Research Project Justification Writer

Target Output (Contract)

Only write to:
```
extraTex/1.1.立项依据.tex
```
Prohibited modifications:
```
main.tex
```
,
```
extraTex/@config.tex
```
, any
```
.cls/.sty
```
files
Writing goal: Clearly explain "why this project needs to be done" and lay the groundwork for " (II) Research Content" with "scientific questions/hypotheses and entry points".
AI dependency: By default, uses the native intelligence of Claude Code / Codex provided by the runtime environment (no need to configure any external API Key; will automatically fall back to hard-coded capabilities if AI is unavailable)
Theoretical innovation orientation (default): Prioritize the falsifiability of scientific questions/hypotheses, clarity of theoretical contributions, and completeness of verification dimensions (see theoretical_innovation_guidelines.md)

Configurable writing orientation: Switch using

style.mode=theoretical|mixed|engineering

skills/nsfc-justification-writer/config.yaml

(default is

theoretical

)

Required Input (Minimal Information Form)

If not provided by the user, first collect/supplement: references/info_form.md

Recommendation: Use the script to quickly generate the information form (with interactive filling), see
skills/nsfc-justification-writer/scripts/run.py init
.

Workflow (Execute in Order)

Locate project and target file: Confirm
```
project_root
```
, read and only edit
```
extraTex/1.1.立项依据.tex
```
.
Extract existing skeleton: If the file already has subheadings like
```
\subsubsection
```
, prioritize retaining the skeleton and only replace the body paragraphs (unless the user requests restructuring). By default, do not enforce exact title matching (
```
strict_title_match=false
```
), focus more on "whether content dimensions are covered".
Progressive writing guidance (recommended): Skeleton first → then paragraphs → then revision → then polishing → then acceptance (avoid the pressure of one-step completion)
- Use
```
scripts/run.py coach --stage auto
```
  to automatically judge the current stage and provide "only three tasks for this round + questions you need to supplement + copyable prompts"
- Only modify the body of one
```
\subsubsection
```
  per round, use
```
apply-section
```
  for safe writing and automatic backup
Generate the main narrative of "Project Justification" (recommended 4-paragraph closed loop; AI will check content dimension coverage instead of rigidly adhering to titles):
- Value and Necessity: Pain points → scope of impact/cost → why it must be done now.
- Current Status and Limitations: Mainstream approaches/representative works → 2–4 clear limitations (try to be quantifiable/verifiable).
- Scientific Questions/Core Hypotheses: One hypothesis + 1–3 key scientific questions (breakpoint style), oriented towards "verifiability".
- Project Entry Point and Contributions: The "differentiated entry point" of this project compared to existing work, with one transition sentence to the research content.
Verifiability and Citation Protection:
- AI semantically identifies "expressions that may cause reviewer discomfort" (absolute statements/filling gaps/unsubstantiated exaggerations/self-qualification) and provides rewriting suggestions; hard-coded high-risk words are only for prompts, not mechanical blocking.
- Do not write unprovable statements like "internationally leading/first in China"; when citing external works, first ask the user to provide DOI/link or call
```
nsfc-bib-manager
```
  for verification before writing
```
\cite{...}
```
  .
Cross-section Consistency Check: Check if terms/abbreviations/indicator calibers align with
```
2.1 Research Content
```
; if necessary, list 3–5 key nouns and indicators for user confirmation.
Target Word Count Analysis: Prioritize parsing the user's intent/"word count"/"± range"/interval description in the information form; use configuration defaults only if there is no explicit instruction.

