AGENT SKILL

editorial-review

Protocols for reviewing business consulting documents against briefs, style profiles, and quality standards. Covers five-layer review (brief compliance, structural logic, clarity, style, consistency), issue severity classification, and revision decision-making. Core skill for the Editor agent. Use when reviewing a draft for clarity, structure, and consistency.

License 许可
Apache-2.0
所属仓库
cwik-tech/octopus
最近更新
2026-10-27
Stars
★ 0
Forks
0

01 前言 Front Matter

name
editorial-review
description
Protocols for reviewing business consulting documents against briefs, style profiles, and quality standards. Covers five-layer review (brief compliance, structural logic, clarity, style, consistency), issue severity classification, and revision decision-making. Core skill for the Editor agent. Use when reviewing a draft for clarity, structure, and consistency.

02 资源文件 3

03 SKILL.md 正文

Editorial Review Skill

When to Use

On every document review. The Editor runs this skill as the structured protocol for evaluating a draft against the original brief, style profile, and style guide. Follow the layers in order — never skip to style checking before confirming the argument holds together.


Review Protocol

Layer 1 — Brief Compliance Check

This is the most important layer. A beautifully written document that doesn't do what the brief asked is a failure.

Checklist:

Check Question Severity if failed
Section coverage Does every section in the brief exist in the draft? BLOCKING — missing sections mean incomplete deliverable
Section depth Does each section match the depth specified in the brief? (Short / Medium / Long) WARNING — underdeveloped sections weaken but don't break
Data usage Does the draft use the data the brief pointed to? BLOCKING if key data is ignored, WARNING if supplementary data is missed
Data fabrication Is there data in the draft that wasn't in the brief or inputs? BLOCKING — fabricated data is never acceptable
Audience alignment Does the document speak at the right level for the reader? WARNING — fixable in revision
Purpose delivery Can the reader make the decision the brief intended? BLOCKING — this is the document's reason for existence
Variable population Are all template variables filled correctly? WARNING — easy fix but embarrassing if missed
Placeholder status Are there unresolved [TODO: ...] placeholders? BLOCKING — each one means incomplete content

How to execute:

  1. Open the brief and the draft side by side
  2. Walk through each section in the brief
  3. For each section, check: exists? correct depth? uses specified data? achieves stated purpose?
  4. Log every discrepancy with section reference, expected vs. actual, and severity

Layer 2 — Structural Logic Analysis

Read the document as an argument, not a collection of sections.

Test 1 — Claim-Evidence Chain:

For every major claim in the document, trace it to supporting evidence:

CLAIM: "The company should enter the enterprise segment"
  ↓ supported by?
EVIDENCE: "Mid-market growth has declined 15% QoQ for 3 quarters"
  ↓ connected by?
REASONING: "Market saturation in mid-market makes enterprise the logical expansion"
  ↓ which implies?
IMPLICATION: "Enterprise entry would diversify revenue and reduce concentration risk"

If any link in the chain is missing, flag it:

  • Missing evidence → BLOCKING: "Unsupported claim in [section]"
  • Missing reasoning → WARNING: "Logical leap in [section] — evidence exists but connection to claim is unstated"
  • Missing implication → SUGGESTION: "Add 'so what' after evidence in [section]"

Test 2 — Logical Flow:

Read the section headings in order. Do they tell a coherent story? Could you rearrange them without anyone noticing? If yes, the structure is weak.

Good flow: Situation → Problem → Analysis → Options → Recommendation → Next Steps (each section builds on the previous)

Bad flow: Background → Recommendation → Market Analysis → Financial Data → Team → Timeline (sections could be in any order)

Test 3 — Circular Reasoning Detection:

Watch for arguments that assume their own conclusion:

  • "We recommend Option A because it's the best option." (Why is it the best?)
  • "The strategy will succeed because the team is strong." (How does team strength guarantee strategy success?)
  • "Customers will adopt the product because it meets their needs." (How do you know it meets their needs?)

For each circular argument, flag as BLOCKING and identify what evidence would break the circle.

