TheHalfMoon
- 98 skills
- 0 followers
- yesterday last updated
- ▌ Configuring Experiment Analytics · thehalfmoon bundleConfigures the analytics side of a Flind experiment — exposure criteria (server-resolved default exposure event vs custom exposure events), primary and secondary metrics, the supported metric types (count, sum, ratio with `math` and `math_property`, retention with `retention_window_start` and `start_handling`, percentile with `quantile`), multivariate user handling ("Exclude from analysis" vs "Use first seen variant"), and how to read results once the experiment is live. Use when the user adds or edits a primary or secondary metric (e.g. "add a secondary metric tracking 'downloaded_file' per user"), sets up a ratio metric (e.g. "revenue from purchase_completed / pageviews"), sets up a retention metric (e.g. "$pageview → uploaded_file, 7-day window"), configures custom exposure (e.g. "only count users who hit /checkout"), changes multivariate handling, or asks "who is in the analysis?", "how do I measure impact?", "is this winning?", "what's the confidence level?", or "should I ship?".
- ▌ Creating Box Plot Insights · thehalfmoon bundleCreates product analytics or SQL-backed box plot insights in Flind. Use when a user asks to create, build, or save a box plot, visualize a numeric distribution, compare quartiles or medians across dates or groups, or turn SQL results into a box plot. Chooses between a standard Trends box plot and a SQL insight, validates the distribution data, saves the insight, and verifies it.
- ▌ Auditing Warehouse View Health · thehalfmoonAudit the health of a Flind project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this materialized view failing?", "are any of my views wasting compute?", or wants a one-shot triage of view health. For source/sync health use `auditing-warehouse-source-health`.
- ▌ Cleaning Up Stale Feature Flags · thehalfmoon bundleIdentify stale feature flags in a Flind project and clean up the code that checks them. Use when the user wants to find, audit, or remove unused, fully rolled out, or abandoned feature flags, run a feature flag hygiene review or a weekly cleanup, reduce feature flag tech debt, or asks "which flags can I remove?". When the agent can read and edit a repository it performs the code cleanup itself: tested local changes, and one draft PR per flag when the user authorizes publishing. Agents without repository access generate a tailored cleanup prompt instead. Covers staleness detection, dependency checking, retained-path rules, and the code-first ordering. This skill does not archive or otherwise change a flag in Flind.
- ▌ Consuming Endpoints From Client Code · thehalfmoonWire a Flind endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts, sending the right auth header, shaping the variables payload (HogQL code_name vs insight breakdown property), handling rate-limit and materialised-endpoint error responses. Use when the user says "how do I call my endpoint", "generate a client for this", or "what auth header do I use".
- ▌ Setting Up A Custom REST Source · thehalfmoon bundleConnect an arbitrary REST API to the Flind data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user points at an API that has no built-in Flind connector — "import data from this REST API", "sync my internal API", "connect this API from its docs", "build a custom data warehouse source" — and gives a docs URL or a natural-language description of the endpoints. Walks through drafting the RESTAPIConfig manifest (auth — bearer, API key, HTTP basic, or OAuth2 client credentials / refresh token — pagination, record path, incremental cursor, parent/child fan-out), validating it, test-reading live rows to verify the field mappings, and creating the source. If the API already has a native Flind connector, use setting-up-a-data-warehouse-source instead — this skill checks the connector registry first and only handles APIs with no native connector.
- ▌ Diagnosing Stacktrace Symbolication · thehalfmoon bundleHelp users debug Flind Error Tracking stack-trace symbolication for any supported platform — JavaScript/TypeScript web, React Native (Hermes), Android (Proguard / R8), or iOS / macOS (dSYM). The Flind symbol-set lookup flow is universal across platforms; build-tool and artifact details live in per-platform references (JavaScript is fleshed out, others come as we encounter them). Use when stack frames stay minified or obfuscated after symbols are uploaded, Flind symbol sets show last_used but frames are not readable, chunk IDs or dSYM UUIDs do not match, "Token not found" appears, uploaded source maps / dSYMs / Proguard mappings look empty, or bundler / symbol-upload configuration needs troubleshooting.
- ▌ Auditing Warehouse Source Health · thehalfmoonAudit the health of a Flind project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.
- ▌ Syncing Migrated Self Managed Tables · thehalfmoonTurn on syncing for warehouse tables that Flind moved from self-managed tables to managed sources (Amazon S3, Google Cloud Storage, Azure Blob, Cloudflare R2 or File upload). Use when the user asks "what happened to my self-managed tables", "how do I sync my migrated bucket tables", "why does my table say it is waiting for its first sync", "will I be billed for these tables", or when a migrated table fails its first sync with access denied, "No files are available for table", or "Flind did not replace the self-managed table".
