Technical Proposal Reviewer
Review technical project proposals for quality, consistency, overpromises, and legal risk. Produce actionable feedback the author can use to improve the proposal.
Review Workflow
- Read the proposal — Load the full document (use
docx or pdf skill as needed)
- Assess structure — Check all expected sections are present and properly ordered
- Check consistency — Verify cross-references between objectives, WPs, deliverables, budget, and timeline
- Flag overpromises — Identify language that oversells or makes unsupported claims
- Flag legal risk — Identify language that could create binding obligations
- Evaluate content quality — Assess depth, citations, and clarity per section
- Produce review report — Structured feedback with severity levels
Review Dimensions
1. Structural Completeness
Check that the proposal contains all standard sections. Missing sections should be flagged.
Expected sections (adapt to funding call):
- Abstract/Executive Summary
- State of the Art
- Objectives
- Methodology
- Work Plan / Work Packages
- Deliverables & Milestones
- Timeline
- Budget
- Risk Management
- Impact & Exploitation
- References
2. Internal Consistency
Cross-check these mappings:
| From |
To |
Check |
| Objectives (O1..On) |
Work Packages |
Every objective covered by ≥1 WP |
| Work Packages |
Objectives |
Every WP maps to ≥1 objective |
| Tasks |
Deliverables |
Every deliverable traces to tasks |
| Deliverables |
Timeline |
Due dates within WP duration |
| Milestones |
Timeline |
Milestone dates on Gantt chart |
| Budget (effort) |
WP effort tables |
Person-months match |
| Partner roles |
WP leads |
Partners listed in WPs match consortium |
3. Overpromise Detection
Flag statements that claim more than the evidence supports:
Red flags:
- "Will achieve X" without feasibility evidence → suggest "Aims to achieve X"
- Benchmark numbers stated as guaranteed outcomes → suggest framing as targets
- Claims of "first ever", "unique", "revolutionary" without strong justification
- Objectives that exceed project scope/budget/timeline
- Impact claims disconnected from project outputs
Suggested replacement patterns:
| Overpromise |
Suggested Alternative |
| "will achieve 95% accuracy" |
"targets 95% accuracy based on preliminary results showing 88%" |
| "will revolutionize" |
"has the potential to significantly advance" |
| "guaranteed delivery" |
"planned delivery, subject to milestone review" |
| "unique solution" |
"novel approach that differs from existing methods in [specific way]" |
| "will solve the problem" |
"addresses key aspects of the problem, specifically [X, Y]" |
4. Legal Risk Assessment
Flag language that could create enforceable obligations:
High risk:
- Unconditional commitments: "we will deliver", "we guarantee", "we commit to"
- Quantitative guarantees without caveats: "system will process 1M records/sec"
- IP transfer language without legal review
- Data sharing commitments that may conflict with GDPR or institutional policy
- Liability-implying language: "we accept responsibility for", "we ensure"
Recommended mitigations:
- Add "subject to" clauses for conditional commitments
- Frame deliverables as "planned" rather than "guaranteed"
- Add standard disclaimers for performance targets
- Flag IP and data clauses for legal counsel review
5. Content Quality
Per-section quality assessment:
| Section |
Key Quality Criteria |
| Abstract |
Self-contained, concise, compelling, no jargon |
| State of the Art |
Recent citations, fair comparison, clear gap statement |
| Objectives |
SMART criteria met, realistic scope |
| Methodology |
Concrete approach, justification over alternatives, feasibility |
| Work Plan |
Clear task breakdown, realistic effort, dependencies shown |
| Impact |
Concrete exploitation paths, quantified where possible |
| Risks |
Honest assessment, high-impact risks included, mitigations concrete |
Output Format
Produce a structured review report:
# Proposal Review: [Project Title/Acronym]
## Summary Assessment
[2-3 sentence overall assessment]
Overall readiness: [Ready / Needs Minor Revisions / Needs Major Revisions / Not Ready]
## Critical Issues (must fix)
1. [Issue description] — [Location in document] — [Suggested fix]
## Major Issues (should fix)
1. [Issue description] — [Location in document] — [Suggested fix]
## Minor Issues (nice to fix)
1. [Issue description] — [Location in document] — [Suggested fix]
## Overpromise Flags
1. [Quoted text] → [Suggested alternative] — [Section]
## Legal Risk Flags
1. [Quoted text] → [Risk description] — [Recommended action]
## Consistency Issues
1. [Description of mismatch] — [Sections involved]
## Strengths
1. [What works well]
## Section-by-Section Notes
### [Section Name]
- [Specific feedback]
Save the review report to data/output/ with naming: review_<project_name>_<YYYYMMDD>.md
1---2name: proposal-reviewer-23description: Review technical project proposals for quality, overpromises, legal risk, and internal consistency. Use when the user asks to review, check, evaluate, or critique a project proposal, grant proposal, or any section thereof. Also use when asked to find overpromises, check for legally binding language, verify consistency between sections (objectives vs work packages vs deliverables vs budget), or assess proposal readiness for submission. Accepts proposals as docx, pdf, or plain text input.4---5
6# Technical Proposal Reviewer
7
8Review technical project proposals for quality, consistency, overpromises, and legal risk. Produce actionable feedback the author can use to improve the proposal.