Test 4 — Internal Contradiction Detection:

Check for statements in one section that conflict with statements in another:

  • Section 2 says "the market is growing rapidly" → Section 4 says "market saturation is a concern"
  • Executive summary says "we recommend immediate action" → Body says "more data is needed before deciding"
  • Financial section says "ROI is projected at 3x" → Risk section says "financial returns are uncertain"

Contradictions are BLOCKING unless they represent genuine tension that's explicitly acknowledged.

Test 5 — Executive Summary Alignment:

Read only the executive summary. Then read only the body. Ask:

  • Does the summary accurately represent the body's conclusions?
  • Does the summary overstate the certainty of the body's findings?
  • Does the summary introduce claims not in the body?
  • Does the summary miss key findings from the body?

Misalignment is BLOCKING — the executive summary is often the only part senior readers see.

Layer 3 — Clarity and Concision Audit

Scan 1 — Corporate filler detection:

Read every sentence and ask: "Does this sentence add information, advance the argument, or clarify a point?" If not, flag it.

Common filler patterns:

  • The Impressive Nothing: "We take a holistic, integrated approach to driving cross-functional alignment." What does this actually mean? Flag and request a concrete replacement.
  • The Vague Quantifier: "Significant growth," "substantial improvement," "numerous stakeholders." If the number exists, use it. If it doesn't, say "the data is unavailable."
  • The Double-Say: Two paragraphs making the same point in different words. Flag the weaker one for deletion.
  • The Empty Introduction: "In this section, we will explore the key factors that..." Just state the factors.

Scan 2 — Sentence-level tightening:

Pattern Example Fix
Unnecessary qualifier "very significant" "significant" (or better: the actual number)
Wordy phrase "in order to" "to"
Wordy phrase "due to the fact that" "because"
Wordy phrase "at this point in time" "now"
Wordy phrase "in the event that" "if"
Hidden verb "make a decision" "decide"
Hidden verb "conduct an analysis" "analyze"
Passive hiding actor "it was decided" "[Who] decided"
Nominalisation "the implementation of" "implementing"

Scan 3 — Paragraph discipline:

  • Any paragraph > 6 sentences → flag for splitting
  • Any paragraph = 1 sentence → flag (should be a heading or merged with adjacent paragraph)
  • Three consecutive paragraphs of the same length → flag for rhythm variation

Layer 4 — Style Compliance Check

Compare the draft against the active style profile field by field:

Protocol:

  1. Read the style profile
  2. Select 5 representative paragraphs from across the document (intro, middle, end, plus executive summary)
  3. For each paragraph, check: tone match? formality match? sentence length? voice? person? hedging level?
  4. Log drift: where does the draft deviate from the profile?

Common drift patterns:

Drift What it looks like Severity
Formality collapse Starts formal, becomes casual by page 5 WARNING
Hedging creep Starts confident ("the data shows"), becomes tentative ("it might suggest") WARNING if pattern, SUGGESTION if isolated
Tone mismatch Profile says "authoritative," document reads as tentative WARNING
Voice inconsistency Switches between active and passive without pattern SUGGESTION
Person shifting Switches between "we" and "the team" inconsistently WARNING

Layer 5 — Consistency Check

Terminology: Search for the same concept described with different words. "The platform" vs. "the system" vs. "the tool" — pick one and use it throughout.

Abbreviations: Check that every abbreviation is defined on first use (full term first, abbreviation in parentheses). Check that after definition, usage is consistent.

Formatting: Check heading levels, bullet styles, table formatting, bold/italic usage for consistency.

Tense: Check that tense is consistent within sections. Past tense for findings. Present tense for analysis. Future tense for recommendations.

Naming: Check that people, organizations, and products are named consistently throughout.


Issue Severity Classification

BLOCKING

The document cannot be approved with this issue. It must be fixed.

Criteria: The issue prevents the document from accomplishing its purpose, introduces factual errors, or would embarrass the author in front of the reader.

Examples: Missing section from brief. Unsupported major claim. Fabricated data. Executive summary contradicts body. Unresolved placeholders.

WARNING

The document is weakened by this issue. It should be fixed but won't catastrophically fail without the fix.

