skills.rest
hthor213
hthor213COMMUNITY
Explore all skills by this author →
GitHub

start

Read project artifacts and generate prioritized work plans for resumed development sessions.

Updated Mar 30, 2026
Search Tags:#git status#project onboarding#task prioritization#context awareness#spec alignment#cold start#dev session
One-click install
npx skills add https://github.com/hthor213/Axiom --skill start-hthor213
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: start
Source: https://github.com/hthor213/Axiom/tree/main/docs/template_skills/start
Command: npx skills add https://github.com/hthor213/Axiom --skill start-hthor213

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the wasted time and misalignment that occurs when resuming a dev session after time away, removing the need to manually hunt through specs, session notes, and task trackers to figure out where you left off and what to work on next.

Core Features & Use Cases

  • Full Project Context Aggregation: Automatically reads vision specs, session state, active tasks, backlog, and git status to build a complete picture of project state.
  • Spec Drift Detection: Flags misalignment between documented requirements and actual codebase state to prevent scope creep and outdated work.
  • Prioritized Action Planning: Recommends the highest-priority unblocked next step based on backlog and active work, with clear open questions and constraint checks.
  • Use Case: If you return from a week-long break to a feature development project, this Skill will pull all relevant project artifacts, check your git status and spec alignment, and tell you exactly what to work on first without any manual context gathering.

Quick Start

Invoke the start skill at the beginning of any dev session to get a full project status report and recommended next steps.

Frequently Asked Questions about start

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resume a software development session after time away without losing context?▼

To resume a software development session without context loss, you can aggregate project artifacts like vision specs and git status to generate actionable work plans. This eliminates manual context hunting by validating spec alignment and recommending the next unblocked task.

What is the best way to align actual codebase state with documented requirements?▼

Aligning actual codebase state with documented requirements involves spec drift detection to flag misalignment. By reading project artifacts and comparing them against the codebase, you identify outdated work and prevent scope creep before planning next steps.

How do I prioritize tasks for a cold start dev session?▼

Prioritizing tasks for a cold start dev session requires assessing backlog items, active work, and git status against project constraints. This generates a prioritized action plan highlighting the highest-priority unblocked next step with clear open questions.

Can I use this project onboarding approach with legacy SPEC.md formats?▼

Project onboarding supports legacy SPEC.md formats, new uninitialized projects, and numbered spec systems. It reads these project artifacts to assess spec health and session state, validating spec alignment without requiring specific framework versions.

Does automated session onboarding detect spec drift in unblocked tasks?▼

Automated session onboarding detects spec drift by comparing documented requirements against the actual codebase state. It flags misalignment to prevent scope creep and evaluates constraints to ensure recommended next steps remain unblocked.

What are the limitations of automated context aggregation for dev session onboarding?▼

Automated context aggregation for dev session onboarding relies on reading existing project artifacts like specs and git status. It cannot generate work plans for completely empty uninitialized projects lacking any documented vision specs or backlog data.

Related Skills

Explore More Software Engineering Skills→
2lab-ai2lab-ai
36

plan-new-task

Propose development tasks and generate STV specs and trace artifacts from git history.

Official
Intermediate
nthpaulnthpaul

get-pr-comments

Summarize active pull request comments into prioritized actions and open questions.

Community
Intermediate
cofincofin
15

beads

Manage persistent task memory across AI agent sessions.

Community
Advanced
miles990miles990

subagent-driven-development

Dispatch fresh subagents to execute multi-step implementation plans with two-stage reviews.

Community
Advanced