Resume

Skill mattjaikaran/meridian/skills/resume

Skill that gives AI coding agents persistent memory and quality enforcementFrom the repository description

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, 566 tokens by cl100k_base, 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?

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most hr recruiting skills give in 566 tokens

Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07

Quantify achievements with specific metricsin 14 of 356, across 6 files
Keep the resume under two pagesin 14 of 356, across 6 files
Request the full job description if not providedin 12 of 356, across 4 files
Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
Map candidate experience to job requirementsin 11 of 356, across 3 files
Ask if the user wants adjustmentsin 11 of 356, across 3 files
Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
Request candidate background details if not providedin 10 of 356, across 2 files
Format experience bullets as action verb plus resultin 10 of 356, across 2 files
Ask for missing inputs before startingin 10 of 356, across 9 files
Use exact job description terminologyin 9 of 356, across 1 file

Said here and by no other author read

run the pre-flight health check
surface warnings or errors to the user
skip the health check if requested
generate the resume prompt from the database
print the full resume prompt
follow the computed next action

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.