Criteria: The issue reduces clarity, undermines credibility, or creates an inconsistency that an attentive reader would notice.

Examples: Underdeveloped section. Logical leap (evidence exists but reasoning is unstated). Tone drift from profile. Terminology inconsistency.

SUGGESTION

An optional improvement. The document works without it but would be better with it.

Criteria: The issue is a matter of craft refinement, not structural integrity.

Examples: A paragraph that could be tighter. A transition that could be smoother. A data point that could use more context.


Verdict Decision Matrix

BLOCKING count WARNING count Verdict
0 0-3 APPROVED
0 4+ REVISION (focused on WARNINGs)
1-5 any REVISION (focused on BLOCKINGs)
6+ any STRUCTURAL REVIEW (return to Brief Builder)

Runtime Output Contract

When emitting the actual review result for the runtime:

  • Include exactly one structured decision tag: <review_decision>APPROVE</review_decision> or <review_decision>REVISE</review_decision>.
  • You may place explanations, blocking issues, and warnings before or after the tag.
  • Do not emit multiple decision tags.
  • Treat the tag as a hard protocol requirement, not a style preference.

References & Templates

File Content
references/common-issues.md Catalog of the 30 most common business document issues with examples and fixes
references/filler-phrases.md Comprehensive list of corporate filler with severity ratings and replacements
templates/editorial-review.md Standard output template for the editorial review report

04 同仓库更多 Skills

cwik-tech
cwik-tech/octopus

twenty-year-land-plan

Apply the Bren discipline of evaluating every land and development decision on a twenty-year horizon, with a comprehensive plan for how the land, the community, and the surrounding public infrastructure evolve together. Deals optimized for a five-year exit are structurally different from deals that compound across generations; insist on knowing which kind you are making. Use when evaluating land, entitlements, master-planned development, or phasing decisions, and when separating five-year exit deals from generational holds.

★ 0
cwik-tech
cwik-tech/octopus

thematic-gut-check

Apply the Gray discipline of identifying the structural theme behind every real estate deal, testing where that theme sits in its capital-flow lifecycle, and insisting that deals without a named theme — or deals late in a crowded theme — clear a higher bar. A mediocre deal in a strong theme usually beats a clever deal in a weak one. Use when naming the structural thesis behind a deal, judging whether that theme is early or crowded, and setting the bar the deal must clear.

★ 0
cwik-tech
cwik-tech/octopus

supply-pipeline-gut-check

Apply the Zell discipline of grounding every real estate thesis in the local supply pipeline. Demand counts over adjectives — units under construction, units permitted, units proposed — and convert them into a forward absorption schedule. A deal that ignores the pipeline is a bet on a market you have not actually studied. Use when validating a market thesis, forecasting absorption and rent growth, or counting units under construction, permitted, and proposed.

★ 0
cwik-tech
cwik-tech/octopus

ruin-scenario-mapping

Apply the Taleb discipline of identifying, for every real estate deal, the specific chain of events that produces ruin — permanent, unrecoverable capital loss — and verifying that no single such chain has non-trivial probability. Deals with any plausible ruin path must be restructured or abandoned. Use when sizing leverage, testing refinancing, covenant, and liquidity risk, or checking whether any single failure chain can permanently wipe out the position.

★ 0
cwik-tech
cwik-tech/octopus

revenue-cost-architecture

Design a venture's revenue streams, pricing logic, cost structure, and unit economics so the business model has a coherent theory of value capture, not just value creation. Use after the value proposition and customer segment are set and before financial projections, when choosing a pricing model, calculating contribution margin or CAC payback, or checking whether the unit economics hold at scale.

★ 0
cwik-tech
cwik-tech/octopus

replacement-cost-stress-test

Apply the Buffett discipline of pricing every real estate asset against the cost to rebuild it from scratch. The ratio of purchase price to replacement cost sets a ceiling on long-run downside: below replacement cost, new supply cannot profitably undercut you; at or above it, you are buying a liability disguised as an asset. Use when setting a purchase price, judging downside protection, or testing how exposed an asset is to newly built competing supply.

★ 0