- ▌ Turning Engineering Analytics Into Insights · thehalfmoon bundleConverts engineering analytics (PR / CI) data into saved Flind insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-analytics-sources, replicating curated column semantics in HogQL, reading exposed engineering_analytics_* warehouse views where product logic is involved (CI cost, fingerprinted failure lines, commit attribution), saving queries with insight-create, and scheduling delivery with subscriptions-create. Use when asked to "save this as an insight", "put CI health / merge times on a dashboard", "email me PR throughput weekly", "chart CI cost", "track time to first review", "subscribe to these numbers", "alert on CI success rate", or "what data/tables/views does engineering analytics read". For ad-hoc CI and merge questions use diagnosing-ci-and-merge-bottlenecks; to investigate one specific CI failure use investigating-ci-failures.
- ▌ Migrating From Fivetran · thehalfmoon bundleMove a user's Fivetran connectors into Flind data warehouse sources. Use when the user says "migrate from Fivetran", "import my Fivetran setup", "replace Fivetran with Flind", or asks what of their Fivetran account Flind can take over. Reads the Fivetran account with a read-only key or through the user's Fivetran MCP server, reports which connections move as they are, which move with caveats, and which Flind cannot take yet, then creates the Flind sources one at a time while the user enters only the secrets.
- ▌ Configuring Experiment Rollout · thehalfmoon bundleConfigures the rollout shape of a Flind experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users enter the experiment, and the disambiguation when a percentage like "roll out to 25%" could mean either. Use when the user mentions a rollout percentage, variant split, or traffic distribution; gives a ratio like 60/40, 70/30, or 80/20; asks "who sees the test variant?"; wants to increase, decrease, or change the rollout or split on a draft or running experiment; weighs equal vs uneven splits; or proposes a mid-experiment split change (often an anti-pattern that needs reset or end-and-restart).
- ▌ Copying Endpoints Across Projects · thehalfmoonCopy a Flind endpoint (a saved HogQL/insight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in the same project. Use when the user wants to duplicate an endpoint, promote an endpoint from staging to production, replicate an endpoint's query/variables/freshness config in another workspace, or clone an endpoint to iterate on it. Unlike feature flags and experiments, endpoints have NO native cross-project copy tool — this skill covers the read-then-recreate flow (endpoint-get then endpoint-create), the active-project switching it requires, name-collision checks, and the safe defaults (land unmaterialised in the target, verify with endpoint-run). Does not cover editing endpoint versions (see managing-endpoint-versions) or authoring a brand-new endpoint from scratch (see creating-an-endpoint).
- ▌ Exploring Endpoint Execution Logs · thehalfmoonExplore and diagnose a Flind endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query performance profiling.
- ▌ Copying Flags Across Projects · thehalfmoonCopy a feature flag from one Flind project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).
- ▌ Exploring MCP Intent Clusters · thehalfmoonExplore Flind MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
- ▌ Creating Online Evaluations · thehalfmoon bundleAuthor continuously-running online evaluations in Flind AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these failures into evals", or after reading traces finds a recurring failure. Covers letting the explored data decide how many evals to create, proposing that set for the user to pick, choosing the target and eval type (hog / llm_judge / sentiment), configuring an llm_judge's provider and model, scoping which generations trigger it via conditions, creating disabled, verifying scope, enabling, and backfilling past data. Proposes a sentiment eval when no failure mode is worth catching. Finding and ranking the failure modes worth evaluating is its own job — use exploring-ai-failures first. To debug or manage evaluations that already exist, use exploring-llm-evaluations.
- ▌ Downloading Batch Export Files · thehalfmoonExport Flind events, persons, sessions, or the results of a HogQL query on demand and download the resulting files. Use when the user asks to download/export raw Flind data, export HogQL query results, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.
- ▌ Modeling Product Usage Metrics · thehalfmoon bundleBuild reusable product-usage and engagement models — retention, stickiness, and lifecycle — on either Flind data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model, define, or compute whether users come back (retention / churn), how frequently they engage (stickiness / power users / DAU-WAU-MAU ratio), or the composition of the active base (new / returning / resurrecting / dormant lifecycle). These three are one engagement family sharing a start-event/return-event vocabulary and an interval granularity; this skill treats them together and helps pick the right lens: retention for the return-rate cohort matrix, stickiness for the frequency distribution, lifecycle for growth quality. On Flind, model them in HogQL (mirroring query-retention / query-stickiness / query-lifecycle); in dbt, build fct_retention / fct_stickiness / fct_lifecycle marts with tests. Read modeling-warehouse-foundations first; feeds the retention validation used by modeling-activation-metrics.
