emem

selfhost-emem-guard

crates/emem-guard/SKILL.md

Stand up an emem-guard verdict server, verify it against the conformance checks, and point any agent at it. Use when asked to self-host emem-guard, add a grounding gate to an agent on any model or framework, wire a checkpoint into Claude Code or Claude Enterprise or MCP, or run a signed allow/deny server for physical-world claims.

emem-device-traces

plugins/emem/skills/emem-device-traces/SKILL.md

Reads and checks the signed activity records (OS traces) emem holds for devices such as robots, drones, satellites and sensor hosts. Lists enrolled devices and their assurance tier, resolves an emem:trace token to its signed OS trace, re-verifies the trace (segment chain, clocks, required layers, output binding, device signature), and reads the platform registry to say which hardware roots of trust are actually admitted. Use when a fact or claim is said to come from a device, when an agent receives an emem:trace or emem:attestation token, or when someone asks whether a robot or satellite can prove what it ran. Read-only: it sends and receives JSON, runs nothing it receives, and states plainly what is roadmap.

emem-document-evidence

plugins/emem/skills/emem-document-evidence/SKILL.md

Turns a scanned document into signed, checkable evidence with emem. Runs OCR on an image, then parses a pesticide-residue lab report (analytes, results in mg/kg, LOQ, printed MRL, exceedances) or a land record (owners, parcel ids, areas in hectares, places, dates), with every value tied to its line and byte offset and every step signed. Use when an agent must extract fields from a lab certificate, a 7/12 extract, a khasra or a CAR record and hand them on with proof of which image and text they came from. Ships an offline verifier.

emem-eudr-due-diligence

plugins/emem/skills/emem-eudr-due-diligence/SKILL.md

Produces a signed, Annex II shaped Due Diligence Statement under the EU Deforestation Regulation (EU 2023/1115) for one or more production plots with emem, and explains what it proves and what it leaves to the operator. Checks each plot against the JRC GFC2020 forest baseline and Hansen Global Forest Change loss year at the 2020-12-31 cut-off, cross-checks JRC TMF, and grades how well the inputs support the verdict. Use when a supplier, importer or auditor asks whether a cocoa, coffee, soy, palm, rubber, cattle or wood plot is deforestation-free, or needs per-cell evidence for an Article 12 record.

emem-field-signals

plugins/emem/skills/emem-field-signals/SKILL.md

Answers agronomy questions about one farm field with signed evidence from emem. Gets the field's boundary polygons, checks for crop-residue burning over a date window (Sentinel-2 NBR and NDTI plus MODIS burned area), sums actual evapotranspiration over a season (MODIS MOD16), and fetches a true-colour Sentinel-2 picture of the plot. Use when the user asks whether a field was burned, how much water a crop used, what a plot looks like, or where the field edges are, and wants per-cell fact ids behind the answer.

emem-field-tokens

plugins/emem/skills/emem-field-tokens/SKILL.md

Fetches a native-resolution raster field over an area from emem, or the same field over several dates, as a signed and re-derivable artifact rather than a set of per-cell scalars. Use when the user needs the actual grid of values over an area of interest (a world-model input, a band or NDVI drape, change analysis over a scene window, pixels a third party can re-hash) rather than one number at one point. Returns content-addressed grid artifacts, a signed derivation record, and an emem:raster, emem:cube or emem:rasterset token. Reads need no key.

emem-find-similar

plugins/emem/skills/emem-find-similar/SKILL.md

Returns the top-K places most similar to a seed place by cosine over a stored 128-D surface-texture embedding (Sentinel-1 plus Sentinel-2, annual). Use when the user asks for analogues or look-alikes ("find places like Bangalore", "where else looks like the Sundarbans"). The embedding band is retired on emem.dev, so the index is frozen at what was already stored; the skill says how to tell "no analogue" from "this seed has no vector and cannot get one".

emem-locate-and-recall

plugins/emem/skills/emem-locate-and-recall/SKILL.md

Resolves a place name to an emem cell64 address and recalls signed Earth-observation facts there (weather, vegetation indices, elevation, soil, land cover, surface water, forest change). Use when the user asks for a measurable value at a named place ("what is the temperature in Bengaluru", "how high is Denali", "what is the NDVI in the Sundarbans") and wants an answer another agent can verify offline. Returns content-addressed facts, a ready-made emem:fact citation token for each, and an Ed25519 receipt. Reads need no key.

emem-long-horizon-memory

plugins/emem/skills/emem-long-horizon-memory/SKILL.md

Keeps an agent's working state in signed emem notes that outlive its context window, so a later session, or the same agent after a reset, picks up from bytes it can verify rather than from a summary it has to believe. Writes and edits notes in the agent's own namespace (emem_memory_create, str_replace, supersede), re-reads them by path or by content id, checks the inbox for notes other agents addressed to it, waits for a new one, and states what survives a reset and what does not. Use for work that spans days or sessions, for checkpointing a long task before a context reset or compaction, or for resuming a task another session started.

emem-multi-agent-handoff

plugins/emem/skills/emem-multi-agent-handoff/SKILL.md

Hands work between agents so it arrives as checkable evidence rather than prose someone has to trust, and checks what other agents hand back. Picks the citation token that binds what matters, composes several readings into one signed bundle, verifies offline which key wrote a memory note and reads that key's own card, seals a note so only one key can read it, and joins the agent-to-agent standard that runs on emem's signed ledger. Use at any trust boundary between agents, such as a multi-agent pipeline, publishing findings another team will build on, or receiving a token or memory path from a stranger. No shared database, account or out-of-band key exchange. Ships an offline authorship verifier and a sealed-note tool.

