agentsclimarketplace

Resume

Skill mattjaikaran/meridian/skills/resume

Skill that gives AI coding agents persistent memory and quality enforcement

Install
npx -y skills add mattjaikaran/meridian --skill resume

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.

SKILL.md

2.2 KB, as published. Nobody here has run it

/meridian:resume — Deterministic Resume

Generate and load a resume prompt from SQLite state. Start exactly where you left off.

Arguments

  • (no args) — run pre-flight health check then generate resume prompt
  • --skip-health — skip the pre-flight health check

Procedure

Step 0: Pre-flight Health Check (skip if --skip-health)

PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from pathlib import Path
from scripts.health import run_health_check
result = run_health_check(Path('.'), do_repair=False)
print(json.dumps(result, indent=2))
"

If status is "warning" or "error", surface the findings to the user before continuing. Example output:

⚠ Health check found 2 warnings:

  • Phase 'Build API' (id=3) has been executing for 7.2h — may be stuck
  • Artifact dir '04-old-feature' has no DB phase record

Run /meridian:health --repair to auto-fix, or continue with --skip-health.

If status is "ok", proceed silently.

Step 1: Generate Resume Prompt

PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
from scripts.resume import generate_resume_prompt
print(generate_resume_prompt('.'))
"

Step 2: Display Resume

Print the full resume prompt so the agent can understand current state.

Step 3: Determine Next Action

The resume prompt always ends with a computed next action. Follow it:

  • activate_milestone → Activate the planned milestone
  • create_phases → Run /meridian:plan
  • gather_context → Dispatch context-gatherer subagent
  • create_plans → Generate plans for the phase
  • execute → Run /meridian:execute
  • execute_plan → Execute the specific plan shown
  • verify_phase → Run acceptance criteria verification
  • review_phase → Run /meridian:review
  • complete_phase → Mark phase complete
  • complete_milestone → Mark milestone complete
  • fix_failed_plan → Debug and retry the failed plan
  • unblock_phase → Address the blocker

Step 4: Announce Position

Tell the user where we are and what's next. Example:

Resuming MyApp — Phase 2: Features (executing) 2/4 plans complete. Next: execute "Add API routes" (wave 2). Ready to continue?

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.