dev-session

jezweb/claude-skills · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/jezweb/claude-skills --skill dev-session
0 commentsdiscussion
summary

Structured progress tracking for multi-session development work with durable handoff files.

  • Four core modes: start a new session with project orientation, checkpoint progress with WIP commits and learnings capture, resume from SESSION.md with git diff context, and wrap sessions with completeness checks
  • Automatically manages SESSION.md files (progress log, current position, blockers, resume instructions) and updates CLAUDE.md with discovered patterns and gotchas
  • Reads git history and
skill.md

Dev Session

Manage multi-session development work with structured progress files, checkpoint commits, and durable learnings. Produces SESSION.md files that survive context compaction and enable clean handoff between sessions.

Operating Modes

Mode 1: Start Session

When: Beginning multi-step work, "start session", "new session for [feature]"

  1. Check if SESSION.md already exists in the project root
  2. Pre-fill fields:
    • Project: from CLAUDE.md or directory name
    • Branch: from git branch --show-current
    • Last Updated: current timestamp
    • Phase: ask user what they're working on
  3. Read the project's CLAUDE.md to orient on context
  4. Present a brief summary: "Session started. Working on [phase] on branch [branch]."

Mode 2: Checkpoint

When: "checkpoint", major milestone reached, before risky changes, context getting large

  1. Update SESSION.md:
    • Add completed items to What Works
    • Update Current Position with exact location (file paths, line numbers)
    • Clear resolved Blockers, add new ones
    • Write concrete Resume Instructions
  2. Capture learnings:
    • If any patterns, gotchas, or commands were discovered during work, add them to CLAUDE.md
    • One line per concept — concise, not verbose
  3. Git checkpoint:
    git add -A && git commit -m "WIP: [what was accomplished]"
    
  4. Record the commit hash in SESSION.md under Checkpoint
  5. Confirm: "Checkpointed at [hash]. SESSION.md updated."

Mode 3: Resume Session

When: "resume", "continue from last session", "where were we", start of a new conversation

  1. Read SESSION.md — if missing, inform user and offer to start a new session
  2. Read the project's CLAUDE.md for context
  3. Check what's changed since the recorded checkpoint:
    git log --oneline [checkpoint-hash]..HEAD
    
  4. Check for uncommitted changes: git status
  5. Present a summary:
    • Phase: what we were working on
    • Position: where we left off
    • Changes since: any commits or modifications since checkpoint
    • Blockers: anything unresolved
    • Suggested next step: first item from Resume Instructions

Mode 4: Wrap Session

When: "wrap session", "done for now", "save progress", ending a session

  1. Run a full checkpoint (Mode 2)
  2. Review SESSION.md for completeness:
    • Are Resume Instructions concrete enough for a fresh session to continue?
    • Is Current Position specific (file paths, not vague descriptions)?
  3. If the phase is complete:
    • Collapse the phase summary to 2-3 lines
    • Clear Resume Instructions or note "Phase complete — ready for next phase"
  4. Confirm: "Session wrapped. Resume with 'resume session' next time."

When to Use

Scenario Use this skill?
Multi-phase feature spanning 2+ sessions Yes
Work that might hit context compaction Yes
Before making risky or destructive changes Yes (checkpoint first)
Quick bug fix or single-file edit No
Single-session task with clear scope No

SESSION.md Principles

  • Track progress, not architecture — SESSION.md is a work log, not project documentation
  • Concrete over vague — "Resume at src/auth.ts:42, implement token refresh" beats "Continue auth work"
  • Collapse completed work — finished phases become 1-2 line summaries
  • Keep under 100 lines — if it's longer, collapse more aggressively

Autonomy Rules

  • Just do it: Read SESSION.md, read CLAUDE.md, check git status/log, present summaries
  • Brief confirmation: Creating new SESSION.md, committing WIP checkpoints
  • Ask first: Overwriting an existing SESSION.md, deleting session data

Reference Files

When Read
Creating a new SESSION.md references/session-template.md
Context compaction tips, what survives references/compaction-survival.md
how to use dev-session

How to use dev-session on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add dev-session
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/jezweb/claude-skills --skill dev-session

The skills CLI fetches dev-session from GitHub repository jezweb/claude-skills and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/dev-session

Reload or restart Cursor to activate dev-session. Access the skill through slash commands (e.g., /dev-session) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.632 reviews
  • Amina Yang· Dec 28, 2024

    Solid pick for teams standardizing on skills: dev-session is focused, and the summary matches what you get after install.

  • Dhruvi Jain· Dec 20, 2024

    I recommend dev-session for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Harper Nasser· Dec 12, 2024

    dev-session is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Anaya Torres· Nov 19, 2024

    dev-session has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Oshnikdeep· Nov 11, 2024

    Useful defaults in dev-session — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Tariq Perez· Nov 3, 2024

    dev-session reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Daniel Okafor· Oct 22, 2024

    I recommend dev-session for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Amelia Dixit· Oct 10, 2024

    Keeps context tight: dev-session is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Ganesh Mohane· Oct 2, 2024

    dev-session is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Amelia Kapoor· Sep 21, 2024

    dev-session is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

showing 1-10 of 32

1 / 4