Source: https://github.com/aipoch/medical-research-skills
Biotech Pitch Deck Narrative
Structured biotech fundraising narrative design with explicit scope limits.
When to Use
- Use this skill when the task needs a biotech pitch narrative, investor-facing section rewrite, or fundraising story structure grounded in available scientific and business inputs.
- Use this skill for academic writing tasks that require explicit assumptions, bounded scope, and a reproducible output format.
- Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.
Key Features
- Scope-focused workflow aligned to: Use biotech-pitch-deck-narrative for academic writing workflows that need structured investor-facing storytelling, explicit assumptions, and clear output boundaries.
- Packaged executable path(s):
scripts/main.py.
- Reference material available in
references/ for task-specific guidance.
- Structured execution path designed to keep outputs consistent and reviewable.
Dependencies
See ## Prerequisites above for related details.
Python: 3.10+. Repository baseline for current packaged skills.
dataclasses: unspecified. Declared in requirements.txt.
enum: unspecified. Declared in requirements.txt.
Example Usage
cd "20260318/scientific-skills/Academic Writing/biotech-pitch-deck-narrative"
python -m py_compile scripts/main.py
python scripts/main.py --help
Example run plan:
- Confirm the user input, output path, and any required config values.
- Edit the in-file
CONFIG block or documented parameters if the script uses fixed settings.
- Run
python scripts/main.py with the validated inputs.
- Review the generated output and return the final artifact with any assumptions called out.
Implementation Details
See ## Workflow above for related details.
- Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
- Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
- Primary implementation surface:
scripts/main.py.
- Reference guidance:
references/ contains supporting rules, prompts, or checklists.
- Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
- Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.
Quick Check
Use this command to verify that the packaged script entry point can be parsed before deeper execution.
python -m py_compile scripts/main.py
Audit-Ready Commands
Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.
python -m py_compile scripts/main.py
python scripts/main.py --help
Workflow
- Confirm the financing stage, investor audience, available evidence, and non-negotiable claim boundaries.
- Check whether the request is for a full narrative, a single section rewrite, or high-level messaging guidance.
- Use the packaged script for supported stage and audience framing; otherwise provide a manual narrative scaffold without inventing data.
- Return a structured deck narrative that separates assumptions, value claims, evidence status, and open diligence gaps.
- If scientific support or market context is missing, stop and request the minimum additional inputs.
Use Cases
- Seed deck messaging for platform biotech companies
- Rewriting a science-heavy section for generalist investors
- Preparing a risk-aware investor Q&A scaffold
Parameters
| Parameter |
Type |
Required |
Default |
Description |
--stage |
string |
No |
seed |
Financing stage (pre-seed, seed, series-a, series-b, series-c, ipo) |
--audience |
string |
No |
generalist-vc |
Target investor audience |
--input |
string |
No |
- |
Input deck or source file path |
--output |
string |
No |
optimized_narrative.json |
Output file path |
Returns
- Investor-facing narrative scaffold
- Stage- and audience-aware positioning cues
- Explicit note where evidence is missing or claims require validation
Example
python scripts/main.py --stage series-a --audience biotech-specialist
Risk Assessment
| Risk Indicator |
Assessment |
Level |
| Code Execution |
Local Python script execution only |
Medium |
| Network Access |
No external API calls |
Low |
| File System Access |
Optional local file input and JSON output |
Medium |
| Instruction Tampering |
Standard prompt-guided workflow |
Low |
| Data Exposure |
Sensitive fundraising content remains in workspace |
Medium |
Security Checklist
Prerequisites
No additional Python packages required for the packaged entry point.
