note: choose `seem` or `appear` by meaning and register. Prefer neither automatically; hedge only to the extent supported by the evidence.
+
+### 5. Use attribution hedging for interpretive claims
+
+When offering your own analysis (not reporting others' findings), attribute the interpretation explicitly.
+
+- "This pattern **appears to** reflect a shift in playing strategy."
+- "One interpretation of this trend is that..."
+- "Based on this analysis, it is **reasonable to infer** that..."
+
+### 6. Avoid "I think" / "I believe"
+
+These are too informal for academic writing. Replace with:
+
+| Informal | Academic |
+|----------|----------|
+| I think | This analysis suggests |
+| I believe | The evidence indicates |
+| In my opinion | Based on the available data |
+| I feel | It appears that |
+
+### 7. Never use "clearly/obviously/definitely" unless justified
+
+These intensifiers are appropriate only for:
+
+- Mathematical certainties: "The mean is **clearly** higher than the median."
+- Logical necessities: "If A > B and B > C, then A is **definitively** greater than C."
+- Universally accepted facts: appropriate in very limited contexts
+
+For all other claims, remove the intensifier and let the evidence speak.
+
+## Quick reference: hedge calibration checklist
+
+Before submitting any academic text:
+
+- [ ] Does every claim carry appropriate hedging for its evidence base?
+- [ ] No double-hedging found?
+- [ ] No "clearly/obviously" used without mathematical or logical justification?
+- [ ] No "I think/believe" constructions?
+- [ ] Interpretive claims attributed with "appears to", "one interpretation", etc.?
+- [ ] Strong evidence not weakened by unnecessary hedges?
+- [ ] Weak evidence not presented as established fact?

package/skills/oma-academic-writing/resources/sentence-structure-reference.md

@@ -0,0 +1,151 @@
+# Sentence structure reference for academic English
+
+## Four sentence types
+
+### 1. Simple sentence
+
+One independent clause in a subject-verb pattern.
+
+**Use for:** High-impact statements, clear assertions, topic sentences.
+
+**Examples:**
+
+- The Australian government introduced an official carbon tax on 1 July 2012.
+- This dataset contains 120 years of match records.
+- Performance declined sharply after the 2018 rule changes.
+
+**Guidance:** Use when a direct assertion is clearest; no paragraph quota.
+
+### 2. Compound sentence
+
+Two independent clauses connected by a coordinating conjunction (FANBOYS: for, and, nor, but, or, yet, so).
+
+**Use for:** Balanced comparisons, contrasts, cause-effect pairs.
+
+**Examples:**
+
+- The Australian government introduced an official carbon tax on 1 July 2012, but this was met with opposition from the general public.
+- Match duration increased by 15%, and spectator attendance declined in parallel.
+- Nadal dominated the clay court, yet Djokovic maintained superiority on hard surfaces.
+
+**Guidance:** Use when the relationship between clauses matters; no paragraph quota.
+
+### 3. Complex sentence
+
+One independent clause + one dependent clause (introduced by a subordinating conjunction: as, because, although, when, while, if, since, after, before, unless, until, whereas).
+
+**Use for:** Causal reasoning, conditional statements, temporal ordering (the backbone of academic analysis).
+
+**Examples:**
+
+- As the Australian government recognized the necessity to significantly reduce greenhouse gas emissions, it introduced an official carbon tax on 1 July 2012.
+- Although the dataset spans 121 seasons, only matches after 1968 include detailed set-level data.
+- Because five-set matches impose greater physical demands, average rally length decreases in the fourth and fifth sets.
+
+**Guidance:** Use to state an actual causal, conditional, or temporal relationship; no paragraph quota.
+
+### 4. Compound-complex sentence
+
+Two or more independent clauses + one or more dependent clauses.
+
+**Use for:** Sophisticated synthesis, multi-factor analysis, nuanced arguments.
+
+**Examples:**
+
+- As the Australian government recognized the necessity to significantly reduce greenhouse gas emissions, it introduced an official carbon tax on 1 July 2012, but this was met with opposition from the general public.
+- While set durations vary considerably between Grand Slam events, the median match length has increased by 12 minutes since 2000, and this trend correlates with advances in racket technology.
+- Because the 1905–1968 era lacked professional circuits, participation remained limited to amateur players; however, match records from this period still provide valuable longitudinal data.
+
+**Guidance:** Use only when combining the clauses makes the argument clearer; no paragraph quota.
+
+## Variation rules
+
+### Within a paragraph
+
+1. Review repeated structures where they obscure emphasis or progression.