9
10## Review Workflow
11
121. **Read the proposal** — Load the full document (use `docx` or `pdf` skill as needed)
132. **Assess structure** — Check all expected sections are present and properly ordered
143. **Check consistency** — Verify cross-references between objectives, WPs, deliverables, budget, and timeline
154. **Flag overpromises** — Identify language that oversells or makes unsupported claims
165. **Flag legal risk** — Identify language that could create binding obligations
176. **Evaluate content quality** — Assess depth, citations, and clarity per section
187. **Produce review report** — Structured feedback with severity levels
19
20## Review Dimensions
21
22### 1. Structural Completeness
23
24Check that the proposal contains all standard sections. Missing sections should be flagged.
25
26Expected sections (adapt to funding call):
27- Abstract/Executive Summary
28- State of the Art
29- Objectives
30- Methodology
31- Work Plan / Work Packages
32- Deliverables & Milestones
33- Timeline
34- Budget
35- Risk Management
36- Impact & Exploitation
37- References
38
39### 2. Internal Consistency
40
41Cross-check these mappings:
42
43| From | To | Check |
44|------|----|-------|
45| Objectives (O1..On) | Work Packages | Every objective covered by ≥1 WP |
46| Work Packages | Objectives | Every WP maps to ≥1 objective |
47| Tasks | Deliverables | Every deliverable traces to tasks |
48| Deliverables | Timeline | Due dates within WP duration |
49| Milestones | Timeline | Milestone dates on Gantt chart |
50| Budget (effort) | WP effort tables | Person-months match |
51| Partner roles | WP leads | Partners listed in WPs match consortium |
52
53### 3. Overpromise Detection
54
55Flag statements that claim more than the evidence supports:
56
57**Red flags:**
58- "Will achieve X" without feasibility evidence → suggest "Aims to achieve X"
59- Benchmark numbers stated as guaranteed outcomes → suggest framing as targets
60- Claims of "first ever", "unique", "revolutionary" without strong justification
61- Objectives that exceed project scope/budget/timeline
62- Impact claims disconnected from project outputs
63
64**Suggested replacement patterns:**
65
66| Overpromise | Suggested Alternative |
67|-------------|----------------------|
68| "will achieve 95% accuracy" | "targets 95% accuracy based on preliminary results showing 88%" |
69| "will revolutionize" | "has the potential to significantly advance" |
70| "guaranteed delivery" | "planned delivery, subject to milestone review" |
71| "unique solution" | "novel approach that differs from existing methods in [specific way]" |
72| "will solve the problem" | "addresses key aspects of the problem, specifically [X, Y]" |
73
74### 4. Legal Risk Assessment
75
76Flag language that could create enforceable obligations:
77
78**High risk:**
79- Unconditional commitments: "we will deliver", "we guarantee", "we commit to"
80- Quantitative guarantees without caveats: "system will process 1M records/sec"
81- IP transfer language without legal review
82- Data sharing commitments that may conflict with GDPR or institutional policy
83- Liability-implying language: "we accept responsibility for", "we ensure"
84
85**Recommended mitigations:**
86- Add "subject to" clauses for conditional commitments
87- Frame deliverables as "planned" rather than "guaranteed"
88- Add standard disclaimers for performance targets
89- Flag IP and data clauses for legal counsel review
90
91### 5. Content Quality
92
93Per-section quality assessment:
94
95| Section | Key Quality Criteria |
96|---------|---------------------|
97| Abstract | Self-contained, concise, compelling, no jargon |
98| State of the Art | Recent citations, fair comparison, clear gap statement |
99| Objectives | SMART criteria met, realistic scope |
100| Methodology | Concrete approach, justification over alternatives, feasibility |
101| Work Plan | Clear task breakdown, realistic effort, dependencies shown |
102| Impact | Concrete exploitation paths, quantified where possible |
103| Risks | Honest assessment, high-impact risks included, mitigations concrete |
104
105## Output Format
106
107Produce a structured review report:
108
109```
110# Proposal Review: [Project Title/Acronym]
111
112## Summary Assessment
113[2-3 sentence overall assessment]
114Overall readiness: [Ready / Needs Minor Revisions / Needs Major Revisions / Not Ready]
115
116## Critical Issues (must fix)
1171. [Issue description] — [Location in document] — [Suggested fix]
118
119## Major Issues (should fix)
1201. [Issue description] — [Location in document] — [Suggested fix]
121
122## Minor Issues (nice to fix)
1231. [Issue description] — [Location in document] — [Suggested fix]
124
125## Overpromise Flags
1261. [Quoted text] → [Suggested alternative] — [Section]
127
128## Legal Risk Flags
1291. [Quoted text] → [Risk description] — [Recommended action]
130
131## Consistency Issues
1321. [Description of mismatch] — [Sections involved]
133
134## Strengths
1351. [What works well]
136
137## Section-by-Section Notes
138### [Section Name]
139- [Specific feedback]
140```
141
142Save the review report to `data/output/` with naming: `review_<project_name>_<YYYYMMDD>.md`
majiayu000