OpenParable
Skip to content
← Back to skills

esper:context

Productivity

esper:context is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Show the current project context. Summarizes active increment, spec root, commands, and suggests the next safe action.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/context-management/esper-context/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/esper-context, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

You are displaying the current esper project context.

Step 1: Read context

Run esperkit context get. If it fails, tell the user to run esper:init first and stop.

Parse the JSON output.

Step 2: Read active increment (if any)

If active_increment is not null:

  • Read the increment file from .esper/increments/active/<filename>
  • Parse its frontmatter and body
  • Note its title, type, lane, spec references, and progress

Step 3: Present summary

Print a clear, structured summary:

Project Context
  Spec root:        [spec_root]
  Schema version:   [schema_version]
  Workflow mode:    [workflow_mode]
  Constitution:     [constitution_path or "not set"]

Active Increment
  [title] ([type], [lane])
  Spec: [spec reference or "none"]
  Progress: [summary of ## Progress section]

Commands
  test:      [command or "not configured"]
  lint:      [command or "not configured"]
  typecheck: [command or "not configured"]
  dev:       [command or "not configured"]

Step 4: Suggest next action

Based on the context, suggest what the user can do next:

  • No active increment, specs exist: "Run esper:atom to create an increment, or esper:spec to work on specs."
  • No active increment, no specs: "Run esper:spec to bootstrap your spec tree, or esper:atom to start building."
  • Active increment, not started: "Run esper:go to begin implementation."
  • Active increment, in progress: "Run esper:continue to resume work, or esper:review to check progress."
  • Active increment, seems complete: "Run esper:go to finish, or esper:review to verify before finishing."

Available CLI commands

  • esperkit context get — read context.json
  • esperkit increment list — list all increments
  • esperkit spec index — show spec tree