- ▌ Modeling Warehouse Foundations · thehalfmoon bundleShared foundations for building reusable data models in Flind, on either of two stacks: Flind-native data-warehouse views / materialized views (HogQL, via the view-* MCP tools), or an external dbt project (sources.yml + staging/marts + schema tests) run against your own or Flind's managed warehouse. Read before authoring any specific business model — covers the Flind-vs-dbt decision, the view-create → view-materialize → sync_frequency workflow and the HogQL column-aliasing rule, the dbt project skeleton and the "no native dbt integration" picture, warehouse joins and star-schema dimensions, currency conversion with convertCurrency(), and checking/registering models in the data catalog for reuse. Companion to modeling-revenue-metrics, modeling-conversion-metrics, modeling-activation-metrics, modeling-product-usage-metrics, and modeling-dimension-tables. Use when the user asks how to build a view, materialized view, or dbt model in Flind, or which of the two stacks to use.
- ▌ Managing Streamlit Apps · thehalfmoonCreate, deploy, and operate Streamlit apps in Flind via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its Flind URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".
- ▌ Creating AI Subscription · thehalfmoonCreate a recurring AI-generated Flind report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email, Slack, or Microsoft Teams on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)
- ▌ Linking Errors To Traces · thehalfmoon bundleLinks a Flind error occurrence or session's errors to OpenTelemetry traces, logs with the same trace ID, and Session Replay. Use when the user asks for trace or span IDs on an error, same-trace logs, or backend traces for errors in a session. Starts from an occurrence UUID, session ID, or error tracking issue URL. For a general issue diagnosis or replay summary, use investigating-error-issue or investigating-replay.
- ▌ Suppressing Noisy Errors · thehalfmoonCreate Flind error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop browser extension errors", "ignore ResizeObserver loops", "suppress bot-driven errors", or wants to reduce ingestion cost from noisy unactionable errors. Identifies suppression candidates, scopes the filter tightly, decides between full suppression and sampling, and confirms the rule before creating it. Suppressed errors are dropped permanently — this skill defaults to caution.
- ▌ Signals Scout Revenue Analytics · thehalfmoonSignals scout for Flind revenue analytics. Watches for upstream failures (Stripe sync stalls, capture regressions), and config drift.
- ▌ Investigating Error Issue · thehalfmoonInvestigates a single Flind error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error-tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass.
- ▌ Diagnosing Experiment Health · thehalfmoon bundleRuns diagnostics and a health check on one Flind experiment: its setup, exposures, results and changes during the run. Covers 0 exposures, sample ratio mismatch, lost or uneven exposures, users in multiple variants, identity faults, who the experiment counts, significance traps (peeking, A/A, 'target reached', Bayesian vs Frequentist, sequential, CUPED), mid-run edits, pause and freeze, and survey follow-up. TRIGGER when: user asks 'is my experiment healthy / set up right / biased?' or 'why 0 exposures?', asks why it counts different people than their insight, mentions the bias or mismatch warning, an uneven split, significance that flips, numbers that disagree with their SQL, results that changed after an edit, or wants user feedback on an experiment. DO NOT TRIGGER when: creating an experiment (use creating-experiments), only configuring rollout (use configuring-experiment-rollout) or metrics (use configuring-experiment-analytics), or only asking lifecycle questions (use managing-experiment-lifecycle).
- ▌ Exploring MCP Tool Quality · thehalfmoonInvestigate the quality of Flind MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
- ▌ Signals Scout Customer Analytics · thehalfmoonSignals scout for Flind Customer analytics (Accounts). Watches per-account engagement for churn-risk shapes — engagement cliffs, dormancy, champion departure — and the expansion inverse.
- ▌ Diagnosing Endpoint Performance · thehalfmoonDiagnose why a Flind endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite the query. Use when the user says "this endpoint is slow", "my endpoint times out", "we're hitting the cost cap on this one", or asks "should I materialise this?". Focuses on a single named endpoint, not a project-wide audit.
- ▌ Triaging Visual Review Runs · thehalfmoonInspects Flind Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot diff", "screenshot test", "storybook regression", "playwright snapshot", "quarantine", asks why a PR is blocked or what changed visually, wants to triage the VR backlog, decide whether a snapshot diff is real vs flaky, quarantine or lift a flaky story, or check whether a story has been changing across runs. Also invoke when a PR has a failing `visual-review` status check, when a PR comment mentions "Visual review", when a PR from a fork fails a screenshot check, or when the user is on a branch with an open VR run.
- ▌ Auditing Experiments Flags · thehalfmoon bundleAudit Flind experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.
- ▌ Writing Streamlit Apps · thehalfmoonWrite Streamlit app source code that runs well in a Flind sandbox — the posthog_apps.query() bridge for reading Flind data, the packages baked into the sandbox image, caching and session state across Streamlit reruns, layout and chart patterns, and the app.py entry point with any helper modules and data files bundled beside it. Use when authoring or debugging the Python source of a Flind Streamlit app, when a query inside an app fails, or when asked to "write a streamlit app that shows Flind data".
