NSFC Proposal Expert Review Simulator

Important Disclaimer (Non-Official)

The output of this skill is only for writing improvement and self-checking, and does not represent any official review caliber, nor does it constitute a funding conclusion or commitment.
The "review grade/funding recommendation" is only for reference as priority and improvement direction; this section may be omitted if the user does not explicitly request it.

Skill Dependencies

Parallel multi-group review mode depends on the
```
parallel-vibe
```
skill.
If
```
parallel-vibe
```
is unavailable, disabled, or
```
panel_count == 1
```
, it automatically degrades to single-group mode (still includes 5 experts).
Expert prompt templates are located in
```
references/expert_*.md
```
, and aggregation rules are in
```
references/aggregation_rules.md
```
.

Security and Privacy (Hard Rules)

By default, proposal content is treated as sensitive information: only process files/directories explicitly provided by the user; do not expand the scanning scope without permission.
Unless explicitly requested by the user and risks are confirmed: no internet access, do not send large segments of the original text externally, and do not repeat unnecessary personal/unit information in the output.
Only perform "text reading and review"; by default, do not execute any compilation/running (e.g., do not run LaTeX compilation, do not execute scripts).
If output needs to be shared: prioritize providing "issue summary + actionable modification suggestions"; when necessary to quote the original text, only quote the shortest necessary fragment.

Input

Users must provide at least one of the following:

```
proposal_path
```
: Proposal directory (recommended, containing multiple
```
.tex
```
files)
```
proposal_file
```
: Single main
```
.tex
```
file (if the user only has one file)
```
proposal_zip
```
: Compressed package (if provided, first extract to a temporary directory for review, and record the extraction location in the report)
- Extraction security: Prohibit path traversal (e.g.,
```
../
```
  ); avoid overwriting existing user files; if necessary, ask the user to confirm the extraction location first.

Optional supplementary inputs (do not assume if not provided by the user):

```
focus
```
: Prioritize a specific dimension (e.g., "innovation/feasibility/research foundation")
```
output_path
```
: Output file path (default see "Output")
```
style
```
: Tone preference (e.g., "strict/moderate/very specific")

panel_count

: Number of review panels (each panel has 5 fixed experts)

Default value see

config.yaml:parallel_review.default_panel_count

Upper limit see

config.yaml:parallel_review.max_panel_count

Output

Default output filename see
```
config.yaml:output_settings.default_filename
```
, which is written to the proposal directory by default:
```
./{default_filename}
```
.
If the user specifies
```
output_path
```
, follow the user's setting; but if the path is unwritable or the directory does not exist, fail fast and prompt the user to change the path.
In parallel mode, output "expert consensus + independent opinions + aggregated suggestions"; original opinions of each expert can be attached as per configuration.
In parallel mode, it is recommended to organize the original reviews of each panel into final deliverable files:
```
./{panel_dir}/G{panel_number}.md
```
(
```
panel_dir
```
see
```
config.yaml:output_settings.panel_dir
```
).
Intermediate files are hidden in
```
config.yaml:output_settings.intermediate_dir
```
by default (default
```
.nsfc-reviewers/
```
) to avoid cluttering the root directory with plans, logs, and parallel runtime environments.

Workflow (Execution Specifications)

Read Configuration (Mandatory)

Before starting, read the

config.yaml

in the skill directory, and use the following configurations as the single source of truth during execution:

```
review_dimensions
```
: Review dimensions, weights, key points, and common issues (as a checklist)
```
severity_levels
```
: P0/P1/P2 grading criteria (for classification)
```
review_grades
```
: Grades and suggestions (only output if requested by the user)
```
proposal_files.patterns/exclude
```
: Proposal file identification rules
```
output_settings
```
: Output filename, panel directory, intermediate process hiding strategy, and chapter switches
```
parallel_review
```
: Parallel review switch, expert personas, aggregation strategy

Phase 1: Pre-Check (Fail Fast)

Verify that the input path exists and is readable; if it is a directory, first filter the list of files to be read according to the
```
proposal_files
```
rules.
If the number of
```
.tex
```
files is 0: directly report an error and request the user to provide the correct path/file.
If the number of files is abnormally large or the directory obviously contains a large number of irrelevant files: first ask the user to confirm the review scope (to avoid reading the wrong directory or too many files).

