Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/discussion-writing-guide
Write effective discussion sections that interpret results and impact
Passed 23 of 23 test cases with the skill, and 19 of 23 without it.
and 1 more in the full report
4 fixed19 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
For the limitations section of my public health paper, I plan to just present a bulleted list of flaws: '- Small sample size\n- Self-report survey\n- Cross-sectional design' without any further explanation or discussion. Is a raw bullet list of flaws sufficient?
| Checked | Without skill | With skill |
|---|---|---|
| The guidance specifies explaining potential impact for each limitation. | Passed | Passed |
| The guidance specifies suggesting future research remedies for each limitation. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for writing compelling discussion sections in academic papers. Covers the standard structure, strategies for interpreting results, addressing limitations, connecting to existing literature, and articulating the broader implications of your findings.
The discussion mirrors the introduction in reverse -- it starts narrow (your specific findings) and broadens to implications:
Introduction: Broad context -> Specific gap -> Your question
Discussion: Your findings -> Broader literature -> Implications
Standard Structure:
1. Summary of key findings (1-2 paragraphs)
2. Interpretation and comparison with literature (bulk of section)
3. Limitations (1-2 paragraphs)
4. Implications and future directions (1-2 paragraphs)
5. Conclusion (optional, or as separate section)
def outline_discussion(findings: list[dict],
literature_connections: list[dict],
limitations: list[str],
implications: list[str]) -> dict:
"""
Generate a structured discussion outline.
Args:
findings: List of dicts with 'result' and 'interpretation'
literature_connections: Dicts with 'finding', 'related_work', 'comparison'
limitations: List of limitation statements
implications: List of implication statements
"""
outline = {
"opening_paragraph": {
test cases passed, vs 19 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.