ejs-session-init
Starts a new development session by setting up metadata and tracking logs for project history.
Install
mkdir -p .claude/skills/ejs-session-init && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15249" && unzip -o skill.zip -d .claude/skills/ejs-session-init && rm skill.zipInstalls to .claude/skills/ejs-session-init
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.
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.Key capabilities
- →Refresh the EJS database index
- →Determine a session ID with a daily sequence
- →Create a Session Journey file from a template
- →Populate frontmatter fields in the Session Journey file
- →Capture the user's stated goal or task description
How it works
The skill refreshes the EJS database index, generates a session ID, and creates a Session Journey file by copying a template. It then populates initial metadata and captures the user's problem or intent.
Inputs & outputs
When to use ejs-session-init
- →Start a new task session
- →Create session journey file
- →Sync ADR database
- →Log development progress
About this skill
EJS Session Initialization
Use this skill when a session is starting — for example when the user says "initialize session", "start session", "create session journey", or begins work on a new task, feature, or bug fix.
Steps
-
Refresh the EJS database index
python scripts/adr-db.py sync -
Determine the session ID
- Format:
ejs-session-YYYY-MM-DD-<seq>(2-digit daily sequence) - Check
ejs-docs/journey/YYYY/for existing sessions today and increment the sequence number.
- Format:
-
Create the Session Journey file
- Copy the template from
ejs-docs/journey/_templates/journey-template.md - Save to
ejs-docs/journey/YYYY/ejs-session-YYYY-MM-DD-<seq>.md
- Copy the template from
-
Populate initial metadata Fill in the frontmatter fields:
session_id— the generated session IDauthor— the human user (if known)date— today's date (YYYY-MM-DD)repo— current repository namebranch— current git branchagents_involved— list the active agents (e.g.,[copilot])decision_detected: false— initial value; updated at session endadr_links: []— populated if an ADR is created later
-
Capture initial Problem / Intent
- Write the user's stated goal or task description into the Problem / Intent section.
-
Confirm initialization
- Inform the user:
"Session initialized: ejs-session-YYYY-MM-DD-<seq>"
- Inform the user:
Contextual References
- Session Journey template:
ejs-docs/journey/_templates/journey-template.md - 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
Initialize early, capture context while it's fresh. A well-initialized session reduces the burden at session end and produces higher-quality documentation.
When not to use it
- →When a session is not starting
- →When the user is not beginning work on a new task, feature, or bug fix
Limitations
- →Requires an existing `ejs-docs/journey/_templates/journey-template.md` file
- →Requires an existing `scripts/adr-db.py` tool
- →Session ID format is fixed to `ejs-session-YYYY-MM-DD-<seq>`
How it compares
This workflow automates the creation and initial population of a session journey file and metadata, unlike a manual process that would require individual steps for database sync, ID generation, file creation, and field entry.
Compared to similar skills
ejs-session-init side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ejs-session-init (this skill) | 0 | 5mo | Review | Beginner |
| decision-logger | 0 | 2mo | Review | Intermediate |
| conductor-validator | 1 | 4mo | No flags | Beginner |
| mighty | 0 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by McFuzzySquirrel
View all by McFuzzySquirrel →You might also like
decision-logger
alirezarezvani
Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.
conductor-validator
sickn33
Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.
mighty
indexedlabs
Use the `mt` tool to work with this repo’s Mighty graph: run `mt prime` at session start; prefer `mt search`/`mt tree`/`mt show` before reading code; create specs/decisions/tasks and link evidence; triage `mt inbox`; and close out with `mt closeout` then `mt commit`. For full workflow + templates, r
openspec-apply-change
PBH-BTN
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-bulk-archive-change
StrayDragon
Archive multiple completed changes at once. Use when archiving several parallel changes.
ejs-session-wrapup
McFuzzySquirrel
Initialize and manage EJS artifacts throughout session lifecycle (Session Journey initialization, continuous updates, and finalization; ADR only when significant)