Evaluation Criteria
Success Metrics
Test Cases
- Basic Functionality: Help output and script parse succeed
- Edge Case: Missing evidence triggers bounded fallback
- Output Quality: Claims, risks, and diligence gaps stay clearly separated
Lifecycle Status
- Current Stage: Draft
- Next Review Date: 2026-03-20
- Known Issues: Live market validation and competitive diligence still require external review
- Planned Improvements:
- Safer section-level examples for audit coverage
- More explicit investor Q&A output modes
Output Requirements
Every final response should make these items explicit when they are relevant:
- Objective or requested deliverable
- Inputs used and assumptions introduced
- Workflow or decision path
- Core result, recommendation, or artifact
- Constraints, risks, caveats, or validation needs
- Unresolved items and next-step checks
Error Handling
- If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
- If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
- If
scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
- Do not fabricate files, citations, data, search results, or execution outcomes.
Input Validation
This skill accepts requests that match the documented purpose of biotech-pitch-deck-narrative and include enough context to complete the workflow safely.
Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:
biotech-pitch-deck-narrative only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.
References
- references/audit-reference.md - Supported scope, audit commands, and fallback boundaries
Response Template
Use the following fixed structure for non-trivial requests:
- Objective
- Inputs Received
- Assumptions
- Workflow
- Deliverable
- Risks and Limits
- Next Checks
If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.
1---2name: biotech-pitch-deck-narrative3description: Use biotech-pitch-deck-narrative for academic writing workflows that need structured investor-facing storytelling, explicit assumptions, and clear output boundaries.4license: MIT5---6> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
7
8# Biotech Pitch Deck Narrative
9
10Structured biotech fundraising narrative design with explicit scope limits.
11
12## When to Use
13
14- Use this skill when the task needs a biotech pitch narrative, investor-facing section rewrite, or fundraising story structure grounded in available scientific and business inputs.
15- Use this skill for academic writing tasks that require explicit assumptions, bounded scope, and a reproducible output format.
16- Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.
17
18## Key Features
19
20- Scope-focused workflow aligned to: Use biotech-pitch-deck-narrative for academic writing workflows that need structured investor-facing storytelling, explicit assumptions, and clear output boundaries.
21- Packaged executable path(s): `scripts/main.py`.
22- Reference material available in `references/` for task-specific guidance.
23- Structured execution path designed to keep outputs consistent and reviewable.
24
25## Dependencies
26
27See `## Prerequisites` above for related details.
28
29- `Python`: `3.10+`. Repository baseline for current packaged skills.
30- `dataclasses`: `unspecified`. Declared in `requirements.txt`.
31- `enum`: `unspecified`. Declared in `requirements.txt`.
32
33## Example Usage
34
35```bash
36cd "20260318/scientific-skills/Academic Writing/biotech-pitch-deck-narrative"
37python -m py_compile scripts/main.py
38python scripts/main.py --help
39```
40
41Example run plan:
421. Confirm the user input, output path, and any required config values.
432. Edit the in-file `CONFIG` block or documented parameters if the script uses fixed settings.
443. Run `python scripts/main.py` with the validated inputs.
454. Review the generated output and return the final artifact with any assumptions called out.
46
47## Implementation Details
48
49See `## Workflow` above for related details.
50
51- Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
52- Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
53- Primary implementation surface: `scripts/main.py`.
54- Reference guidance: `references/` contains supporting rules, prompts, or checklists.
55- Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
56- Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.
57
58## Quick Check
59
60Use this command to verify that the packaged script entry point can be parsed before deeper execution.
61
62```bash
63python -m py_compile scripts/main.py
64```
65
66## Audit-Ready Commands
67
68Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.
69
70```bash
71python -m py_compile scripts/main.py
72python scripts/main.py --help
73```
74
75## Workflow
76
771. Confirm the financing stage, investor audience, available evidence, and non-negotiable claim boundaries.
782. Check whether the request is for a full narrative, a single section rewrite, or high-level messaging guidance.
793. Use the packaged script for supported stage and audience framing; otherwise provide a manual narrative scaffold without inventing data.
804. Return a structured deck narrative that separates assumptions, value claims, evidence status, and open diligence gaps.