Recommended deterministic approach (avoid "missing subdirectories / mis-scanning intermediate directories / scanning deliverables"):

bash

# List .tex files to be included in the review (recursive scan, automatically skipping panels/, .nsfc-reviewers/, .parallel_vibe/)
python3 <nsfc_reviewers_path>/scripts/list_proposal_files.py --proposal-path <proposal_root>

# Optional: Limit maximum number of files (exit code=3 if exceeded)
python3 <nsfc_reviewers_path>/scripts/list_proposal_files.py --proposal-path <proposal_root> --max-files 200

Phase 2: Read-Through and Structured Understanding

Quickly read through the proposal in chapter order, extracting "project topic/scientific hypothesis/objectives/technical route/innovation points/research foundation/team and conditions/expected outcomes".
Generate a "proposal structure index" (only to chapter level) as a positioning anchor for subsequent references.

Phase 3: Parallel Multi-Group Review (Priority) or Single-Group Mode (Degradation)

Pre-Judgment

Calculate

effective_panel_count

: prioritize user input

panel_count

, otherwise use

parallel_review.default_panel_count

Limit

effective_panel_count

[1, parallel_review.max_panel_count]

Directly use single-group mode if any of the following conditions are met:
- ```
parallel_review.enabled == false
```
- ```
effective_panel_count == 1
```
- Cannot find the
```
parallel-vibe
```
  script

parallel-vibe Script Path Discovery Order

Search the following paths in order, use the first one found:

~/.claude/skills/parallel-vibe/scripts/parallel_vibe.py

~/.codex/skills/parallel-vibe/scripts/parallel_vibe.py

<current_repository>/parallel-vibe/scripts/parallel_vibe.py

If none are found: record a warning and degrade to serial mode without interrupting the overall review.

Parallel Mode Steps

Prepare Intermediate Directory Structure (Highly Recommended):

bash

mkdir -p <proposal_root>/<intermediate_dir>/{logs/plans,snapshot}

<intermediate_dir>

corresponds to

config.yaml:output_settings.intermediate_dir

(default

.nsfc-reviewers

Construct Master Prompt (completed by the host AI):
- Read 5 expert personas from
```
references/expert_*.md
```
  (corresponding to
```
config.yaml:parallel_review.reviewer_personas[*].prompt_file
```
  )
- Read the master prompt template from
```
references/master_prompt_template.md
```
- Inject context: "proposal structure index + key information summary" produced in Phase 2
- Inject unified quality threshold: issue classification, evidence anchors, output format
- Inject independence constraints: each expert makes independent judgments without assuming other experts' opinions
- Inject output constraints: write the panel's output to
```
config.yaml:parallel_review.panel_output_filename
```
  in the root directory of the current thread's
```
workspace/
```
- Replace template placeholders: replace
```
{panel_output_filename}
```
  with
```
config.yaml:parallel_review.panel_output_filename
```
- Save the master prompt to a temporary file (recommended to be placed in
```
<proposal_root>/<intermediate_dir>/logs/
```
  for easy tracing without polluting the root directory), recorded as
```
<master_prompt_path>
```
Generate parallel-vibe Plan File (Mandatory):
- Reason: Avoid escaping ultra-long prompts in the CLI; and avoid the automatic splitting logic of
```
parallel-vibe --prompt
```
  (this skill requires "the same master prompt to be executed repeatedly in N independent workspaces")
- Prioritize using the built-in script of this skill to generate the plan file:

bash

python3 <nsfc_reviewers_path>/scripts/build_parallel_vibe_plan.py \
  --panel-count <effective_panel_count> \
  --master-prompt-file <master_prompt_path> \
  --out <plan_json_path>

If the script cannot be used, manually generate
```
plan.json
```
(minimum structure):

json

{
  "plan_version": 1,
  "prompt": "nsfc-reviewers parallel panels",
  "threads": [
    {
      "thread_id": "001",
      "title": "Panel G001",
      "runner": { "type": "<config:parallel_review.runner>", "profile": "<config:parallel_review.runner_profile>", "model": "", "args": [] },
      "prompt": "<master_prompt>"
    }
  ],
  "synthesis": { "enabled": false }
}

Call parallel-vibe (Based on Plan File):

It is recommended to prepare a proposal snapshot (e.g.,
```
proposal_snapshot/
```
) in
```
<proposal_root>/<intermediate_dir>/snapshot/
```
first, and use it as
```
--src-dir
```
to avoid copying
```
.nsfc-reviewers/
```
,
```
panels/
```
and other intermediate/deliverable directories into the
```
workspace/
```
of each thread again.
Minimum approach: Copy the "proposal directory to be reviewed" to
```
snapshot/
```
and exclude intermediate/deliverable directories (specific commands depend on platform tools; principle: the snapshot directory should only contain proposal source files).

bash

python3 <parallel_vibe_path> \
  --plan-file <plan_json_path> \
  --src-dir <proposal_snapshot_root_or_proposal_root> \
  --out-dir <proposal_root>/<intermediate_dir> \
  --timeout-seconds <config:parallel_review.timeout_seconds> \
  --no-synthesize

