pp-function-health
Every Function Health feature, plus a local SQLite store with biomarker trends across every round you've ever drawn Trigger phrases: `show me my function health labs`, `what's worst on my function panel`, `trend my apoB`, `make me a pdf for my doctor with my function history`, `what changed since my last function draw`, `use function-health`, `run function-health-pp-cli`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/other/function-health/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# Function Health — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `function-health-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer:
```bash
npx -y @mvanhorn/printing-press-library install function-health --cli-only
```
2. Verify: `function-health-pp-cli --version`
3. Ensure `$GOPATH/bin` (or `$HOME/go/bin`) is on `$PATH`.
If the `npx` install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish.
If `--version` reports "command not found" after install, the install step did not put the binary on `$PATH`. Do not proceed with skill commands until verification succeeds.
Function Health gives you a great single-round dashboard but no way to see what's drifting across years of draws — and no way to share a clean, branded lab history with your physician. function-health-pp-cli pulls every round into a local SQLite store with FTS5, exposes cross-round trend analysis nobody else offers (`goat`, `biomarker trend`, `biomarkers trending`, `biomarkers oscillating`), and renders a Function-branded PDF with your name and date of birth that an MD can read in 30 seconds.
## When to Use This CLI
Reach for function-health-pp-cli whenever an agent is asked to reason about lab trends over time, to prioritize which biomarker the user should worry about, or to produce an artifact a clinician will actually read. It is the right tool when the question requires joining data across multiple test rounds, when the user wants a branded PDF for a doctor, or when an agent needs a focused Markdown context block for one biomarker rather than the entire JSON export. It is the wrong tool for one-off single-result lookups on a draw that hasn't been synced yet — for those, run `sync` first or query the Function web app directly.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Doctor-ready outputs
- **`export pdf-for-doctor`** — Render a Function-branded multi-round lab report PDF with your name and date of birth, suitable for emailing to your personal physician.
_When an agent needs to produce something the user will hand to a third party, this is the durable artifact — not a JSON blob._
```bash
function-health-pp-cli export pdf-for-doctor --out ~/Downloads/function-history.pdf
```
### Local-SQL trend analysis
- **`biomarker trend`** — Every value of a biomarker across every round you've ever drawn, with the delta from Function's optimal range, an ASCII sparkline in the terminal, and structured JSON for agents.
_When the agent is asked 'how has X changed', this is the one query that answers it without re-fetching anything._
```bash
function-health-pp-cli biomarker trend ApoB --json
```
- **`goat`** — Ranks every biomarker by distance-from-optimal multiplied by its slope-away-from-optimal across the last 3 rounds; returns the single most worrying biomarker right now with reasoning fields.
_When the agent is asked 'what should I worry about', this is the one-call answer._
```bash
function-health-pp-cli goat --agent
```
- **`biomarkers trending`** — Lists every biomarker whose slope across the last N rounds points away from Function's optimal range, sorted by magnitude.
_Lets the agent prioritize a long biomarker list without burning the user's context window on every reading._
```bash
function-health-pp-cli biomarkers trending --direction worse --last 3 --json
```
- **`category trend`** — For one of the ~13 categories, returns a per-round aggregate score (percent of biomarkers inside Function's optimal range) over time.
_Rolls up 100+ biomarkers into a single trajectory per body system, so the agent can summarize organ-level changes._
```bash
function-health-pp-cli category trend cardiovascular --json
```
- **`biomarkers oscillating`** — Biomarkers that crossed the optimal-range boundary at least twice in the last N rounds — flags instability separate from trend.
_Distinguishes 'unstable measurement noise' from 'consistently bad' — important when the agent is reasoning about whether a single high reading matters._
```bash
function-health-pp-cli biomarkers oscillating --rounds 4
```
- **`recommendations stale`** — Recommendations (supplements / foods) whose target biomarker is STILL outside Function's optimal range, joined by Quest code. The /recommendations endpoint has no issued-date, so staleness is by outcome not age; --min-rounds tightens to persistence and --group (supplements, foods_to_eat, foods_to_avoid) focuses a large set.
_Closes the loop between guidance and outcome — the agent can ask 'did the last fix work?' instead of 'what is recommended now?'._
```bash
function-health-pp-cli recommendations stale --json
```
### Agent-native plumbing
- **`bundle`** — Composes a single Markdown file with a biomarker's full history, every clinician note mentioning it (FTS5), Function's optimal range, and relevant recommendations — ready to paste into Claude or ChatGPT.
_When the agent is being asked to draft a question for the user's clinician, this is the prefab context block._
```bash
function-health-pp-cli bundle ApoB --window 3rounds
```
## Command Reference
**biological_age** — Biological-age and BMI calculations Function derives from your panels.
- `function-health-pp-cli biological-age bio-age` — Your biological age vs. chronological age. 404 if not yet calculated.
- `function-health-pp-cli biological-age bmi` — BMI with the weight and height inputs Function recorded.
**biomarkers** — Function Health's full biomarker catalog with names, units, reference ranges, and Function's "optimal" ranges.
- `function-health-pp-cli biomarkers get` — Get one biomarker's full result history across every round you've drawn, with values, units, status, and ranges.
- `function-health-pp-cli biomarkers list` — List every biomarker the platform knows about (across all categories).
**categories** — The ~13 medical categories biomarkers are organized into (Heart, Hormones, Thyroid, Metabolic, Liver, Kidney, etc.).
- `function-health-pp-cli categories` — List every biomarker category with the biomarkers nested under it.
**notes** — Clinician notes attached to your results.
- `function-health-pp-cli notes` — List all clinician notes (annotations on biomarkers / rounds).
**notifications** — Change notifications (new results landing, biomarker direction changes).
- `function-health-pp-cli notifications` — Read all unread/read notifications about result changes.
**recommendations** — Personalized health recommendations tied to your results.
- `function-health-pp-cli recommendations` — Per-category health guidance. May 404 if Function hasn't computed any yet.
**requisitions** — Lab requisitions — pending (in-progress draws) and completed (rounds with results).
- `function-health-pp-cli requisitions completed` — Completed requisitions (your past test rounds, keyed by requisitionId).
- `function-health-pp-cli requisitions pending` — Currently in-progress requisitions (lab orders awaiting completion).
**results** — Lab results — both the structured bioRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.