Configuration Validation and Large File Support (Optional)

Configuration validation:

python skills/nsfc-justification-writer/scripts/run.py validate-config

Large File Tier2:
```
diagnose/review --tier2 --chunk-size 12000 --max-chunks 20
```
(supports
```
.cache/ai
```
caching; ultra-large files will prioritize streaming chunking to reduce peak memory usage; use
```
--fresh
```
to force recalculation)
Note: The script layer of this repository will not "directly connect to external large models by default"; whether AI capabilities are available depends on whether the runtime environment injects a responder (will automatically fall back to hard-coded capabilities if unavailable)
Related design instructions:
- Content dimension coverage check:
```
skills/nsfc-justification-writer/references/dimension_coverage_design.md
```
- Identification and rewriting of "expressions that may cause reviewer discomfort":
```
skills/nsfc-justification-writer/references/boastful_expression_guidelines.md
```
- Theoretical Innovation Orientation Writing Guidelines:
```
skills/nsfc-justification-writer/references/theoretical_innovation_guidelines.md
```
  (includes warnings on misused methodological terms)
- Comparison Examples of Misused Methodological Terms:
```
skills/nsfc-justification-writer/references/methodology_term_examples.md
```
  (newly added)

Configurable Prompt Templates (Optional)

prompts.*

config.yaml

preset.yaml

override.yaml

supports two forms:

File path: e.g.,
```
prompts/tier2_diagnostic.txt
```
Direct multi-line Prompt: Write multi-line text in YAML using
```
|
```
(suitable for adjusting focus in different fields)

It also supports override by preset variants: for example, when

--preset medical

is used,

prompts.tier2_diagnostic_medical

can be provided.

Recommended

\\subsubsection

Title and Content Mapping

Note: The template and

config.yaml

recommend 4

\subsubsection

titles by default (

structure.recommended_subsubsections

), while the "4-paragraph closed loop" is the content narrative logic. To avoid user confusion, recommend mapping writing according to the following table:

`\\subsubsection` Title	Corresponding Narrative Paragraph	Core Writing Elements (Theoretical Innovation Orientation by Default)
Research Background	Value and Necessity	Theoretical gaps/cognitive deficiencies → Why it must be done now (theory-driven)
Domestic and International Research Status	Current Limitations	Mainstream approaches → Theoretical Limitations (overly strong assumptions/unified framework missing/causality gaps/loose boundaries)
Limitations of Existing Research	Scientific Questions/Core Hypotheses	Falsifiable hypothesis → Key scientific questions → Verification dimensions (theoretical proof/theorem/numerical verification)
Research Entry Point	Project Entry Point and Contributions	Theoretical Differentiated Entry Point (new representation/methodology/unified framework) → Transition to 2.1 Research Content

If the user really needs to modify the subheadings: It is recommended to maintain the 4-paragraph structure and unify the title skeleton first (see

templates/structure_template.tex

); the structure check will no longer mechanically match titles, but still requires at least 4 sections.

Key Capabilities

For the closed loop of "diagnose first → then generate → then safe writing → then acceptance":

AI Function List (Optional Enhancement)

Function	AI Required?	Fallback Behavior
Tier1 Diagnosis (structure/citation/word count/high-risk examples/dangerous commands)	❌	N/A
Content Dimension Coverage Check	✅	Heuristic keyword detection (fallback)
Boastful Expression Recognition (semantic)	✅	No blocking; only rely on Tier1 high-risk example prompts
Term Consistency (semantic)	✅	Only output hard-coded matrix ( `terminology.dimensions` )
AI Example Recommendation (with reasons)	✅	Keyword/category heuristic matching
AI Stage Judgment (coach --stage auto)	✅	Hard-coded threshold rules
Tier2 In-Depth Diagnosis (diagnose --tier2)	✅	Skip (only output Tier1)

Whether AI is available depends on whether the runtime environment injects a responder; use
skills/nsfc-justification-writer/scripts/run.py check-ai
for self-test.

