Research

Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" ...

Research-brief + claim-record discipline for delegated or AI-assisted research work. Use when starting any substantive research task or long autonomous run (write the brief first), and when reporting results that will support a claim in a paper or decision (produce the claim record). Keeps faster execution from being confused with credible evidence.

Stress-test a finding against the choices you did not make. Enumerates the discrete forks a competent analyst could have taken (measure definition, sample filter, control set, clustering level, weighting, functional form), runs the specification grid, and reports the distribution rather than a point estimate — then attacks the identifying assumption with named, computable sensitivity statistics. Use when the user says "is this robust", "challenge this result", "specification curve", "multiver...

Before and after changing anything shared — a function's return value, a signature, a schema, a label set, a config default, a constant, a file format — find every consumer and actually run them. Catches the change that looks purely additive but silently breaks a contract in a file you never opened. Use when editing shared code, adding a field/column/return element, renaming, changing units or defaults, or touching a pipeline that produces reported numbers.

Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.

Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review. Coordinates food-science databases, preprints, semantic search, and food-safety/regulatory sources; runs a four-layer search, two-phase screening, and cross-source synthesis via subagents;...

General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review (APA 7.0 by default, or a target journal's style) and polish it through an editorial + integrity review loop. Use standalone for a deep dive or literature review, or as the deep-dive engine called ...

Creates research-backed user personas with JTBD, pain points, gains, and unexpected behavioral insights. Use when building personas from survey or interview data, or segmenting users to inform product decisions. Triggers on: user persona, user profile, customer segment, jobs-to-be-done, JTBD, persona creation, user segmentation, target user, who are our users.

Creates decision-focused PRDs and product specs — the kind that make explicit decisions, not document hopes. Make sure to use this skill whenever someone asks to write, review, draft, or improve any product document, including PRDs, feature specs, requirements docs, or product specifications. Trigger even when the user doesn't say "PRD" explicitly — phrases like "write a spec for X", "define requirements for Y", "what should my PRD include", "help me document this feature", or "my spec feels ...

Translates stakeholder feature requests into validated outcome statements before any work is committed. Use this skill — proactively and without waiting to be asked — whenever a stakeholder, exec, or customer arrives with a pre-packaged solution: "we need a dashboard", "add a Slack notification", "build an export feature", "create a report", "let's add a filter", "can we just add X". Also triggers for: "how do I push back on this request", "what outcome does this feature solve", "outcome vs o...

Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".

Generate supported images, videos, audio, and 3D models via RunningHub API and run RunningHub AI Applications by webappId.

Discipline for repairing a false claim once it has propagated: select what depends on it, produce a replacement, and accept with an expiring verdict. Trigger when: - A claim, citation, premise, or documented fact is found wrong and its downstream consequences must be traced and fixed. - A refutation, a failed re-run, a retracted external source, or a human correction lands against something already closed or already promoted. - Prompt contains: /remediation, remediation, retraction, false cla...

SOP for locating, auditing, and importing production-tested reference patterns and peer-reviewed literature. Trigger when: - Designing or implementing non-trivial algorithms, system protocols, design patterns, or major library integrations. - Prompt contains: prior art, reference implementation, research patterns, standard implementation, arXiv, RFC.

Structured root cause analysis for arriving at a concrete action. Use when something went wrong, a pattern keeps recurring, behavior has drifted, or you catch yourself resolving to "do better" / "remember to X" without a concrete artifact. Five-whys forces behavioral resolutions into file edits, config changes, memory block updates, or scheduled jobs — the action item must produce a diff someone else can verify. Do not use for simple debugging with an obvious cause.

Discover what bundled skills exist in this mimir install and what each one does. Use when you're not sure if a capability is already covered by a skill ("can I X?", "is there a skill for Y?", "what skills do I have?"). Reads SKILL.md frontmatter from each skill directory and surfaces names + descriptions.

Recognize when you're in a runaway loop and stop yourself. Use when the same tool call has repeated 3× with the same args, when the same error class has fired 3× in a turn, when you've been told the same correction twice, when "let me try one more variation" is the third small variation, or when a refinement loop is orbiting rather than converging. The right move on a trip is to switch from action to inquiry — read events.jsonl, list assumptions, look for contradictions, ask the human, file a...

Use when a high-priority signal needs to reach the operator but doesn't fit the current conversation (off-hours wake, urgent error needing eyes, scheduled-tick discovery worth surfacing now). Routes via MIMIR_OPERATOR_ALERT_CHANNEL.

Analyze and automatically remediate MoonSpec artifact inconsistencies across spec.md, plan.md, tasks.md, and related design files. Use when the user asks to run `/moonspec.align`, identify uncertainty, weigh tradeoffs in project context, edit artifacts without asking follow-up questions, resolve coverage gaps, or align generated MoonSpec documents before implementation.

Rank the brand idea bank against the approved Phase-2 strategic roadmap. Grades the whole captured pile — which priority each idea serves, the lever it pulls, how strong the evidence is, whether it trips a roads-not-taken kill — and produces a ranked shortlist by priority that ends in a plain ranked call the sprint plan sizes into a round, plus a read of what the bank is starving for. The skeptical pass. Run after harvest-ideas (weekly), when the bank grows enough to change the rank, or when ...

Maintain a brand-specific idea bank from context docs, research, Parker data, user conversations, manual ideas-tab saves, expert signals, competitor ads, organic videos, and internal Parker observations.

Use when starting or resuming a Plan. Runs bounded tacit-knowledge intake when needed, creates or updates a roadmap, then advances one verified Goal at a time. Use Qgoal only as a goal-intake alias.

Use when: performing a scheduled Loki log sweep (e.g. the daily n8n Log Monitor workflow), summarising warnings and anomalies across hosts, and producing a written report on how to fix or suppress each finding. Defines the sweep methodology, the report format (markdown files in `log-sweeps/`), and a list of known-benign log patterns that must be excluded from reports.

Use this skill when you have analysis results, review findings, or session insights that need to be converted into an actionable implementation plan. The goal is to transform observations into prioritized, executable tasks.