ejs-session-wrapup

Étoiles0

Forks0

Mis à jour11 mars 2026 à 19:15

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.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

McFuzzySquirrel

McFuzzySquirrel/ezansiedgeai-small

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	ejs-session-wrapup
description	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.

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".

Steps

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.
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
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)
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
Update decision_detected field
- Set to true if an ADR is warranted, false otherwise.
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.
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.

Plus depuis ce dépôt

même dépôt

ejs-story-builder

McFuzzySquirrel/ezansiedgeai-small

Build a complete end-to-end project story from EJS journey and ADR files. Use when: "build story", "generate story", "tell the story", "project narrative", "end-to-end story", "full story", "what happened", "project history", "summarize all sessions". Reads journey sessions and ADRs, synthesizes a chronological narrative covering what was built, how it was built, and collaboration perspectives (human, human+agent, agent, agent-to-agent). Outputs to chat and saves to ejs-docs/narratives/.

2026-04-110

create-content-chunk

McFuzzySquirrel/ezansiedgeai-small

Author a CAPS-aligned Markdown content chunk for an eZansiEdgeAI content pack. Use this skill each time a new curriculum topic chunk is created — there will be 3+ chunks and 2+ worked examples per Grade 6 Maths topic across Terms 1–4.

2026-03-140

scaffold-android-feature

McFuzzySquirrel/ezansiedgeai-small

Scaffold a new Android feature module for eZansiEdgeAI with standard structure: Activity/Fragment or Composable, ViewModel, Repository interface, DI setup, and test stubs. Use this skill each time a new feature screen is added (chat, topics, profiles, preferences, library).

2026-03-140

ejs-session-init

McFuzzySquirrel/ezansiedgeai-small

Initialize an Engineering Journey System (EJS) session by creating a Session Journey file, refreshing the ADR/journey database index, and setting up metadata for continuous recording throughout the session.

2026-03-110

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".

Steps

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.

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

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)

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

Update decision_detected field

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

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.

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.