Collect and Verify Panel Outputs:
- Read
```
panel_output_filename
```
  from the
```
workspace/
```
  of each thread
- Typical path (after running but before organizing output):
```
<proposal_root>/<intermediate_dir>/.parallel_vibe/<project_id>/<thread_id>/workspace/<panel_output_filename>
```
- If you have executed "Phase 5: Output Organization", the parallel-vibe environment is usually located at:
```
<proposal_root>/<intermediate_dir>/parallel-vibe/<project_id>/...
```
- ```
parallel-vibe
```
  will print the current
```
project_root
```
  path in stdout; prioritize using this path
- If the output of individual threads is missing, record the missing and continue aggregating completed results (fail-soft)
- It is recommended to copy/organize the final review report of each panel into final deliverable files:
```
<proposal_root>/{panel_dir}/G{thread_id}.md
```

Single-Group Mode Steps (Degradation)

Read
```
references/expert_*.md
```
to get 5 expert personas (innovation/methodology/foundation/strict/constructive)
Simulate parallel process: let 5 experts complete "independent reviews" in sequence (without referencing each other)
Perform intra-panel aggregation (consensus identification/severity escalation/deduplication and merging)
Output the single-panel review report to
```
panel_output_filename
```

Phase 4: Aggregation, Sorting and Optional Conclusion

Cross-Panel Aggregation (Parallel Multi-Group Mode)

Read cross-panel aggregation rules from
```
references/aggregation_rules.md
```
.
Cross-compare N groups of
```
panel_review.md
```
to identify different expressions of the same issue.
Cross-panel consensus threshold: pointed out by at least
```
ceil(N * consensus_threshold)
```
panels → cross-panel consensus (threshold see
```
config.yaml:parallel_review.aggregation.consensus_threshold
```
).
Secondary severity escalation: cross-panel consensus issues P2→P1→P0 (P0 no longer escalated).
Merge duplicate issues, retaining the most complete evidence anchors and actionable suggestions.
Retain independent opinions and label their source panel (e.g., "from Panel G001").
Output results in order of P0→P1→P2, and provide a minimal viable modification sequence.
If
```
keep_individual_reviews == true
```
, append original review reports of each panel in the appendix.

Single-Panel Summary

Output "summary of modification suggestions", sorted by P0→P1→P2, and provide a minimal viable modification sequence.

Optional Comprehensive Conclusion

Only output "comprehensive score/funding recommendation" when explicitly requested by the user (and reaffirm that it is for improvement reference).

Phase 5: Output Organization (Mandatory Execution)

Importance: This phase is key to ensuring output traceability and cannot be skipped. When

config.yaml:output_settings.enforce_output_finalization == true

, you must not end the review without completing this phase.

Goal: Final deliverables are clearly visible; intermediate processes are uniformly managed in

config.yaml:output_settings.intermediate_dir

(default

.nsfc-reviewers/

) to avoid clutter in the root directory from plans, logs, parallel environments, etc.

Pre-Check (Execute in Order)

Calculate and confirm
```
effective_panel_count
```
(see Phase 3).
Determine the review mode for this time:
- If
```
effective_panel_count > 1
```
  and you actually called
```
parallel-vibe
```
  (or found the
```
.parallel_vibe/
```
  runtime environment) → regarded as "parallel mode"
- Otherwise → "serial mode" (still must create minimal intermediate directories and logs)

Recommended Approach: Use Script to Automate Output Organization (Deterministic, Highly Recommended)

bash

python3 <nsfc_reviewers_path>/scripts/finalize_output.py \
  --review-path <proposal_root> \
  --panel-count <effective_panel_count> \
  --intermediate-dir <config:output_settings.intermediate_dir> \
  --apply

Without
--apply
, it is a DRY-RUN: only print actions to be executed without modifying files.

Manual Organization (Fallback When Script Is Unavailable)

Both parallel and serial modes must create at least the minimal directory structure:

bash

mkdir -p <proposal_root>/<intermediate_dir>/{parallel-vibe,logs/plans,snapshot}

Parallel mode: Migrate the project directory of

.parallel_vibe/

<intermediate_dir>/parallel-vibe/

(compatible with two source locations):

bash

# 1) Prioritize migration from <proposal_root>/<intermediate_dir>/.parallel_vibe/ (common when parallel-vibe --out-dir points to intermediate_dir)
if [ -d "<proposal_root>/<intermediate_dir>/.parallel_vibe" ]; then
  mv "<proposal_root>/<intermediate_dir>/.parallel_vibe/"* "<proposal_root>/<intermediate_dir>/parallel-vibe/" 2>/dev/null || true
  rmdir "<proposal_root>/<intermediate_dir>/.parallel_vibe" 2>/dev/null || true
fi

