biotech-pitch-deck-narrative
Use biotech-pitch-deck-narrative for academic writing workflows that need structured investor-facing storytelling, explicit assumptions, and clear output boundaries.
49
37%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/biotech-pitch-deck-narrative/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description fails to specify what the skill concretely does — it provides no actionable capabilities like 'creates slide narratives', 'structures data stories', or 'generates pitch deck outlines'. The confusing framing of 'academic writing workflows' combined with 'investor-facing storytelling' creates an identity crisis that would make skill selection unreliable. While it has a 'Use when' structure, the trigger conditions are contradictory and the lack of concrete actions significantly weakens its utility.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Generates narrative slide content for biotech pitch decks, structures scientific data into investor-friendly storylines, and outlines key assumptions for fundraising presentations.'
Clarify the confusing relationship between 'academic writing workflows' and 'investor-facing storytelling' — these seem contradictory and would cause selection confusion. Pick the primary use case or explain the bridge between them.
Expand trigger terms to include natural user phrases like 'fundraising deck', 'VC pitch', 'biotech presentation', 'startup narrative', or 'investor slides'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions. It mentions 'structured investor-facing storytelling, explicit assumptions, and clear output boundaries' but doesn't specify what the skill actually does (e.g., create slides, generate narratives, format decks). The actions are abstract rather than concrete. | 1 / 3 |
Completeness | It has a 'Use when' clause ('academic writing workflows that need structured investor-facing storytelling'), but the 'what does this do' part is very weak — it doesn't clearly describe the skill's capabilities or outputs. The 'when' guidance is present but oddly specific to 'academic writing workflows' which seems contradictory with 'investor-facing storytelling'. | 2 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'biotech', 'pitch deck', 'investor-facing', and 'academic writing', but misses common natural variations users might say such as 'fundraising deck', 'VC presentation', 'startup pitch', 'Series A', or specific biotech terms like 'clinical trials' or 'drug pipeline'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'biotech' and 'pitch deck' provides some distinctiveness, but the mention of 'academic writing workflows' creates confusion and potential overlap with academic writing skills. The scope is unclear enough that it could conflict with general presentation or writing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered with extensive boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that consume tokens without adding actionable value. The core task—constructing biotech pitch deck narratives—lacks concrete examples of actual narrative output, input formats, or specific storytelling frameworks. The repetition of commands and cross-references to nearby sections adds clutter without clarity.
Suggestions
Cut the file by at least 60%: remove or externalize Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, and deduplicate the repeated py_compile commands into a single Quick Check section.
Add a concrete input/output example showing what a biotech pitch narrative actually looks like—e.g., sample input evidence and the resulting narrative scaffold with assumptions marked.
Consolidate the two overlapping workflows (Example Usage run plan and Workflow section) into a single, clearly sequenced workflow with explicit validation checkpoints.
Move boilerplate sections (Security Checklist, Evaluation Criteria, Lifecycle Status) into a separate reference file and link to it, keeping SKILL.md focused on actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Multiple sections restate the same information (e.g., 'python -m py_compile scripts/main.py' appears 3 times, 'Quick Check' and 'Audit-Ready Commands' are nearly identical). Cross-references like 'See ## Prerequisites above' and 'See ## Workflow above' point to sections that add little value. Much of the content (Risk Assessment tables, Security Checklists, Lifecycle Status, Evaluation Criteria) is boilerplate that doesn't help Claude execute the task. The skill could be cut to less than a third of its length. | 1 / 3 |
Actionability | There are some concrete commands (python scripts/main.py --stage series-a --audience biotech-specialist) and a parameter table, but the core workflow steps are vague ('Use the packaged script for supported stage and audience framing; otherwise provide a manual narrative scaffold without inventing data'). The actual narrative construction guidance is abstract rather than showing concrete examples of input/output or specific narrative structures. | 2 / 3 |
Workflow Clarity | The Workflow section has a reasonable 5-step sequence with a stop condition (step 5), and Error Handling covers fallback paths. However, there are no explicit validation checkpoints between steps, and the workflow lacks concrete verification of outputs. The 'Example run plan' in Example Usage is a separate 4-step workflow that partially overlaps, creating confusion about which workflow to follow. | 2 / 3 |
Progressive Disclosure | There is a reference to 'references/audit-reference.md' and mention of 'references/' directory, which is good. However, the main file itself is a monolithic wall of text with many sections that could be externalized (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status). The document has too many sections inline that dilute the core actionable content. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
8277276
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.