emem-recall-polygon

plugins/emem/skills/emem-recall-polygon/SKILL.md

Recalls signed Earth-observation facts at sampled cells inside an area (a named region, a bounding box, or a GeoJSON boundary) in one call. Use when the user asks about an extent rather than a point, such as "average NDVI inside this watershed", "precipitation across the Western Ghats", or "elevation across this admin boundary". Returns per-cell facts, each cell with its own Ed25519 receipt, plus the sampling it actually did so the agent can state coverage honestly.

emem-referential-drift

plugins/emem/skills/emem-referential-drift/SKILL.md

Stops two agents, or one agent across two sessions, from reporting different numbers for the same reading. Pins a value to a citation token another party resolves to byte-identical signed bytes, grades a value about to be said against what was signed, asks why a number moved when the words held, and finds where the corpus disagrees with itself. Use when a figure is carried between contexts, when two sources report different values for one place, when a number changed and nobody can say what changed, or before publishing a number the agent did not read from a token in this turn.

emem-research-grade-citation

plugins/emem/skills/emem-research-grade-citation/SKILL.md

Prepares emem facts for use in research, where a reviewer needs to know exactly what a number is, how it was read, and how to reproduce it. States the estimand each fact leaves implicit (support, statistic, source pixel), reads units, the valid range enforced at signing, the reader stamp and pinned source, explains the stated ULP window on derived means and sums and what change_attribution does and does not split, and writes a methods paragraph and data-availability statement with verifiable tokens. Use when citing emem values in a paper, report, thesis or dataset, when a reviewer asks how a figure was obtained, or before comparing emem values with another dataset.

emem-shared-identity

plugins/emem/skills/emem-shared-identity/SKILL.md

Makes two agents refer to the same object. Finds an existing canonical identity for a thing (a field, a corridor, an asset, a place treated as an object) from a fuzzy phrasing, attests that two phrasings denote one object, or mints a new identity when none exists. Use when several agents or documents call one thing by different names and the disagreement is about words rather than measurements, or before handing another agent a finding it must be able to look up. Reads are open; writing to the shared identity space needs a key and tier T3.

emem-sign-and-attest

plugins/emem/skills/emem-sign-and-attest/SKILL.md

Writes to emem with the agent's own Ed25519 key, either a signed note in its namespace that other agents can verify it wrote, or a derivation over signed facts that the responder recomputes. Use when the user wants to record something durably and verifiably, hand a finding to another agent with proof of authorship, or publish a computed value with its lineage. There is no registration and no API key; the key is held by the optional emem-signer plugin, never by this one, and the signer computes the digest of the write the agent composed, so no refusal round trip is needed. The responder's refusal names the same digest, which serves as a cross-check.

emem-tokenise-files

plugins/emem/skills/emem-tokenise-files/SKILL.md

Turns a file into signed, resolvable tokens with emem. Cuts the file into units (markdown sections, or byte ranges), commits every unit's BLAKE3 under one Merkle root in a pointer.v1 index note the agent signs with its own key, and hands out emem:tree tokens that name the whole file or one unit. Resolves a unit's audit path from GET /v1/tree and proves it offline, including against the bytes of the source. Use when an agent must cite one section, page or tensor of a large file without shipping the file, prove later that a unit was part of a document as published, or hand a document to another agent as checkable parts. Ships an offline builder and checker.

emem-transparency-log

plugins/emem/skills/emem-transparency-log/SKILL.md

Audits emem's append-only RFC 6962 transparency log offline. Verifies a signed tree head, proves a log entry or a memory note is committed under it, proves a later head extends an earlier one without rewriting history, and reads which independent witnesses countersigned. Use when the question is not "is this fact signed" but "could this responder have shown someone else a different history", when pinning evidence for an audit, or before relying on a note whose deletion or rewrite would matter. Ships a small Python verifier.

emem-urban

plugins/emem/skills/emem-urban/SKILL.md

Answers urban-analysis questions with signed emem facts and says what each number measures. Covers Overture buildings, places, road length and road bearing, WorldPop population density, the Sentinel-2 built-up index (NDBI), ESA WorldCover built-up class, JRC surface-water recurrence and DMSP night lights, with each band's source, release, resolution and failure modes. Use when the user asks how built-up, dense, connected or lit a neighbourhood is, compares districts, or needs street and building evidence another agent can verify, and when an area total must be estimated from sampled cells honestly.

emem-verify-before-publish

plugins/emem/skills/emem-verify-before-publish/SKILL.md

Checks a draft before it is sent. Finds every emem citation in the text, confirms each resolves and verifies, checks the number written next to each citation against the signed value, and optionally flags measurable claims that carry no citation, returning allow or deny with a machine-readable reason. Use before publishing any answer that cites emem, before handing a report to a user or another agent, and whenever a number in the draft came from earlier in the conversation rather than from a token resolved just now.

emem-verify-receipt

plugins/emem/skills/emem-verify-receipt/SKILL.md

Verifies an emem receipt's Ed25519 signature offline by rebuilding its canonical BLAKE3 preimage (v1 or v2) and checking it against the responder's published key. Use when the user pastes a receipt or an emem response and asks whether it is authentic, when an agent must prove a fact was not fabricated, or when checking a cached answer later without trusting or re-contacting the responder. Ships a small Python verifier; a server-side check is the fallback.