- ▌ Working With Autoresearch · thehalfmoon bundleUse Flind Autoresearch, agent-driven predictive models: ask "who will do X in the next N days?", let an agent train a model, then score people daily into a person property and `autoresearch_prediction` events. Use when a user wants to predict churn, activity, return, feature adoption, conversion or any event or action per person; create or validate a model from a template; start training or score now; read model quality (holdout vs realized AUC, lift, calibration, likelihood segments, coverage); steer training with suggestions; act on predictions with cohorts, feature flags, workflows or SQL; or diagnose a model that fails to train, scores everyone the same, or stops scoring. Trigger on "autoresearch", "predictive model", "propensity score", "churn prediction", "likely to convert", "who will do X", "predicted_p_", "autoresearch_prediction", "realized AUC", "champion model".
- ▌ Resolving Ingestion Warnings · thehalfmoon bundleDiagnoses and resolves Flind ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, invalid data). Use when a user asks why events are missing, dropped, or undercounted, why identify/alias calls don't work or accounts stay duplicated, why person or group properties aren't updating or profiles look inflated, why recordings have gaps, heatmaps are empty, LLM token counts are missing, why cookieless events vanish, or whenever the `ingestion_warning` health check fires. Explains severity triage (error = dropped, warning = modified, info = intentional) and routes all warning types — size limits and enrichment, merges and distinct IDs, high-volume distinct IDs, `$process_person_profile`, timestamps, cookieless, heatmaps, transformations, session replay — to per-issue reference files with code-level causes and per-SDK fixes.
- ▌ Exploring MCP Tool Usage · thehalfmoonStarting point for exploring how a Flind MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how is my MCP doing?", "what should I look at?", "explore my tool calls", "who uses my MCP tools?", "what are agents doing with the MCP?", or pastes an MCP analytics URL without a specific question. Offers a menu of questions, each backed by a query tool, then hands off to the focused skill.
- ▌ Sending Transactional Emails · thehalfmoon bundleSet up Flind transactional emails: one-off emails that code sends to one person, such as password resets, sign-in codes, magic links, verification emails, receipts, and invites. Use whenever the user mentions transactional email or one of those emails, or an email provider they send them with (Resend, Postmark, SendGrid, Mailgun, Amazon SES, Mandrill, Loops, Brevo, Customer.io transactional, nodemailer or SMTP). Use it when they set one up, move one, debug one, or only describe what they have now. Covers offering Flind as the sender, the verified sender, the template, making it transactional, the API key, sending from code with the SDKs, idempotency keys, and checking an email's status.
- ▌ Investigating Metric Anomalies · thehalfmoonInvestigates server/infrastructure metric anomalies in Flind Metrics — from "this metric is rising/dropping/spiking" or a fired alert to a probable cause with evidence. Use when asked why a metric looks wrong (ingestion lag rising, error rate spiking, latency degrading, queue depth growing, throughput dropping), when an alert fires on an OTel/Prometheus metric, or for any incident triage that starts from a metric symptom. Composes characterize-metric-anomaly, query-metrics, and metric-names-list with logs (query-logs) and traces (APM span tools) for cross-signal root-cause correlation.
- ▌ Signals Scout AI Observability · thehalfmoon bundleSignals scout for Flind AI observability. Watches LLM traces for cost, latency, error, volume, and eval-performance regressions.
- ▌ Exploring LLM Costs · thehalfmoon bundleInvestigate LLM spend in Flind — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.
- ▌ Grouping Noisy Errors · thehalfmoonConsolidate Flind error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many TypeError issues that look the same?", "merge these duplicates", "stop splitting this error into new issues", or wants to clean up fingerprint sprawl. Decides between a one-shot merge of existing issues and a durable grouping rule that keeps future events from creating new fingerprints. Does NOT group conceptually similar bugs across different runtimes, SDKs, or call sites.
- ▌ Triaging Error Issues · thehalfmoonTriage Flind error tracking issues during a daily or on-call review. Use when the user asks "what's broken?", "what new errors do we have?", "show me top errors today", "what should I look at this morning", or wants a prioritized list of active issues to work on. Surfaces new and high-impact issues, ranks by users affected and recency, points at linked replays, and proposes next actions (investigate, assign, suppress, merge).
- ▌ Exploring MCP Sessions · thehalfmoonInvestigate individual Flind MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
- ▌ Signals Scout Data Pipelines · thehalfmoonSignals scout for Flind data pipelines — CDP destinations and transformations, batch exports, and hog flows. Watches for delivery failures, degraded functions, and stalled exports against each pipeline's baseline.
- ▌ Signals Scout Error Tracking · thehalfmoonSignals scout for Flind error tracking. Watches `$exception` bursts, stuck loops, multi- fingerprint clusters, and status regressions.
- ▌ Signals Scout MCP Tool Calls · thehalfmoon bundleSignals scout for Flind MCP tool calls. Watches `$mcp_tool_call` telemetry for tools that need improvement — broad-reach failure rates, retry hammering, slow or context-bloating responses — grouped by owning product category, each with a fix suggestion.
- ▌ Signals Scout Session Replay · thehalfmoonSignals scout for Flind session replay. Watches that sessions keep recording (capture cliffs) and surfaces friction inside recordings — rage/dead-click clusters, error-after- interaction cohorts.
- ▌ Managing Subscriptions · thehalfmoon bundleCreate and manage scheduled Flind subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports. Use when a user wants recurring email, Slack, or Microsoft Teams delivery; an AI summary; delivery history; schedule or recipient changes; a test delivery; pause, resume, or deletion; or help with subscription permissions, limits, billing, and failures. Use product alerts when delivery must depend on a threshold or anomaly.
- ▌ Checking Member Access · thehalfmoonExplains what a member or a role can do in a Flind project, using the access control MCP tools. Use when the user asks what someone can see or edit, who can edit dashboards or feature flags, why a member can or cannot open a dashboard, notebook or table, what a role grants, which properties are hidden from someone, or how the project's default access is set. Covers what each level means, how the stored rule, the enforced level and the inherited access relate, what the null values mean, which tool answers which question, and when the answer needs the role tools too.
- ▌ Exploring LLM Traces · thehalfmoon bundleDebug and inspect LLM/AI agent traces using Flind's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
- ▌ Working With Task Comments · thehalfmoonRead and use comments attached to the current Flind task, its artifacts, and any canvas through the Flind MCP exec dispatcher. Use when the user mentions task comments, artifact or canvas comments, annotations, selected-text feedback, replies, unresolved comments, or asks an agent to inspect or act on feedback left in Flind Desktop. Covers exec discovery and calls, target filtering, pagination, full-thread retrieval, anchor/version context, task-scoped access, and standalone canvas comments that have no task.
- ▌ Debugging Experiments · thehalfmoon bundleDebug and support Flind Experiments (A/B tests) for a customer looking at their own results. Use whenever an experiment support ticket is pasted or a customer asks a results question, most commonly "why aren't my exposures even?", "why is one variant getting no traffic?", "why am I missing / seeing too few exposures?", "why does the bias banner show?", or "why don't Flind's numbers match my SQL?". Pulls the experiment's real data read-only, matches it to a known-cause catalog, and produces a customer-facing explanation, fix, and review of the pertinent numbers. Loads diagnosing-experiment-health as its deep diagnostic library. DO NOT TRIGGER when: creating an experiment (use creating-experiments), only configuring rollout (configuring-experiment-rollout) or metrics (configuring-experiment-analytics), asking lifecycle questions (managing-experiment-lifecycle), or the underlying feature flag is what's misbehaving rather than the results (use debugging-feature-flags).
- ▌ Checking Deploy Timing · thehalfmoonDetermine when a Flind code change reached a given environment by reading the hidden GIT deploy annotations in the project and correlating them with the merge commit on GitHub. Use when Flind staff ask "when was X deployed", "is my change live in the US/EU yet", "has my PR shipped", "did the fix roll out to prod-us", or otherwise want to know whether/when a commit, PR, or feature went out to a region. Do not answer deploy-timing questions from event/data volume alone — that only shows when data changed, not when code shipped.
- ▌ Signals Scout Experiments · thehalfmoonSignals scout for Flind A/B experiments. Watches running experiments for validity threats — sample ratio mismatch, contamination, exposure stalls, mid-run flag mutations — and lifecycle drift.
- ▌ Signals Scout Skills Store · thehalfmoonSkill-hygiene scout for the team's Flind skills store. Watches recently-changed and most- used skills for authoring violations — vague descriptions, bloated bodies, dead file links, kitchen-sink scope, committed secrets.
- ▌ Feature Usage Feed · thehalfmoonSet up an LLM-judge evaluation that extracts canonical use cases for a Flind feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).
- ▌ Understanding Billing Usage · thehalfmoon bundleExplains Flind billing usage and spend from the customer's visible Billing MCP tools. Use when the user asks why usage or spend is high, which product or project is driving usage, what a usage type means, how to reduce usage, what changed over time, why they got a usage change alert, or whether a spike/drop alert was real or noisy. Also use before product-specific analytics skills when the user names a billable Flind product metric such as events, recordings, feature flag requests, exceptions, survey responses, synced rows, logs, AI events, AI credits, or Inbox credits. Starts from Billing usage/spend tools, then routes to customer-visible product MCP surfaces for deeper investigation.
- ▌ Signals Scout Conversations · thehalfmoonSignals scout for Flind Conversations (support inbox). Watches `$conversation_*` ticket- lifecycle events for SLA breach steps, first-response latency blowouts, backlog imbalance, and channel or assignment concentration.
- ▌ Signals Scout Feature Flags · thehalfmoon bundleSignals scout for Flind feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags, response-distribution shifts, and flag debt.
- ▌ Signals Scout Health Checks · thehalfmoonSignals scout over Flind's own health checks. Bundles the project's active health issues by kind, weights them by blast radius, and surfaces the ones worth acting on.
- ▌ Signals Scout Replay Vision · thehalfmoonSignals scout for Flind Replay Vision scanners. Watches that enabled scanners keep observing (throughput and quota cliffs) and that aggregate score shifts and recurring themes get surfaced.
- ▌ Signals Scout Web Analytics · thehalfmoonSignals scout for Flind web traffic. Watches per-channel session volume, attribution breakage, and landing-page health (bounce and 404 steps) against the site's own baseline. Per- page web vitals belong to `signals-scout-web-vitals`.
- ▌ Review Hog Authoring · thehalfmoonHow to author custom Flind Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive Flind Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a Flind Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what Flind Review publishes", "tune what Flind Review implements".
- ▌ Signals Scout Workflows · thehalfmoonSignals scout for Flind workflows. Looks at the workflows whose owner asked for suggestions, reads each email step's per-version delivery metrics, and proposes one concrete change a person can approve, filed through the workflows suggestions API. It files no report and emits no signal: the suggestion on the workflow page is the output.
- ▌ Querying Posthog Data · thehalfmoon bundleExplains how to query Flind data, defaulting to typed runners for supported product analytics. Read it before you write HogQL/SQL. Also read it before you call execute-sql against Flind. Use it to find or aggregate Flind entities. These entities include insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, warehouse data, and persons. Use it for trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, and LLM traces. Before you calculate a governed business or telemetry measure, check system.information_schema.metrics for an approved definition. Examples include MRR, activation, billable usage, active organizations, and failure rates. Use the approved definition before you derive a measure from raw events or use a typed domain tool. It also covers HogQL differences, system table schemas, functions, query examples, and schema discovery.
- ▌ Implementing API Surveys · thehalfmoon bundleImplements a Flind API (headless) survey inside the user's own codebase so it renders with their UI components and captures the exact events Flind expects, then verifies the first response arrived. Use when asked to implement a survey, build a headless survey, build a custom survey UI, render a survey in my app, or wire up a survey of type `api` in a browser, server, or custom mobile UI. Covers the posthog-js event contract, server-side SDK capture, and post-implementation verification through MCP. To design or create the survey definition, use creating-surveys instead. For a survey that is implemented but not showing or not recording, use debugging-surveys.
- ▌ Working With Scouts · thehalfmoon bundleWork with Flind Signals scouts: scheduled agents that monitor a project and write reports into the Signals inbox. Use to assign monitoring work, schedule quality scoring, find which scout covers a surface, act on reports, reduce noise, investigate missing findings, or improve the fleet through feedback and calibration. Also covers follow-up checks that verify whether a reported problem stays fixed. Use `authoring-scouts` for edits, `exploring-scouts` for run observability, and `inbox-exploration` for report triage. Trigger on "work with my scouts", "get more out of scouts", "have a scout watch X", "tell me if Y spikes", "score X on a schedule", "measure quality of Y", "what do I do with this scout report", "calibrate/review my scout fleet".
- ▌ Auditing Endpoints · thehalfmoonAudit every endpoint in a Flind project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.
- ▌ Diagnosing Sdk Health · thehalfmoonDiagnoses the health of a project's Flind SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about Flind SDK versions, outdated SDKs, upgrade recommendations, "SDK health", "SDK doctor" (the former name), or when events or features seem off and it might be due to an old SDK.
- ▌ Managing Reminders · thehalfmoonCreate and manage Flind reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a Flind resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be reminded to look at a dashboard, insight, experiment, feature flag, survey, notebook, replay, or error, or wants to list, change, or cancel their reminders. Covers when to pick a reminder over an alert or subscription, the one-off vs recurring vs cron schedule field mappings, timezones, and attaching a resource.
- ▌ Exploring Apm Traces · thehalfmoon bundleInvestigates distributed application performance using Flind APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, error-rate trends or spikes, latency distributions, trace IDs, or span attributes — not AI observability traces or product logs. Uses posthog:apm-service-health, posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-spans-sparkline, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
- ▌ Building HTML Canvases · thehalfmoonAuthor a Flind canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has routed a canvas request to a plain-HTML/browser-API implementation. Covers the thin component wrapper the current runtime requires, styling and theming without Quill, drawing surfaces, and animation/cleanup patterns.
- ▌ Prioritizing My Inbox · thehalfmoon bundleGive the current user a personal, ranked shortlist of the Flind Inbox reports they are most likely to care about right now. Reads their stored personal ranking first, with one `inbox-reports-list` call (`view=for_you`, `sort=personal`), and keeps its order and reasons. Uses `inbox-reports-for-me` for a fresh or focused list, and builds a ranking by hand from the activity summary and the ranking model's lifts only when no stored ranking applies or the user asks for custom weights. Use when the user says "let's look at my inbox", "what's in my inbox for me?", "my top 10 inbox reports", "what should I look at today?", or asks to re-rank, focus, or filter that list. For browsing, filtering, drilling into, or acting on a single report, use `inbox-exploration`.
- ▌ Signals Scout Surveys · thehalfmoon bundleSignals scout for Flind surveys. Watches active surveys for score regressions, response- volume drops, abandonment spikes, and targeting drift, and aggregates open-text responses into recurring themes.
- ▌ Composing Grid Canvases · thehalfmoon bundleCompose Flind grid canvases — widget grids (including the user's home canvas) built from reusable component canvases. Use when a task asks to add, fill, move, resize, or remove a widget on a grid or home canvas, to compose a whole canvas of widgets from one ask, to build a reusable widget/component, or when a placement id or grid canvas id is the target. Covers the component store search → configure → fork → build ladder, the component placement contract (size, configSchema), the placement lifecycle (pending/generating/live/failed), the guarded layout patch loop, and reading the canvas's comment threads.
- ▌ Creating An Endpoint · thehalfmoon bundleCreate a Flind endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown), data_freshness_seconds, and whether to materialise on day one. Use when the user says "create an endpoint", "expose this query as an API", "turn this insight into an endpoint", or asks for help structuring a new endpoint. Steers away from common mistakes: materialising a query with cohort breakdowns or an ineligible compare query, inline-only variables on a materialised endpoint, unbounded date ranges, ambiguous names.
- ▌ Finding Experiments · thehalfmoonResolves a Flind experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, paused, exposure frozen, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.
- ▌ Authoring Log Alerts · thehalfmoon bundleAuthor useful, low-noise log alerts on services in a Flind project. Use when the user asks to set up alerts for their logs, suggest alerts they should add, or evaluate whether a service is worth monitoring. Covers service triage, baseline characterisation, threshold drafting, back-testing via simulate, and shipping with a notification destination.
- ▌ Inbox Exploration · thehalfmoon bundleExplore Flind's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's Flind flagged recently?", asks about a specific report by ID or title, wants to act on / fix / implement a report (turn it into a PR), wants to resolve, dismiss, or snooze a report, or wants to see which signal sources are configured. Also use before you investigate an error, bug, metric change, or support ticket in code, to find research the Inbox already did. Covers listing, filtering, drilling into, and acting on reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed. For a personal, ranked top N of reports, use `prioritizing-my-inbox`, which starts from the stored personal ranking (`view=for_you`, `sort=personal`).
- ▌ Signals Scout Apm · thehalfmoon bundleSignals scout for Flind distributed tracing (APM / OpenTelemetry spans). Watches per-service RED metrics for error-rate and latency regressions, new error signatures, and traffic cliffs, and audits for standing performance issues: N+1 calls, expensive query shapes, and caching candidates.
- ▌ Debugging Surveys · thehalfmoon bundleDiagnose Flind Surveys configuration and responses across all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), or when diagnosing why a survey does or doesn't display. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.
- ▌ Analyzing Task Runs · thehalfmoon bundleSplit a completed Flind task run into activity records — what the agent tried, whether it worked, what blocked it — and record each one through the report_activity tool. Use when a task asks to analyze a run, produce a task analysis, or review a run from an attached run log. Covers the log query protocol (bounded jq queries over the raw JSONL), both log schemas, the activity schema, and evidence verification. Records facts only; it does not suggest fixes.
- ▌ Analyzing AI Citations · thehalfmoon bundleAnswer AI citation and answer engine optimization (AEO) questions in Flind: whether AI answer engines (ChatGPT, Claude, and an Exa retrieval baseline) cite the project's site for its tracked prompts, which topics and engines cite it least, which domains get cited instead, and whether citations line up with Google Search Console rankings and AI referral or AI crawler traffic. Use when the user asks "are we cited by AI?", "which prompts never cite us?", "citation rate by topic or engine", "who gets cited instead of us?", "do AI citations drive traffic?", or wants to cross-reference AI answers, Search Console and Flind web traffic.
- ▌ Signals Scout Logs · thehalfmoonSignals scout for Flind logs. Watches for emerging and rate-shifted message patterns, volume bursts, severity-distribution shifts, service silence, and trace-correlated bursts.
- ▌ Working With Skills · thehalfmoon bundleBest practices for agents managing Flind skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any `skill-*` tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Also use when asked what skills are good for or how to shape one (project hub, runbook, catalog, handover, daily driver). Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, pattern, and pitfall guidance.
