EJ

Finalizes an EJS session by summarizing interactions, decisions, and outcomes into structured documentation.

Install

mkdir -p .claude/skills/ejs-session-wrapup-mcfuzzysquirrel && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15964" && unzip -o skill.zip -d .claude/skills/ejs-session-wrapup-mcfuzzysquirrel && rm skill.zip

Installs to .claude/skills/ejs-session-wrapup-mcfuzzysquirrel

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Finalize an Engineering Journey System (EJS) session by completing all journey sections, populating machine extracts, evaluating the ADR decision rubric, and optionally creating an ADR document.
194 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Review the session journey for completeness
  • Finalize sections like Interaction Summary and Agent Collaboration Summary
  • Populate machine-readable extracts for session continuity
  • Evaluate the ADR decision rubric for architectural decisions
  • Create an Architecture Decision Record (ADR) if warranted
  • Update the `decision_detected` field based on ADR necessity

How it works

This skill reviews and completes all sections of an Engineering Journey System (EJS) session, populates machine extracts, evaluates the ADR decision rubric, and creates an ADR document if specific criteria are met.

Inputs & outputs

You give it
Current journey file at `ejs-docs/journey/YYYY/ejs-session-YYYY-MM-DD-<seq>.md`
You get back
A finalized journey file, populated machine extracts, and an optional ADR document

When to use ejs-session-wrapup

  • Ship project phase
  • Checkpoint session context
  • Finalize engineering journey
  • Document session decisions

About this skill

EJS Session Wrap-Up

Use this skill when a session is ending — for example when the user says "wrap up", "finalize session", "end session", "ship it", "commit this", or "commit and push".

This skill also applies for context-threshold checkpoints — proactive mid-session saves that prevent documentation loss if context runs out. See the Checkpoint vs. Full Finalization section below for the differences.

Steps

  1. Review the Session Journey for completeness

    • Read the current journey file at ejs-docs/journey/YYYY/ejs-session-YYYY-MM-DD-<seq>.md
    • Identify any sections that are incomplete or missing context.
  2. Finalize all sections Complete each section with coherent summaries:

    • Interaction Summary — ensure all key exchanges are documented
    • Agent Collaboration Summary — which agents participated and their contributions
    • Sub-Agent Contributions — if sub-agents were involved, ensure their decisions and handoffs are captured
    • Agent Influence — suggestions adopted vs. rejected, human overrides
    • Experiments / Evidence — what was tried and what happened
    • Iteration Log — pivots, reversals, or refinements
    • Decisions Made — all decisions with reason and impact
    • Key Learnings — technical, prompting, and tooling insights
    • If Repeating This Work — do this, avoid this, watch out for
    • Future Agent Guidance — prefer/avoid patterns for future agents
  3. Populate machine extracts Fill in the ## MACHINE EXTRACTS section with structured summaries:

    • INTERACTION_EXTRACT — compact summary of the collaboration trail
    • DECISIONS_EXTRACT — list of decisions with rationale
    • LEARNING_EXTRACT — transferable insights
    • AGENT_GUIDANCE_EXTRACT — guidance for future agents
    • SUB_AGENT_EXTRACT — sub-agent contributions (if applicable)
  4. Evaluate the ADR decision rubric Create an ADR only if at least one of these criteria is met:

    • Introduces or changes a system boundary (service, datastore, topology)
    • Changes a public contract (API, schema, protocol)
    • Alters security, privacy, or compliance posture
    • Requires choosing among credible alternatives with meaningful trade-offs
    • Has long-lived or hard-to-reverse consequences
    • Changes engineering process or workflow for future work
  5. Update decision_detected field

    • Set to true if an ADR is warranted, false otherwise.
  6. Create ADR if warranted

    • Use template: ejs-docs/adr/0000-adr-template.md
    • Save to: ejs-docs/adr/NNNN-<kebab-title>.md (next available number)
    • Link the ADR back to the session journey and vice versa via adr_links.
  7. Confirm finalization

    • Inform the user: "Session finalized: ejs-session-YYYY-MM-DD-<seq>"
    • If an ADR was created, mention it: "ADR NNNN created: <title>"

Contextual References

  • ADR template: ejs-docs/adr/0000-adr-template.md
  • Lifecycle patterns: ejs-docs/session-lifecycle-patterns.md
  • Database tool: scripts/adr-db.py

Key Principle

By session end, most of the journey should already be populated from continuous updates. Finalization is a quick review and completion step, not a full reconstruction effort.

Checkpoint vs. Full Finalization

AspectCheckpoint (mid-session)Full Finalization (session end)
TriggerContext getting large, 3+ unsaved interactions, before heavy operations, 5+ exchanges since last saveUser signals session end
Sections updatedInteraction Summary, Decisions Made, Experiments, Iteration Log, Key LearningsAll sections reviewed and completed
Machine extractsNot populatedPopulated in full
ADR rubricNot evaluatedEvaluated; ADR created if warranted
GoalPreserve work-in-progress against context lossProduce a coherent, complete record

When to Perform a Checkpoint

  • 3+ unsaved interactions have accumulated since the last save (an interaction is one human prompt and the corresponding agent response)
  • A significant decision has been made but not yet written to the journey
  • A large, context-intensive operation is about to start
  • 5+ exchanges have occurred since the last journey file save
  • Substantial work completed but user has not signalled session end

When not to use it

  • When the session is not ending
  • When a context-threshold checkpoint is not needed
  • When the user does not signal session end

Limitations

  • ADR creation is conditional on specific criteria being met
  • The skill requires an existing journey file to review
  • Finalization is a review and completion step, not a full reconstruction

How it compares

This skill provides a structured, automated process for finalizing an EJS session and creating ADRs, which differs from manual documentation and decision tracking.

Compared to similar skills

ejs-session-wrapup side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ejs-session-wrapup (this skill)05moNo flagsIntermediate
session-handoff132moReviewBeginner
spec-to-backlog84moNo flagsIntermediate
create-handoff36moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

session-handoff

davila7

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

1370

spec-to-backlog

atlassian

Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When Claude needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.

868

create-handoff

parcadei

Create handoff document for transferring work to another session

331

moai-workflow-project

modu-ai

Integrated project management system with documentation, language initialization, and template optimization modules. Use when setting up projects, generating documentation, configuring multilingual support, or optimizing templates.

29

granola-core-workflow-b

jeremylongshore

Post-meeting note processing and sharing workflow with Granola. Use when reviewing meeting notes, sharing with team members, or processing action items after meetings. Trigger with phrases like "granola post meeting", "share granola notes", "granola follow up", "process meeting notes", "granola action items".

00

reporting

comeredon

Final pipeline execution report format. Defines the structure, agent registry, Mermaid gantt chart, and change summary. Used by AnalystAgent in Phase 6.

00

Search skills

Search the agent skills registry