pull-together-agent-transcript-goal-context

Stars2

Forks0

UpdatedMay 15, 2026 at 14:13

Build context around what a user was trying to accomplish in a Transcript Segment when the Goal is not self-evident from the user message (segment.trigger.text) alone. Reaches into git repos (commits, PRs, branch state at the time of the session), issue trackers, and any other systems referenced in the message. Use this skill when analyze-agent-transcript-user-prompt cannot confidently confirm a Goal.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

pulsemcp

pulsemcp/ai-artifacts

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name	pull-together-agent-transcript-goal-context
description	Build context around what a user was trying to accomplish in a Transcript Segment when the Goal is not self-evident from the user message (segment.trigger.text) alone. Reaches into git repos (commits, PRs, branch state at the time of the session), issue trackers, and any other systems referenced in the message. Use this skill when analyze-agent-transcript-user-prompt cannot confidently confirm a Goal.
user-invocable	false

Pull together goal context

Helper for analyze-agent-transcript-user-prompt. Pulls just enough external context to make a low-confidence Goal extraction high-confidence.

Inputs

segment: the Segment whose Goal needs disambiguation. The user message lives in segment.trigger.text (when trigger.source == "user"); the event span lives in segment.meta.event_range.
transcript.json: the OpenTranscripts Transcript document. Dereference event ids from segment.meta.event_range into transcript.json events[] for the surrounding events — they may name a file, a PR, an issue, a service, etc.
external_context (optional): external-context.json if present — supplies project, branch, ticket, and session-timing context, often resolving the Goal without any external pull.

Output

{
  "goal": "<refined one-sentence goal>",
  "goal_certainty": "high" | "medium" | "low",
  "evidence": [
    {"source": "git" | "github_pr" | "github_issue" | "linear" | "...", "ref": "...", "snippet": "..."}
  ],
  "still_unclear": "<what remains ambiguous, if anything>"
}

This is a helper invoked by analyze-agent-transcript-user-prompt, not an analyzer the orchestrator writes into a findings.<kind>.json — its output is consumed in-process, so it carries no id / segment_id / analyzer wrapper.

Sequencing checklist

Inventory the references in segment.trigger.text, external_context, and the events in segment.meta.event_range (file paths, PR/issue numbers, branch names, service names, commit shas, ticket ids)
For each reference, pull the smallest amount of external context that resolves the ambiguity:
- Git: git log around the session timestamp, git show <sha>, the diff on the branch at that time
- GitHub PRs/issues: gh pr view, gh issue view, including the description and the most recent few comments
- Other trackers / docs: only if directly named in the prompt and an MCP / CLI is available
Stop as soon as the Goal is high-confidence — do not bulk-pull
Return the refined Goal and the evidence supporting it

Notes

This skill is read-only. It must not modify any external system, even by accident. No comments on PRs, no edits to issues, no force-pushes.
Be aggressive about delegating verbose external pulls (full PR threads, large diffs) to a subagent so the analysis context window stays small.
If after reasonable effort the Goal is still unclear, return goal_certainty: "low" with still_unclear populated. The orchestrator will mark the Segment "tentative" rather than fabricate a Goal.

More from this repository

same repository

analyze-agent-transcript

pulsemcp/ai-artifacts

Orchestrator for analyzing a single Claude Code session transcript. Takes the tmp folder produced by get-claude-code-transcript-from-local, requires the Segment tree from decompose-agent-transcript-into-transcript-segments (invoking it if the tmp folder doesn't already have one), drives the per-Segment analyzers across four buckets (outcomes, prompts, skills, mcp) and writes their conclusions as findings.<kind>.json — and stops there. It produces only that transcript's four findings files; there is no per-transcript report. The report is a batch-end step: once every transcript of interest has been analyzed, synthesize-agent-transcript-analysis-report runs once over the whole batch's findings. Use this skill when the user wants a single session analyzed, a "how could this have gone better" review, or to surface Skill/MCP opportunities from real usage.

2026-06-032

analyze-cross-agent-transcript-patterns

pulsemcp/ai-artifacts

Cross-cutting analyzer. Given the per-transcript findings.*.json sets of several already-analyzed transcripts (the phase-3 outputs of analyze-agent-transcript — findings.outcomes/prompts/skills/mcp.json), surface patterns that no single transcript reveals: Segments that could have been shorter with hindsight, user prompts that repeat the same nudges or context, recurring missing Skills / MCP tools across sessions, time-spend patterns where the agent consistently takes 5x what a human would. Still phase-3 labeling, but runs once over the whole batch — last in phase 3, after every transcript has been analyzed — as an optional pre-report augmentation, not interleaved per transcript and not fanned out by the orchestrator. Runs on the raw per-transcript findings; there is no per-transcript report, and reading raw findings is what catches the long tail that only matters in aggregate. Writes findings.cross-transcript.json into the batch_dir for synthesize-agent-transcript-analysis-report to pick up. Use this skill w

2026-06-032

analyze-agent-transcript-failure-hypothesis

pulsemcp/ai-artifacts

Per-Segment analyzer. Produces an improvement hypothesis for every Failure Outcome and every retro-Failure (a Correction trigger at the next Segment's head implies the prior Segment failed even if it didn't recognize it). Both user-source and agent-source Corrections qualify as retro-Failure signals; user-source is the stronger signal. Each hypothesis names the most plausible root cause — usually a missing Skill, a Skill whose description didn't trigger, a missing MCP capability, or a user-side prompting issue — and the concrete change that would have prevented the failure. Fed by analyze-agent-transcript; outputs flow into the Prompting / Skills / MCP recommendation buckets of the final report.

