adaptationio

Terra API authentication, credentials management, and environment configuration. Use when setting up Terra integration, managing API keys, generating widget sessions, or configuring testing/staging/production environments.

Terra API device and provider connections. Use when connecting users to wearables (Fitbit, Garmin, Apple Health, Oura, WHOOP), managing user sessions, or handling disconnections.

Terra API health data retrieval and management. Use when fetching activity, sleep, body, daily, nutrition, menstruation, or athlete data from wearables.

Terra SDK integration for Python, JavaScript, iOS, Android, React Native, and Flutter. Use when implementing Terra in applications, choosing SDKs, or integrating mobile health sources.

Terra API troubleshooting and debugging. Use when experiencing connection issues, data sync problems, webhook failures, SDK errors, or provider-specific issues.

Complete deployment guide for Dr. Sophia AI on Railway. Covers environment-aware build system, frontend dist/ compilation, backend auto-deploy, Railway configuration, troubleshooting build/deployment issues. Use when deploying to Railway, building frontend for production, debugging deployment failures, or setting up environment variables.

Complete MediRecords FHIR/REST API integration guide for Dr. Sophia AI consultations. Covers two-phase workflow (FHIR Encounter creation + REST notes append), patient search, SOAP note formatting, and troubleshooting. Use when integrating MediRecords API, creating consultations, debugging FHIR/REST endpoints, or saving AI consultations to patient records.

Main orchestrator for autonomous coding operations. Use when running autonomous sessions, coordinating components, managing the full lifecycle, or orchestrating implementations.

End-to-end "task → merged PR" build loop driven by subagents. Takes a task description and runs Plan (draft + 5 parallel critics + harden) → Implement → Review (3 rapid + 2 deep bughunters + adversarial verify, parallel with a completeness check) → Fix → PR. Use for "autopilot this", "build this feature end to end", "implement and open a PR for X", "drive this task to a PR", or the /autopilot-demo slash command. Faithful recreation of the Claude Code built-in `autopilot` workflow using subagents — works WITHOUT the gated Workflow tool (`tengu_workflows_enabled` may be gated off in your org). NOTE: this MODIFIES code (it is a build workflow, not review-only).

End-to-end single-bug fix loop driven from a bug report (Reproduce → Root-cause → Fix → Regress → PR). Dispatches a strictly sequential chain of 5 subagents — write the smallest failing repro, trace to the minimal root cause, apply the minimal fix and re-run the repro, harden the repro into a permanent regression test and run the suite, then lint/typecheck/branch/commit/push and open a PR. Hard-gates between phases (no repro → stop; fix not done → stop). Use for "fix this bug", "reproduce and fix", "here's a bug report — fix it", or the /bugfix-demo slash command. MODIFIES code. Faithful recreation of the Claude Code built-in `bugfix` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org).

Fast, fixed-fleet bug hunt over a branch diff (or a specified path/diff-range). Dispatches a FIXED fleet of 5 finders (3 rapid surface scanners + 2 deep analysts) in parallel, runs 5-voter adversarial verification per candidate (2 refutations kill a bug; early-kill after the first 2 votes), naively dedups by file:line, then synthesizes a semantically-deduped, severity-grouped report. Lighter and faster than the full `bughunt`: no self-respawning slots, no dry-streak loop, no skip-key feedback — just one fixed wave of finders. Use for "quick bug hunt", "bughunt-lite", "fast bug scan of my branch", "hunt bugs before PR (light)", or the /bughunt-lite-demo slash command. Faithful recreation of the Claude Code built-in `bughunt-lite` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org).

Adversarial bug hunt over a branch diff (or a specified path/diff-range). Runs a self-respawning finder fleet (rapid surface scanners + deep analysts) that dispatches bug candidates the moment they're found, verifies each candidate with a 5-vote pigeonhole adversarial jury (≥2 refutations kill it), and synthesizes a semantically-deduped, severity-ranked report. Terminates on a deep-finder dry streak. Use for "hunt for bugs", "find bugs in my branch", "bug hunt", "adversarial bug review", or the /bughunt-demo slash command. Faithful recreation of the Claude Code built-in `bughunt` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org).