# 2) Compatible with old instances: migrate from root directory .parallel_vibe/
if [ -d "<proposal_root>/.parallel_vibe" ]; then
  mv "<proposal_root>/.parallel_vibe/"* "<proposal_root>/<intermediate_dir>/parallel-vibe/" 2>/dev/null || true
  rmdir "<proposal_root>/.parallel_vibe" 2>/dev/null || true
fi

Migrate logs and plan files (execute only if they exist):

bash

mv "<proposal_root>/master_prompt.txt" "<proposal_root>/<intermediate_dir>/logs/" 2>/dev/null || true
mv "<proposal_root>"/plan*.json "<proposal_root>/<intermediate_dir>/logs/plans/" 2>/dev/null || true
mv "<proposal_root>/proposal_snapshot" "<proposal_root>/<intermediate_dir>/snapshot/" 2>/dev/null || true

Verification Checklist (Self-Check After Execution, Cannot End If Not Passed)

<proposal_root>/<intermediate_dir>/

has been created, and contains at least

logs/

and

logs/plans/

If in parallel mode:

<proposal_root>/<intermediate_dir>/parallel-vibe/

contains the

<project_id>/...

runtime environment

master_prompt.txt

(or its copy) can be found in

<proposal_root>/<intermediate_dir>/logs/

Final deliverables are still in the root directory:
```
{default_filename}
```
and
```
{panel_dir}/G*.md
```
(unrelated intermediate files should not be scattered in the root directory)

Report Format (Hard Threshold)

For each P0/P1 issue, it must include at least one "evidence anchor":

```
Evidence Anchor
```
: Filename + chapter title/key sentence (line number optional)
```
Observation
```
: Why this is an issue (no vague descriptions)
```
Impact
```
: How it will affect review judgment/feasibility/persuasiveness
```
Suggestion
```
: Actionable modification plan (prioritize providing "how to modify" and "what level of modification is sufficient")
```
Validation
```
: How to self-check after modification (e.g., "add a roadmap", "add a paragraph of coordinate system comparison", "add a chain of pre-experiment evidence")

Recommended structure for parallel mode:

markdown

# NSFC Proposal Review Opinions (N Groups of Independent Experts)

## Review Configuration
- Number of review panels: N groups
- Experts per panel: 5
- Total expert person-times: N×5

## Cross-Panel Consensus (Pointed Out by Multiple Groups)
### P0 Level

## Independent Opinions (Proposed by Single Group)
### From Panel G001

## Summary of Modification Suggestions

## Appendix: Original Review Reports of Each Panel (Optional)

Usage Example

User input:

text

Please review the NSFC proposal at /path/to/nsfc_proposal and save the opinions to /path/to/output.md

Configuration Parameters

See

config.yaml

for details:

```
review_dimensions
```
: Review dimension configuration (weights/key points/common issues)
```
severity_levels
```
: Definition of issue severity levels
```
review_grades
```
: Review grades and suggestions (optional output)
```
proposal_files
```
: Proposal file identification rules
```
output_settings
```
: Output settings (default filename/panel directory/intermediate directory/chapter switches; and output organization verification:
```
enforce_output_finalization
```
/
```
warn_missing_intermediate
```
/
```
validation_level
```
)
```
parallel_review
```
: Parallel multi-group review configuration (switch/number of panels/expert persona references/cross-panel aggregation strategy)

nsfc-reviewers

NPX Install

Tags

SKILL.md Content (Chinese)

NSFC Proposal Expert Review Simulator

Important Disclaimer (Non-Official)

Skill Dependencies

Security and Privacy (Hard Rules)

Input

Output

Workflow (Execution Specifications)

Read Configuration (Mandatory)

Phase 1: Pre-Check (Fail Fast)

Phase 2: Read-Through and Structured Understanding

Phase 3: Parallel Multi-Group Review (Priority) or Single-Group Mode (Degradation)

Pre-Judgment

parallel-vibe Script Path Discovery Order

Parallel Mode Steps

Single-Group Mode Steps (Degradation)

Phase 4: Aggregation, Sorting and Optional Conclusion

Cross-Panel Aggregation (Parallel Multi-Group Mode)

Single-Panel Summary

Optional Comprehensive Conclusion

Phase 5: Output Organization (Mandatory Execution)

Pre-Check (Execute in Order)

Recommended Approach: Use Script to Automate Output Organization (Deterministic, Highly Recommended)

Manual Organization (Fallback When Script Is Unavailable)

Verification Checklist (Self-Check After Execution, Cannot End If Not Passed)

Report Format (Hard Threshold)

Usage Example

Configuration Parameters