agentleFS
reatlatreatlat/fullstory-claude-plugin/skills/session-search/SKILL.md

session-search

Skill36 starsChanged 14 days agoMITView on GitHub

Search across sessions by user properties, device, browser, custom events, or page — find the needle in the haystack. Use when you need to find specific sessions without a pre-built metric or segment.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ml-training-recipe, replication and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • getcompanion-aiSkill

    ml-training-recipe

    Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.

    Also in 3 projects that use this

  • getcompanion-aiSkill

    replication

    Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

    Also in 3 projects that use this

  • brainbytes-devSkill

    alpha-research

    Also in 3 projects that use this

  • JaimeParkerSkill

    paper-code-audit

    Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.

    Also in 3 projects that use this

  • JimLiuSkill

    pdf-explore

    Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.

    Also in 3 projects that use this

  • michalparkolaSkill

    session-log

    Summarize the current conversation session and append results to the weekly agent-log. Use when user says "log this", "session log", "summarize this session", or asks to write results to the agent-log.

    Also in 4 projects that use this

  • +1 more from getcompanion-ai

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the search returns many sessions, offer to narrow by:

    line 81
  2. Very specific:

    If the user wants to know what happened in a session, pass it to session-review.

    line 88
  3. Distinctive:

    If search returns zero, broaden the criteria (wider time range, fewer filters) before reporting "not found."

    line 103
  4. Distinctive:

    Always return session URLs — the user may want to watch the replay in Fullstory.

    line 104
  5. Very specific:

    If the user wants to understand *what happened* in the sessions found, delegate to session-review or session-context — don't try to do it …

    line 106

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Session Search

Find sessions by searching across user properties, device, browser, custom events, and pages — without needing a metric or segment first.

When to Use

  • "Find sessions where users on Safari mobile visited /checkout"
  • "Show me sessions from enterprise users who saw an error"
  • "Find the session for user ID 84721 from yesterday"
  • "Show me sessions where custom event 'trial_started' fired"
  • "Find sessions from users in Germany who visited the pricing page"

Mental Model

Session search is for targeted lookups when you know who or what you're looking for. It's different from metrics (which aggregate across many users) and opportunities (which rank by frustration). Session search is a point query: "find me these specific sessions."

Workflow

Step 1: Clarify the search criteria

What does the user know? Common search axes:

CriterionTool
Specific user ID or emailfullstory:get_user_profile → sessions
Device type or browserfullstory:get_sessions with device/browser filters
Page URLfullstory:get_sessions with page filter
Custom eventfullstory:get_sessions with event filter
User property (plan, role, country)Build segment → fullstory:get_sessions(segment_id)
Time rangeAlways specify — narrow is faster

Step 2: Execute the search

By user ID or email:

fullstory:get_user_profile(userIdentifier="user@example.com")
→ returns user's recent sessions with device_id and session_id
→ load each session through session-context agent

By device/browser/page:

fullstory:get_sessions(
  device="mobile",
  browser="safari",
  page="/checkout",
  time_range="last_7_days",
  limit=5
)

By user property (plan, role, country):

fullstory:build_segment("users on enterprise plan in Germany")
fullstory:get_sessions(segment_id=segment_id, limit=5)

By custom event:

fullstory:get_sessions(
  event="trial_started",
  time_range="last_30_days",
  limit=5
)

Step 3: Present results

For each session found, show:

  • Session date/time
  • User identifier (if available)
  • Device and browser
  • Key pages visited
  • Session URL (so the user can open it in Fullstory)

If the search returns many sessions, offer to narrow by:

  • Adding a time range constraint
  • Adding a device/page filter
  • Combining criteria (e.g., "enterprise users on mobile who visited /checkout")

Step 4: Investigate (if needed)

If the user wants to know what happened in a session, pass it to session-review. If they want to know what a specific user did across multiple sessions, use user-journey.

Common Search Patterns

QuestionApproach
"Show me user 84721's sessions"get_user_profile → sessions
"Find Safari mobile sessions on /checkout"get_sessions(device="mobile", browser="safari", page="/checkout")
"Enterprise users who hit errors"Build enterprise segment + build error metric → get_sessions(metric_id)
"Sessions where trial_started fired"get_sessions(event="trial_started")
"Sessions from Germany on pricing page"Build Germany segment → get_sessions(segment_id, page="/pricing")

Guidelines

  • Narrow time ranges first — scanning 90 days of sessions is slow. Default to last_7_days.
  • If search returns zero, broaden the criteria (wider time range, fewer filters) before reporting "not found."
  • Always return session URLs — the user may want to watch the replay in Fullstory.
  • For user property searches (plan, role, country), building a segment is one extra call but much faster than scanning all sessions.
  • If the user wants to understand what happened in the sessions found, delegate to session-review or session-context — don't try to do it here.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.