Tier1 Hard-Coded Diagnosis: Structure (≥4
```
\subsubsection
```
s) / whether citation keys exist in
```
.bib
```
/ DOI missing and format abnormality prompts / word count statistics / high-risk expression prompts and dangerous command scanning
Content Dimension Coverage Check (AI): Does not depend on title wording, checks whether "value and necessity/current limitations/scientific questions/entry points" are covered
Boastful Expression Recognition (AI): Identifies absolute statements/gap-filling/unsubstantiated exaggerations/self-qualification, outputs rewriting suggestions
Cross-Section Consistency Matrix: Provides cross-section consistency prompts based on
```
terminology.dimensions
```
(research objects/indicators/terms) in
```
config.yaml
```
AI Term Consistency (Optional): When AI is available and
```
terminology.mode=auto/ai
```
, additionally provides semantic perspective checks and modification suggestions for "synonym/abbreviation misuse" (only outputs matrix if unavailable)
Safe Writing Tool: Precisely locates and replaces the body text by
```
\subsubsection{...}
```
, writes to whitelisted files + backup (products are stored in
```
skills/nsfc-justification-writer/runs/
```
)
Pre-Writing Quality Gate (Optional):
```
apply-section --strict-quality
```
only scans the "newly added body text" for high-risk words/dangerous commands; if AI is available, it adds semantic blocking of "boastful expressions" to avoid being stuck by historical content
Reviewer Suggestion Generator: Based on DoD + diagnosis results, outputs "what reviewers will ask + how to modify" (
```
scripts/run.py review
```
)
Visual HTML Diagnosis Report: Quickly locate issues (
```
scripts/run.py diagnose --html-report auto
```
)
Version Diff/Rollback: View differences and one-click rollback based on runs backups (
```
scripts/run.py diff/rollback
```
)
Example Recommendation: Read
```
*.metadata.yaml
```
keywords from
```
examples/
```
to assist in matching reference skeletons by topic (
```
scripts/run.py coach --topic ...
```
/
```
scripts/run.py examples
```
)
AI Example Recommendation (Optional): When AI is available, prioritize semantic matching and provide "recommendation reasons" (falls back to keyword/category heuristics if unavailable)
AI Stage Judgment (Optional): When
```
--stage auto
```
is used in coach, AI can comprehensively infer "skeleton/draft/revise/polish/final" based on word count/structure/quality status; falls back to hard-coded thresholds if AI is unavailable
Configuration Override and Presets: Supports
```
--preset medical/engineering
```
and
```
~/.config/nsfc-justification-writer/override.yaml
```
to override parameters such as term dimensions (can be turned off with
```
--no-user-override
```
if needed)

Script entry:

skills/nsfc-justification-writer/scripts/run.py

(usage see

skills/nsfc-justification-writer/scripts/README.md

systematic-literature-review Integration (Optional)

This skill supports read-only access to literature review directories generated by

systematic-literature-review

, facilitating citation of existing research status content.

Identification Criteria

A directory is automatically identified as a

systematic-literature-review

generated directory if it meets any of the following conditions:

Contains a hidden folder

.systematic-literature-review

, which includes

{topic}_review.tex

and

{topic}_参考文献.bib

references.bib

files (running pipeline)

Contains typical file combinations:

{topic}_review.tex

{topic}_参考文献.bib

references.bib

{topic}_工作条件.md

(completed output directory)

Contains files with the same prefix:
```
{topic}_review.tex
```
and
```
{topic}_参考文献.bib
```
(based on filename prefix matching)

Read-Only Access Constraints

For directories generated by

systematic-literature-review

Read-only mode: Only read the content of
```
.tex
```
and
```
.bib
```
files
No writing allowed: Will not modify any files in the directory
Citation verification: Automatically verify whether citations in
```
.tex
```
are consistent with definitions in
```
.bib
```

Usage Scenarios

The user requests to cite existing literature review content
Need to extract research status information from systematic reviews
Want to ensure citation consistency

Core Functions

Directory detection:

detect_slr_directory(path)

judges whether it is a

systematic-literature-review

Acceptance Criteria (Definition of Done)

See: references/dod_checklist.md

Change Log

This skill does not maintain change history in this document; it is uniformly recorded in the root-level
```
CHANGELOG.md
```
.
Version numbers are only maintained in
```
skills/nsfc-justification-writer/config.yaml
```
(
```
skill_info.version
```
) and the frontmatter of this file to avoid inconsistent caliber.

nsfc-justification-writer

NPX Install

Tags

SKILL.md Content (Chinese)