alirezarezvani/claude-skills / engineering/skills/agent-regression-evals
agent-regression-evals
VerifiedUse before shipping any agent, prompt, model or tool change, or when a pass-rate drop needs a verdict. Runs repeated trials, gates candidate vs baseline with paired statistics in regression_gate.py, checks tool-call trajectories and finds flaky cases.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.3 KB |
| assets/ci_eval_gate.example.yml | config | 1.7 KB |
| assets/eval_case_spec.example.json | config | 669 B |
| assets/sample_baseline.jsonl | other | 3.7 KB |
| assets/sample_candidate.jsonl | other | 3.7 KB |
| references/eval_statistics.md | markdown | 4.8 KB |
| references/flaky_cases_and_quarantine.md | markdown | 4.8 KB |
| references/trajectory_grading.md | markdown | 4.1 KB |
| scripts/flake_detector.py | script | 9.8 KB |
| scripts/regression_gate.py | script | 12.2 KB |
| scripts/trajectory_checker.py | script | 10.6 KB |
assets/ci_eval_gate.example.yml
View on GitHub# Example CI job: block a pull request when the agent regresses.
# Adapt the "run evals" step to however your agent is executed. The gate itself
# needs only Python 3 and the two JSONL files; it makes no network calls.
#
# Exit codes from regression_gate.py: 0 PASS, 2 WARN, 3 bad input, 4 BLOCK.
# This job fails on 3 and 4 and surfaces 2 as a warning for a human to read.
name: agent-regression-evals
on:
pull_request:
paths: ["agent/**", "prompts/**", "tools/**"]
jobs:
eval-gate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Run eval suite on the candidate (3 trials per case)
run: ./scripts/run_evals.sh --trials 3 --out evals/candidate.jsonl # your runner
- name: Fetch the baseline from the default branch's last green run
run: ./scripts/fetch_baseline.sh evals/baseline.jsonl # your storage
- name: Flaky cases
run: |
python3 skills/agent-regression-evals/scripts/flake_detector.py \
--results evals/candidate.jsonl --k 3 || [ $? -eq 2 ]
- name: Regression gate
run: |
set +e
python3 skills/agent-regression-evals/scripts/regression_gate.py \
--baseline evals/baseline.jsonl --candidate evals/candidate.jsonl \
--quarantine evals/quarantine.json --output json > gate.json
code=$?
python3 skills/agent-regression-evals/scripts/regression_gate.py \
--baseline evals/baseline.jsonl --candidate evals/candidate.jsonl \
--quarantine evals/quarantine.json
if [ $code -eq 2 ]; then echo "::warning::eval gate WARN - read gate.json"; exit 0; fi
exit $code
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |