finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…

npx skills add https://github.com/posthog/skills --skill finding-experiments

Finding experiments

Users refer to experiments by name, description, or relative references — not by ID. This skill resolves natural language references to concrete experiment IDs.

How to find an experiment

Use the experiment-list tool from the Posthog-local MCP server.

IMPORTANT: Do NOT use feature-flag-get-all or any feature flag tool to find experiments. Use the dedicated experiment list tool: experiment-list.

This tool returns experiments with their id, name, status, feature_flag_key, start_date, end_date, and created_at. Browse the returned list to find the experiment matching the user's reference:

  • By name: scan the name field for matches
  • By recency: results are ordered newest first by default
  • By status: match the status field (draft, running, paused, exposure_frozen, stopped)
  • By flag key: skip the list and call experiment-get-by-flag-key with the key. It returns the full experiment, or found: false with a reason. no_flag and no_experiment mean the key is free, so this is also the existence check to run before experiment-create. ambiguous means several experiments share the flag and none is the single live one: show the candidates and pick one with experiment-get rather than creating another.

After finding matches

  • Exactly one match: Use it. Confirm with the user by name before destructive actions (delete, ship, end).
  • Multiple matches: List them with name, status, and creation date. Ask the user to pick.
  • No matches: Tell the user. Suggest checking archived experiments or different terms.

Get full details if needed

After resolving to an ID, call experiment-get for the full object (metrics, flag details, parameters).

Examples

User: "pause my signup experiment"

Agent:
1. Calls experiment-list
2. Scans results, finds "New signup process" (ID: 1371, status: running)
3. Proceeds to pause experiment 1371

When NOT to search

  • You already have the experiment ID from earlier in the conversation
  • The user just created the experiment — you have the ID from the create response
  • The user provided the ID directly

Related skills

  • managing-experiment-lifecycle — act on the experiment once you've resolved its ID
  • diagnosing-experiment-results — investigate the experiment you found

Plus de skills de posthog

error-tracking-hono
posthog
Suivi des erreurs PostHog pour Hono
tuning-incremental-sync-config
posthog
La configuration d'une synchronisation réside sur ExternalDataSchema et peut être modifiée à tout moment via external-data-schemas-partial-update. La plupart des modifications sont non destructives (prennent effet lors de la prochaine synchronisation), mais certaines (changement de sync_type, modification des clés primaires) nécessitent une manipulation prudente pour éviter de corrompre les données synchronisées.
playwright-test
posthog
Écrire un test playwright, s'assurer qu'il s'exécute et qu'il n'est pas instable.
error-tracking-ruby
posthog
PostHog suivi des erreurs pour Ruby
authoring-log-alerts
posthog
Créez des alertes de logs utiles et peu bruyantes sur les services d’un projet PostHog. Utilisez lorsque l’utilisateur demande de configurer des alertes pour ses logs, suggérez des alertes à ajouter,…
making-scenes-tab-aware
posthog
Guides converting PostHog frontend scenes to be tab aware for internal scene tabs. Use when adding or refactoring a `SceneExport` scene, fixing state leaking…
posthog-survey-creator
posthog
Créez et configurez des enquêtes dans PostHog via une conversation guidée. Utilisez cette compétence lorsqu'un utilisateur souhaite créer une enquête, recueillir des
authoring-scouts
posthog
Comment rédiger, éditer et adapter les scouts PostHog Signals — les agents programmés qui analysent un projet et écrivent des rapports dans la boîte de réception Signals. Utilisez lorsqu'un utilisateur…