sajor2000/methodsmith / plugins/methodsmith/skills/method-power
method-power
VerifiedCalculates sample size and power for clinical, survival, cluster, and prediction-model studies, with a script, sweep, and SAP text. Use when the user asks for power or sample size.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.9 KB |
| references/evidence-access.md | markdown | 2.2 KB |
| references/formula-cheatsheet.md | markdown | 8.2 KB |
| references/sensitivity-sweep-template.R | other | 2.3 KB |
| references/sensitivity-sweep-template.py | script | 2.3 KB |
| scripts/pmsampsize_runner.R | other | 6.3 KB |
references/evidence-access.md
View on GitHub# Evidence access
Use connected MCP servers for literature; never invent a citation, effect size, or guideline item.
- **PubMed MCP** (canonical biomedical metadata). Call by purpose; two servers are common, so match the name on whichever is connected: search (`pubmed_search_articles` or `search_articles`), metadata by PMID (`pubmed_fetch_articles` or `get_article_metadata`), partial reference to PMID (`pubmed_lookup_citation` or `lookup_article_by_citation`), PMID/PMCID/DOI conversion (`pubmed_convert_ids` or `convert_article_ids`), related papers (`pubmed_find_related` or `find_related_articles`), full text (`pubmed_fetch_fulltext`, or `get_copyright_status` then `get_full_text_article` for open PMC). The documented default server (`@cyanheads/pubmed-mcp-server`) also offers `pubmed_lookup_mesh`, `pubmed_spell_check`, `pubmed_europepmc_search`, and `pubmed_format_citations` (a display check, never a substitute for a reference-manager field). Tool names carry the harness's server prefix; with the documented default server in Claude Code they are `mcp__pubmed-mcp-server__pubmed_search_articles`, `mcp__pubmed-mcp-server__pubmed_fetch_articles`, and so on.
- **Paperclip MCP** (full text across papers, preprints, trials, FDA documents): `search` with an explicit `source` (for example `pmc`), `lookup` by DOI/PMID/PMCID, then `cat`, `grep`, `scan`, `map`, or `filter` on the result, and `ask-image` for figures. In Claude Code these are `mcp__paperclip__search`, `mcp__paperclip__lookup`, and so on. The authenticated `paperclip` CLI is the fallback; neither is required.
- **Fallbacks:** without PubMed MCP (or when its calls error), load the `method-pubmed` skill, which owns the NCBI E-utilities fallback; without Paperclip, continue PubMed-only and state the full-text limitation.
- **Rules:** no PHI, patient-level values, or small-cell counts in any query; a search hit is not evidence until the source is read; label every claim at the level read (`abstract`, `full_text`, `figure`, `trial`, `regulatory`, `documentation`); keep PMID/PMCID/DOI, the query string, and the date as provenance; cite PubMed and include DOIs whenever PMC full text is used; lawful full-text access only.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |