Resume engagement

Skill cynco-labs/ai-accounting-skills/accounting-engagement/skills/resume-engagement

Agent-native accounting skills for Claude Code — folder dump → books → Beancount + Fava. MPERS, smart intake, hard gates.

Install

npx -y skills add cynco-labs/ai-accounting-skills --skill resume-engagement

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

2 things to look at

29 days oldThe repository was created 29 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
2 stars2 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

Resume from engagement_state.json. Use when continue client, pick up books, or where we left off.

SKILL.md

1.6 KB, 393 tokens by cl100k_base, as published. Nobody here has run it

/resume-engagement

Purpose

Make multi-session work safe. Disk is truth.

Workflow

Find engagement_state.json:

cwd, or
cwd/clients/*/engagement_state.json, or
path user provides, or
fixtures path if testing

Load state + shared/agent-runtime.md + shared/operator-lens.md + references/stage_artifacts.md
If operator missing → resolve once and write it (do not re-ask if inferable)
Verify artifacts listed in state.artifacts still exist
Run python3 scripts/validate_engagement_artifacts.py <client_dir> if workpapers present
Print status board:

## Resume — [legal_name] · [operator] · [engagement_type] · period [fy / on-disk]
- Stage: [current_stage] ([status])
- Completed: [stages_completed]
- Blockers: [blockers or none]
- Open queries: [n]
- Next: [concrete next skill/action]

If status == blocked → work the blocker first
If status == waiting_on_user and open_queries non-empty → re-issue unanswered asks via structured user-question tool (shared/user-questions.md) — do not only re-print queries.md
Else continue from current_stage by loading that stage’s SKILL.md
Do not restart the pipeline from setup unless user says so

If no state file

Say so clearly. Offer:

engagement-setup for a new client
full-engagement-pipeline if they dumped files

Completion

Done when: state loaded, one-line status shown, next stage skill identified (or blockers listed).

What ships with it

Read from the repository

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