+2. Let sentence length follow the argument; split overloaded sentences and preserve useful short assertions.
+3. Do not require a fixed mix of sentence types in each paragraph.
+4. Vary paragraph length where it improves the argument; uniform blocks alone do not identify AI authorship.
+
+> For rhythm review and punctuation limits, see `anti-ai-checklist.md`, sections "Rhythm and sentence structure" and "Formatting".
+
+### Sentence openers (vary these)
+
+| Opener Type | Example |
+|-------------|---------|
+| Subject-first | "The analysis reveals..." |
+| Adverbial phrase | "Between 2015 and 2020, match duration..." |
+| Prepositional phrase | "In the context of Grand Slam competition, ..." |
+| Participial phrase | "Drawing on longitudinal data, this study..." |
+| Dependent clause | "Although the sample size was limited, the trend..." |
+| Transitional phrase | "By contrast, the women's draw exhibited..." |
+| Inverted structure | "Particularly notable is the decline in..." |
+
+**Diagnostic:** Review repeated openers for clarity and emphasis; keep deliberate repetition when it serves the argument.
+
+## Common errors to prevent
+
+### Sentence fragments
+
+A sentence missing subject, verb, or complete thought.
+
+| Error Type | Bad | Fixed |
+|-----------|-----|-------|
+| Missing subject | "Becoming extinct because of rising sea temperatures." | "Phytoplankton may face extinction because of rising sea temperatures." |
+| Missing verb | "Significantly, one particular form of Western Australian finch." | "Significantly, one particular form of Western Australian finch has decreased in numbers." |
+| Incomplete thought | "In a recent article about loss of habitat due to climate change." | "In a recent article about loss of habitat due to climate change, Australian animals were identified as particularly vulnerable." |
+
+**Watch out for:** Sentences beginning with so, as, because, who, which, that, since these are often incomplete.
+
+### Run-on sentences
+
+Two independent clauses joined without proper punctuation or conjunction.
+
+| Bad | Fixed (conjunction) | Fixed (separate) |
+|-----|-------|---------|
+| "Poverty and famine are indicators of climate change these issues are not being addressed." | "Poverty and famine are indicators of climate change, **but** these issues are not being addressed." | "Poverty and famine are indicators of climate change. These issues are not being addressed." |
+
+### Lack of clear meaning
+
+Every sentence must be fully understandable when read in isolation. If a sentence requires mental gymnastics to parse, rewrite it more simply.
+
+## Paragraph cohesion model
+
+```
+[Topic Sentence — main point, often complex or compound-complex]
+[Supporting Sentence 1 — evidence, often simple or complex]
+[Supporting Sentence 2 — analysis, often complex]
+[Supporting Sentence 3 — additional evidence or counter-argument, often compound]
+[Concluding Sentence — link to broader argument or transition, often compound-complex]
+```
+
+### Bad example (monotonous structure)
+
+> Nursing education states that measures should be in place to avoid infection. Also, that infection rates tend to soar when hygiene standards decrease. Appropriate steps should be taken to decrease these risks. It is suggested that medical staff are educated to understand these risks.
+
+**Problems:** Same structure (simple/simple), same opener pattern ("X states", "Also, that"), same sentence length, no cohesion between sentences.
+
+### Good example (varied structure)
+
+> Nursing educators argue that strict measures should be implemented to avoid infection in medical institutions. Considerable evidence links falling hygiene standards to sharply rising infection rates. Because these risks escalate quickly once standards slip, institutions must adopt procedures that reduce them. To this end, hospitals should require all staff to maintain effective hygiene, and managers should audit compliance at regular intervals.
+
+**Improvements:** Varied openers (subject-first, dependent clause, transitional phrase), mixed simple/complex/compound structures, varied sentence lengths, logical flow from claim → evidence → argument → recommendation, accurate verbs, and no unnecessary inflated vocabulary.
+
+## Quick reference: conjunction inventory
+
+### Coordinating (FANBOYS): for compound sentences
+
+for, and, nor, but, or, yet, so
+
+### Subordinating: for complex sentences
+
+**Cause/reason:** because, since, as, given that, owing to the fact that
+**Contrast:** although, though, even though, whereas, while
+**Condition:** if, unless, provided that, on condition that
+**Time:** when, whenever, after, before, until, since, while, as soon as
+**Purpose:** so that, in order that
+**Result:** so ... that, such ... that
+
+### Transitional phrases (non-AI): for sentence openers
+
+By contrast, More specifically, In parallel, To this end, From a different perspective, On closer examination, Upon further analysis, In quantitative terms, At the aggregate level, Within this framework, Across all conditions