resume
alirezarezvani/claude-skills
Resume a paused experiment, read history, and continue iterating from where you left off.
What is resume?
Resumes a paused autoresearch experiment by checking out the experiment branch, loading all historical results, and summarizing progress. Use when you need to pick up a previously started experiment and decide on the next iteration strategy.
- List available experiments with their status (active/paused/done)
- Checkout the experiment branch and load full configuration and strategy
- Read complete results history from results.tsv to understand all prior iterations
- Display current state including target file, metric, experiment counts, best result, and recent patterns
- Offer next-action options: single iteration, autonomous loop, or results review
How to install resume
npx skills add https://github.com/alirezarezvani/claude-skills --skill resume- Git repository with autoresearch experiment branches (autoresearch/{domain}/{name})
- Experiment metadata in .autoresearch/{domain}/{name}/ directory (config.cfg, program.md, results.tsv)
- Python environment with setup_experiment.py script available
How to use resume
- 1.Run /ar:resume with optional experiment name (e.g., /ar:resume engineering/api-speed)
- 2.If no experiment specified, view the list and select one
- 3.Review the summarized state including target, metric, experiment counts, and best result
- 4.Choose next action: single iteration (/ar:run), autonomous loop (/ar:loop), or manual review
- 5.The skill will hand off to the selected mode with the experiment pre-selected
Use cases
- Resume an optimization experiment after context limit or pause
- Review progress on a long-running performance tuning task
- Understand what has been tried and what patterns emerged before continuing
- Pick up an experiment from a previous session and decide on next steps
- Hand off to single-run or loop mode after assessing current state
- Researchers running autoresearch experiments
- Performance optimization engineers
- Developers iterating on code improvements over multiple sessions
- Teams managing long-running experiment workflows
resume FAQ
Run /ar:resume without arguments to list all available experiments with their status and let you pick one.
It checks the age of results.tsv in each experiment directory to infer status (recent = active, old = paused, no results = not started).
Yes, the skill reads the full results.tsv file and displays patterns from recent experiments, showing which types of changes were kept or discarded.
If you pick single iteration, it hands off to /ar:run; if loop, it hands off to /ar:loop with the experiment pre-selected.
Full instructions (SKILL.md)
Source of truth, from alirezarezvani/claude-skills.
name: "resume" description: "Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment." command: /ar:resume
/ar:resume — Resume Experiment
Resume a paused or context-limited experiment. Reads all history and continues where you left off.
Usage
/ar:resume # List experiments, let user pick
/ar:resume engineering/api-speed # Resume specific experiment
What It Does
Step 1: List experiments if needed
If no experiment specified:
python {skill_path}/scripts/setup_experiment.py --list
Show status for each (active/paused/done based on results.tsv age). Let user pick.
Step 2: Load full context
# Checkout the experiment branch
git checkout autoresearch/{domain}/{name}
# Read config
cat .autoresearch/{domain}/{name}/config.cfg
# Read strategy
cat .autoresearch/{domain}/{name}/program.md
# Read full results history
cat .autoresearch/{domain}/{name}/results.tsv
# Read recent git log for the branch
git log --oneline -20
Step 3: Report current state
Summarize for the user:
Resuming: engineering/api-speed
Target: src/api/search.py
Metric: p50_ms (lower is better)
Experiments: 23 total — 8 kept, 12 discarded, 3 crashed
Best: 185ms (-42% from baseline of 320ms)
Last experiment: "added response caching" → KEEP (185ms)
Recent patterns:
- Caching changes: 3 kept, 1 discarded (consistently helpful)
- Algorithm changes: 2 discarded, 1 crashed (high risk, low reward so far)
- I/O optimization: 2 kept (promising direction)
Step 4: Ask next action
How would you like to continue?
1. Single iteration (/ar:run) — I'll make one change and evaluate
2. Start a loop (/ar:loop) — Autonomous with scheduled interval
3. Just show me the results — I'll review and decide
If the user picks loop, hand off to /ar:loop with the experiment pre-selected.
If single, hand off to /ar:run.
Related skills
More from alirezarezvani/claude-skills and the wider catalog.
revenue-operations
Analyzes sales pipeline health, revenue forecasting accuracy, and go-to-market efficiency metrics for SaaS revenue optimization. Use when analyzing sales pipeline coverage, forecasting revenue, evaluating go-to-market performance, reviewing sales metrics, assessing pipeline analysis, tracking forecast accuracy with MAPE, calculating GTM efficiency, or measuring sales efficiency and unit economics for SaaS teams.
review
Systematically audit Playwright tests for anti-patterns, best practices, and coverage gaps.
risk-management-specialist
Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.
run
Run a single experiment iteration: edit, evaluate, keep or discard.
sales-engineer
Analyzes RFP/RFI responses for coverage gaps, builds competitive feature comparison matrices, and plans proof-of-concept (POC) engagements for pre-sales engineering. Use when responding to RFPs, bids, or proposal requests; comparing product features against competitors; planning or scoring a customer POC or sales demo; preparing a technical proposal; or performing win/loss competitor analysis. Handles tasks described as 'RFP response', 'bid response', 'proposal response', 'competitor comparison', 'feature matrix', 'POC planning', 'sales demo prep', or 'pre-sales engineering'.
scrum-master
Advanced Scrum Master skill for data-driven agile team analysis and coaching. Use when the user asks about sprint planning, velocity tracking, retrospectives, standup facilitation, backlog grooming, story points, burndown charts, blocker resolution, or agile team health. Runs Python scripts to analyse sprint JSON exports from Jira or similar tools: velocity_analyzer.py for Monte Carlo sprint forecasting, sprint_health_scorer.py for multi-dimension health scoring, and retrospective_analyzer.py for action-item and theme tracking. Produces confidence-interval forecasts, health grade reports, and improvement-velocity trends for high-performing Scrum teams.