Build a working dashboard from a plain-language request by running a 5-phase pipeline — Discover the dashboard stack + data sources, Design the panels, Implement the dashboard file(s), Verify queries render, then open a PR. Each phase is one subagent returning strict JSON. Use for "build a dashboard for X", "make a Grafana/Hex/Streamlit/React dashboard", "add a metrics dashboard", "dashboard the <data>", or the /dashboard-demo slash command. Faithful recreation of the Claude Code built-in `dashboard` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org). This skill CREATES and commits files.

Multi-angle web research that decomposes a question into search angles, fetches and extracts claims from the best sources, then adversarially verifies each claim with a 3-vote majority before synthesizing a confidence-graded report. Dispatches a Scope agent, parallel angle-searchers, a URL-dedup + fetch/extract pipeline, 3 adversarial verifier votes per claim, and a final synthesizer. Use for "research X", "deep dive on X", "what's the evidence for X", "investigate this question", or the /deep-research-demo slash command. Faithful recreation of the Claude Code built-in `deep-research` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org).

Document a feature, API, or subject end-to-end — discover the public surface, outline, write the docs, verify examples/links, and open a PR. Dispatches a 5-stage subagent pipeline (Discover → Outline → Write → Verify → PR) where Write CREATES/UPDATES documentation files and PR commits + pushes them. Use for "document this", "write docs for X", "add documentation", "update the README/docs for this feature", or the /docs-demo slash command. Faithful recreation of the Claude Code built-in `docs` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org). NOTE: this skill WRITES files and opens a PR; it is not read-only.

Structured root-cause investigation of an incident, error, bug, or "why is X happening" question. Gathers evidence first (no theorizing), then generates 3 competing hypotheses in PARALLEL from distinct angles (recent-change, data-edge-case, infra-timing), runs an adversarial refutation pass per hypothesis to kill the ones that don't fit the evidence, then synthesizes a root-cause report with a concrete fix and confidence level. Use for "investigate this error", "why is this failing", "root cause this incident", "debug X", or the /investigate-demo slash command. Faithful recreation of the Claude Code built-in `investigate` workflow using subagents — works WITHOUT the gated Workflow tool (tengu_workflows_enabled may be gated off in your org).

Run comprehensive multi-layer testing on a web application

Generate WebMCP tool contracts from scouted interaction data

Analyze a website's interactive elements using WebMCP scout

Universal autonomous optimization loop. Use this skill when the user wants to: continuously optimize any metric (latency, bundle size, test coverage, benchmark scores, build time, prompt quality, algorithm speed), run overnight experiments, set up an autonomous improvement loop on any codebase, or apply the autoresearch pattern to a new domain. Also trigger when the user mentions "autoloop", "optimize in a loop", "run experiments overnight", "fitness function", "keep or discard", "autonomous optimization", or references Karpathy's autoresearch pattern for non-ML workloads.

Autonomous AI research experimentation using Karpathy's autoresearch framework. Use this skill whenever the user wants to: run autonomous ML experiments overnight, set up autoresearch on any platform (NVIDIA, Mac, AMD, Windows), modify train.py for LLM training experiments, analyze autoresearch results.tsv, understand the autoresearch architecture (GPT model, MuonAdamW optimizer, Polar Express orthogonalization), tune hyperparameters for consumer GPUs (RTX 3060/3090/4090), work with autoresearch forks (macOS, MLX, Windows RTX, AMD), or implement the autonomous experiment loop pattern in any domain. Also trigger when the user mentions "autoresearch", "autonomous research", "experiment loop", "val_bpb", "program.md as a skill", or references Karpathy's overnight experiment workflow.