815. If scientific support or market context is missing, stop and request the minimum additional inputs.
82
83## Use Cases
84
85- Seed deck messaging for platform biotech companies
86- Rewriting a science-heavy section for generalist investors
87- Preparing a risk-aware investor Q&A scaffold
88
89## Parameters
90
91| Parameter | Type | Required | Default | Description |
92|-----------|------|----------|---------|-------------|
93| `--stage` | string | No | `seed` | Financing stage (`pre-seed`, `seed`, `series-a`, `series-b`, `series-c`, `ipo`) |
94| `--audience` | string | No | `generalist-vc` | Target investor audience |
95| `--input` | string | No | - | Input deck or source file path |
96| `--output` | string | No | `optimized_narrative.json` | Output file path |
97
98## Returns
99
100- Investor-facing narrative scaffold
101- Stage- and audience-aware positioning cues
102- Explicit note where evidence is missing or claims require validation
103
104## Example
105
106`python scripts/main.py --stage series-a --audience biotech-specialist`
107
108## Risk Assessment
109
110| Risk Indicator | Assessment | Level |
111|----------------|------------|-------|
112| Code Execution | Local Python script execution only | Medium |
113| Network Access | No external API calls | Low |
114| File System Access | Optional local file input and JSON output | Medium |
115| Instruction Tampering | Standard prompt-guided workflow | Low |
116| Data Exposure | Sensitive fundraising content remains in workspace | Medium |
117
118## Security Checklist
119
120- [ ] No hardcoded credentials or API keys
121- [ ] No unauthorized file system access (`../`)
122- [ ] Claims are tied to supplied evidence, not invented data
123- [ ] Regulatory and clinical statements remain bounded
124- [ ] Output path reviewed before overwrite
125- [ ] Error handling does not imply completed diligence
126- [ ] Market-sizing claims require user-supplied assumptions
127- [ ] Legal and scientific review remains mandatory
128
129## Prerequisites
130
131No additional Python packages required for the packaged entry point.
132
133## Evaluation Criteria
134
135### Success Metrics
136- [ ] Script path parses successfully
137- [ ] Help output documents supported framing options
138- [ ] Narrative remains within supplied scientific and commercial evidence
139- [ ] Missing data triggers explicit assumption or stop conditions
140
141### Test Cases
1421. **Basic Functionality**: Help output and script parse succeed
1432. **Edge Case**: Missing evidence triggers bounded fallback
1443. **Output Quality**: Claims, risks, and diligence gaps stay clearly separated
145
146## Lifecycle Status
147
148- **Current Stage**: Draft
149- **Next Review Date**: 2026-03-20
150- **Known Issues**: Live market validation and competitive diligence still require external review
151- **Planned Improvements**:
152 - Safer section-level examples for audit coverage
153 - More explicit investor Q&A output modes
154
155## Output Requirements
156
157Every final response should make these items explicit when they are relevant:
158
159- Objective or requested deliverable
160- Inputs used and assumptions introduced
161- Workflow or decision path
162- Core result, recommendation, or artifact
163- Constraints, risks, caveats, or validation needs
164- Unresolved items and next-step checks
165
166## Error Handling
167
168- If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
169- If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
170- If `scripts/main.py` fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
171- Do not fabricate files, citations, data, search results, or execution outcomes.
172
173## Input Validation
174
175This skill accepts requests that match the documented purpose of `biotech-pitch-deck-narrative` and include enough context to complete the workflow safely.
176
177Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:
178
179> `biotech-pitch-deck-narrative` only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.
180
181## References
182
183- [references/audit-reference.md](references/audit-reference.md) - Supported scope, audit commands, and fallback boundaries
184
185## Response Template
186
187Use the following fixed structure for non-trivial requests:
188
1891. Objective
1902. Inputs Received
1913. Assumptions
1924. Workflow
1935. Deliverable
1946. Risks and Limits
1957. Next Checks
196
197If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.