Esper sync

Skill sichengchen/esper/skills/esper-sync

Tool-neutral, simple workflow layer for agentic, spec-driven software development. 🪄✨

Install

npx -y skills add sichengchen/esper --skill esper-sync

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Update spec files to match shipped implementation. Records sync notes in the increment and finishes it when complete.

SKILL.md

2.1 KB, 453 tokens by cl100k_base, as published. Nobody here has run it

You are synchronizing the spec tree with the shipped implementation.

Step 1: Read context

Run esperkit context get to determine the current state.

If no active increment, tell the user: "No active increment to sync. Run esper:atom first." and stop.

Step 2: Read the increment and specs

Read the active increment file from .esper/increments/active/<filename>. Read the referenced spec files (from spec: field and ## Spec Impact section). Run esperkit spec index to see the full spec tree.

Step 3: Inspect shipped implementation

Review the implementation changes:

Read the files listed in ## Files Affected
Check git log for recent commits related to this increment
Understand what was actually built vs what was planned

Step 4: Update spec files

For each spec file that needs updating:

Read the current spec: esperkit spec get <file>
Compare against the shipped implementation
Update the spec to reflect actual behavior:
- Add new sections for new features
- Update existing sections where behavior changed
- Remove sections for deprecated behavior
- Keep the declarative, present-tense style ("The system does X")
Write the updated spec file

Step 5: Record sync notes

Update the active increment's ## Spec Impact section with what was synced:

## Spec Impact
- [synced] product/behavior.md — updated authentication section
- [synced] interfaces/cli.md — added new command documentation
- [no-change] system/architecture.md — no updates needed

Step 6: Finish the increment

Once all specs are synced:

Confirm with the user that the sync is complete
Run esperkit increment finish <filename>
Print a summary of what was updated

Available CLI commands

esperkit context get — read context
esperkit spec index — show spec tree
esperkit spec get <file> — read a spec
esperkit increment finish <file> — finish the increment

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.