- ▌ Querying Canvas Data · thehalfmoon bundleGet Flind data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in Flind; ad-hoc queries expose the exact query that ran), per-insight-type result shapes, progressive per-query loading, date-range wiring, live third-party data through the viewer's own connections (ph.connectors), and event capture from a canvas. Use whenever a canvas shows metrics, charts, tables, any Flind data, or data from GitHub or an MCP server, or needs to send analytics events.
- ▌ Signals Scout Tasks · thehalfmoon bundleSignals scout for Flind Tasks. Watches delivery health — failing runs clustered by repository and error class, retry storms — and, on a slower rotation, recurring demand across human-authored tasks. Skips the scout fleet's own runs.
- ▌ Signals Scout Aeo Citations · thehalfmoonWatches AEO citation-check results in system.aeo_citation_checks and files an inbox report when a domain's citation rate on an answer engine drops or spikes versus its baseline, or when the citation runner itself is failing.
- ▌ Adding Warehouse Person Properties · thehalfmoon bundleSync columns from a synced data warehouse table onto Flind person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting, cohorts, insight filters and breakdowns, surveys, session replay filters, workflows, and the person profile. Use when the user wants to "add a person property from my warehouse", "enrich people with Stripe/Postgres/Salesforce data", "put ARR or plan tier on my persons", "target a feature flag by a warehouse column", "sync warehouse columns onto groups or organizations", or wants to inspect, backfill, disable, or debug an existing warehouse-backed person or group property.
- ▌ Skills Store · thehalfmoonDiscover and use shared team skills stored in Flind. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or references the "skills store" / "skill store".
- ▌ Building Loops · thehalfmoonBuild a Loop for Flind Desktop: a workflow that creates an AI task each time its trigger fires, optionally followed by a Slack or email notification with the task's result. Use when asked to create, set up, or change a loop, a recurring agent, a scheduled task, or an automation that runs an AI task when a GitHub, Slack, or Flind event happens. Covers the exact graph, trigger configs, schedule presets, the notify step, structured output, and the test-run steps.
- ▌ Investigating Logs · thehalfmoonInvestigate logs in a Flind project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying. Use when the user asks to "check the logs", asks whether a service, deploy, release, or change is working or broke anything, asks why errors are up or what changed, or wants the root cause of failures visible in logs. Routes the logs MCP tools (services overview, pattern mining, before/after pattern diffing, bucketed counts, facets, raw rows) so investigations start from summaries instead of raw rows or hand-written SQL over the logs table.
- ▌ Building Canvases · thehalfmoon bundleCreate or edit a Flind freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in Flind and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a standalone canvas app, or when a freeform canvas id is given as the publish target. For grid/home canvases, widget placements, or reusable components, use composing-grid-canvases instead. Covers resolving or creating the target canvas, choosing an implementation approach (React + Quill vs plain HTML/browser APIs), the read → edit → validate → publish → build loop, and which companion canvas skills to load for the details.
- ▌ Authoring Scouts · thehalfmoon bundleWrite, edit, and adapt Flind Signals scouts: scheduled agents that scan a project and report findings. Use to change a canonical scout's scope, thresholds, schedule, or dry-run settings; add a scout for an uncovered surface; record structured output from scheduled LLM scoring; or give feedback through notes. Covers SKILL.md structure, report requirements, follow-up report checks, structured output, duplicate detection, scratchpad memory, scout notes, per-team skills-store and canonical repository edits, and private prompt trials with saved rubrics. Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>", "score/judge/measure X with a scout", "test/compare scout prompts", "generate scout rubrics", "structured output from a scout", "scout output to Slack", "leave a note for / give feedback to a scout".
- ▌ Exploring Scouts · thehalfmoon bundleHow to explore and make sense of Flind Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the reports it wrote or edited, reading the follow-up checks still measuring a report, and assessing a scout's health and performance over time (cadence, success rate, report rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/report nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".
- ▌ Creating Surveys · thehalfmoon bundleCreates and launches Flind surveys through MCP, including NPS/CSAT popovers, hosted feedback forms, and headless surveys. Guides survey type selection, audience targeting, draft review, and launch readiness. Use when asked to create a survey or form, or before calling survey-create. For investigating an existing survey's delivery or responses, use debugging-surveys instead.
- ▌ Diffcipline · thehalfmoonEngineering discipline for coding agents. Use for coding, debugging, refactoring, implementation planning, or code changes when the goal is to reduce silent assumptions, avoid unnecessary code and dependencies, keep diffs surgical, scale verification with risk, and require evidence before declaring work done.
- ▌ Diffcipline Review · thehalfmoonReview a code change for unnecessary scope, hidden assumptions, dependency churn, weak proof, and risk-inappropriate verification. Use for pull requests, patches, diffs, or requests to simplify or verify agent-written code.