2026-06-032

analyze-agent-transcript-prompt-ambition

pulsemcp/ai-artifacts

Per-user-source-New-Trigger analyzer (the case formerly known as the Initial Prompt). Flags user-typed Triggers that look like they under-scoped the work — short, narrow, followed quickly by another user-source New Trigger on a related Goal. Pattern suggests the user split work the agent could have one-shotted with a more ambitious prompt. Output feeds the human-prompting recommendation bucket, and may also surface deterministic-trigger opportunities (the ideal end-state for user-source New Triggers).

2026-06-032

analyze-agent-transcript-user-prompt

pulsemcp/ai-artifacts

Analyze a single user-source Trigger attached to a Transcript Segment. Classify it (question vs delegation), confirm the Segment's Goal, and assess whether the Segment closed the loop on that Goal. The Trigger kind (New vs Correction) and source (user) are already set by the segmenter; this skill consumes them. If the Goal isn't self-evident, delegate to pull-together-agent-transcript-goal-context. Output feeds the "human prompting" recommendation bucket of analyze-agent-transcript.

2026-06-032

synthesize-agent-transcript-analysis-report

pulsemcp/ai-artifacts

Phase-4 synthesis — runs once over a whole batch of analyzed transcripts. Given the per-transcript tmp_dirs that make up the batch, reads every transcript's phase-3 findings (findings.outcomes/prompts/skills/mcp.json) plus findings.cross-transcript.json when present, and synthesizes them into ONE final report of actionable next steps across three buckets: human prompting, Skills (create/modify/delete), and MCP servers (create/modify/delete). Writes findings.report.json (the reviewable recommendation slate) and report.md (the human-readable report grouped by priority, including a key-stats block aggregated across the batch), and a multi-page HTML site that drills from the report down into every intermediate decision the pipeline made — report.html landing + recommendations/rec-NNN.html per rec + sessions/<tag>.html per transcript + segments/<tag>--<SID>.html per Segment (its decomposition plus every phase-3 finding tagged to it) + optional external-context and cross-transcript pages — into a batch_dir. Use onc

2026-06-032

name	pull-together-agent-transcript-goal-context
description	Build context around what a user was trying to accomplish in a Transcript Segment when the Goal is not self-evident from the user message (segment.trigger.text) alone. Reaches into git repos (commits, PRs, branch state at the time of the session), issue trackers, and any other systems referenced in the message. Use this skill when analyze-agent-transcript-user-prompt cannot confidently confirm a Goal.
user-invocable	false

Pull together goal context

Helper for analyze-agent-transcript-user-prompt. Pulls just enough external context to make a low-confidence Goal extraction high-confidence.

Inputs

segment: the Segment whose Goal needs disambiguation. The user message lives in segment.trigger.text (when trigger.source == "user"); the event span lives in segment.meta.event_range.
transcript.json: the OpenTranscripts Transcript document. Dereference event ids from segment.meta.event_range into transcript.json events[] for the surrounding events — they may name a file, a PR, an issue, a service, etc.
external_context (optional): external-context.json if present — supplies project, branch, ticket, and session-timing context, often resolving the Goal without any external pull.

Output

{
  "goal": "<refined one-sentence goal>",
  "goal_certainty": "high" | "medium" | "low",
  "evidence": [
    {"source": "git" | "github_pr" | "github_issue" | "linear" | "...", "ref": "...", "snippet": "..."}
  ],
  "still_unclear": "<what remains ambiguous, if anything>"
}

Sequencing checklist

Inventory the references in segment.trigger.text, external_context, and the events in segment.meta.event_range (file paths, PR/issue numbers, branch names, service names, commit shas, ticket ids)
For each reference, pull the smallest amount of external context that resolves the ambiguity:
- Git: git log around the session timestamp, git show <sha>, the diff on the branch at that time
- GitHub PRs/issues: gh pr view, gh issue view, including the description and the most recent few comments
- Other trackers / docs: only if directly named in the prompt and an MCP / CLI is available
Stop as soon as the Goal is high-confidence — do not bulk-pull
Return the refined Goal and the evidence supporting it

Notes

This skill is read-only. It must not modify any external system, even by accident. No comments on PRs, no edits to issues, no force-pushes.
Be aggressive about delegating verbose external pulls (full PR threads, large diffs) to a subagent so the analysis context window stays small.
If after reasonable effort the Goal is still unclear, return goal_certainty: "low" with still_unclear populated. The orchestrator will mark the Segment "tentative" rather than fabricate a Goal.