# Skill reference Start with [Usage tiers](usage.md) to choose a workflow. This page is a lookup for individual tools; you do not need to learn them all. Commands below use Claude Code syntax. In Codex, replace `/mycelium-extra:` with `$mycelium-extra:`. In OpenCode, use the same `/mycelium-extra:` commands (`@grill` also works) and send `approve plan ` the same way; the plugin adapter handles it. See [Host compatibility](installation.md#host-compatibility). ## Common prompts | Need | Command | |---|---| | Make a plan | `/mycelium-extra:grill ` | | Enable execution checks | `/mycelium-extra:init` | | Check a completed run | `/mycelium-extra:verify ` | | Create an analysis folder | `/mycelium-extra:new-analysis analysis/: ` | | Resume in a fresh session | `/mycelium-extra:handoff` | | Park a passing idea | `/mycelium-extra:idea ` | | Choose the next idea | `/mycelium-extra:idea-triage` | ## grill Reads project evidence and turns your question into a sourced, numbered plan. It asks only consequential questions you own, at most five after the opening question. It calls `decision-status` and `data-contract-check` when needed. It writes nothing and runs no analysis. The brief ends with `READY`, `READY_WITH_ASSUMPTIONS`, or `DECISION_REQUIRED`. Its `Inputs:` line identifies files the gate will pin. With the gate enabled, use the displayed `approve plan ` message to authorize covered runs. See [Approving a plan](approval-gate.md#approving-a-plan). ## init Turns on the approval gate for the current repository. Writes `.mycelium-extra/gate.json` and adds `.mycelium-extra/` to `.gitignore`; leaves an existing gate unchanged. Default paths are `analysis/**` and `nbs/**`. See [Gate settings](approval-gate.md#settings) to change coverage. ## verify Checks an approved plan against receipts, pinned inputs, outputs, lint, and explicit claims. It never re-runs the analysis. Requires the approval gate for a current plan's report; `verify stale`, `status` and `runs` can read saved provenance without it. Other subcommands (`list`, `diff`, `multiplicity`, `explore`, and `--require-reportable`) are described in [Verification reference](verification.md); `stale`, `status`, `diff` and `runs` are in [Advanced features](advanced.md#verify-features). ### What the report shows Planned scripts and their run evidence, changed inputs, output attribution, lint findings, and whether declared claims match saved output cells. See [Report details](verification.md#what-the-report-shows). ### Status `CONFORMS` means the checked record agrees; `CONFORMS_WITH_GAPS` means evidence is missing; `DOES_NOT_CONFORM` means a blocking mismatch or failure was found. A missing check never counts as clean. See [Status details](verification.md#status). ### What it writes After confirmation, saves the frozen plan, receipts, output inventory, lint, environment records where available, and report under `/provenance/`. See [Provenance files](verification.md#what-it-writes). ## new-analysis Creates a new folder with numbered step stubs, a Snakefile, `run.sh`, an analysis doc, one `PLAN.md`, one `TRACKER.md`, and data/output/log/report locations. Refuses non-empty folders and missing link targets; stubs stop until implemented. Uses `.md` in Mycelium projects and `README.md` elsewhere. Writes only the new folder; Mycelium's `analyze` handles manifest and memory updates. See [Full project workflow](usage.md#tier-4-full-project-workflow). ## plan-review Challenges a grill draft before approval. In Claude Code or OpenCode, the host assembles a minimal packet for separate Codex engineering and Biomni biomedical critiques. Before anything leaves the machine it runs a pre-send check and asks you to type `send packet `; Biomni uses cloud credits. The check and the consent mechanics are in [Advanced features](advanced.md#plan-review-packets-and-consent). Missing reviewers are reported unavailable. Writes nothing and approves nothing (apart from the prepared packet folder the send route needs). Material revisions need a new approval. In Codex, this skill supplies the engineering critique only. See [Host compatibility](installation.md#host-compatibility) for reviewer requirements. ## decision-status Resolves which past Mycelium decision applies. Explicit supersession wins, then matching scope; contested choices go to you. After confirmation, appends a resolution to `.living/decisions.md` without editing old entries. Usually called by `grill` when a plan depends on prior decisions. ## data-contract-check Compares a plan's assumptions with CSV/TSV sample tables or H5AD `obs`. Checks columns, cohort levels/counts, unique units, complete pairs, and batch versus contrast nesting. Writes nothing. H5AD needs h5py; a missing dependency is a gap. Never loosens the contract to make a failed check pass without agreement. Usually called by `grill` when sample assumptions matter. ## handoff Writes a short root `HANDOFF.md` with the goal, current state, locked decisions, dead ends, code pointers, and one exact next action. Replaces the previous handoff and ends with a resume prompt. A grill plan still waiting for approval is carried word for word: `HANDOFF.md` points to the gate's stored copy (or holds the whole brief when there is none), and the new session prints it unchanged for a fresh approval card. Does not commit or change `.living/`. ## idea Parks a passing idea without a question, so the main work keeps its flow. Writes `todo/.md` and one `todo/TODO_REGISTRY.md` row (priority `idea`, status `open`) in Mycelium's todo format, then replies with one line. Uses your words as written. Writes only under `todo/`: no code runs, and a plan waiting for approval stays approvable. Mycelium's own `todo-idea` mode asks up to six questions first; `idea` is the no-question path into the same registry. ## idea-triage Ranks the open ideas in `todo/` so you can choose the next one. Each idea gets a pitch, two impact ratings, the number of things that must go right, its riskiest assumption (1 to 5) with months to test, a search of existing findings, and red flags; the top idea gets a cheapest go/no-go test. It shows a ranked table with a `park all` option and waits. After you pick, it records the triage in the item file and marks the pick `in-progress`; it offers `grill` but does not start it. Based on Fischbach and Walsh (2024), *Cell*. ## harden Turns one Mycelium learning's concrete mitigation candidate into a test in the repository's existing test setup. Demonstrates failure on a minimal reproduction and a pass on current code. After confirmation, marks the learning's mitigation as structural and records the test path. Leaves analysis code unchanged.