eval-regression
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
Skill by reidemeister94
Chalk Labs
Need help deploying eval-regression?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/reidemeister94-eval-regression
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/eval-regression
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Glob,Read,Bash,Grep,AskUserQuestion
What's inside
- Skill name
eval-regression- Description
- Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
- License
- MIT
- Allowed tools
- Glob,, Read,, Bash,, Grep,, AskUserQuestion
- Instructions
- 29 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (2)
- SKILL.md
- run_evals.py · scripts/
SKILL.md (first lines)
# Eval regression Use deterministic repository tests first. Stop when the target has no behavioral diff. Resolve the plugin from the argument or cwd. Its catalog is `evals/evals.json`; the runner is `scripts/run_evals.py` in this skill. Require the user to choose agent, model, and effort. Never select a costly model or high effort silently. ## Normal check 1. Select cases by changed paths with `--changed-from <base>`, or name them with `--case`. Do not select the full catalog implicitly. 2. Run the command without `--run`. The runner prints cases, modes, repeats, sessions, timeout, and maximum duration without starting an agent. 3. An approved plan that names this exact run already authorizes it. For a standalone eval, present the run plan and stop once. 4. After approval, repeat the same command with `--run`. Default to candidate-only, one run per case, 180 seconds, and four sessions maximum. 5. Report every failed assertion, timeout, non-zero exit, duration, and token count. Missing evidence is inconclusive. ## Escalation - Compare base and candidate only when the user asks, or when a failed candidate check needs a baseline. - Extract the base with `git archive`. Use the same cases, agent, model, effort, repeats, and timeout on both versions. - Repeat only a failed or observably unstable case. Three repeats are a stability benchmark, not a default. - `--all`, `--repeat > 1`, more sessions, or a longer timeout is new scope. Update the run plan and get authority first. - Routing cases stop at the first Skill selection. Tool assertions are appropriate because routing is the contract. Remove temporary base copies after the comparison. Do not edit or commit the target. Deterministic assertions are `tool`, `tool_not`, `clean_worktree`, `changed_files_exact`, `file_contains`, `file_not_contains`, `transcript_contains`, and `tool_sequence`. Use a semantic judge only when no filesystem, command, tool, ordering, or assistant-output observation can express the contract.
From reidemeister94/development-skills, MIT.
More from reidemeister94/development-skills
- 0.596score
create-test
reidemeister94
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
handoff
reidemeister94
Create a self-contained temporary handoff document when the user asks to transfer the session to a new chat or runs /handoff.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
ai-agent-bench
reidemeister94
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
changelog
reidemeister94
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
align-docs
reidemeister94
Align stale repository docs and task records; use --clean for a full documentation cleanup.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
explain-diff
reidemeister94
Explain a code change, its reasons, effects, trade-offs, and verification limits.
SkillBFreshness: B★ 12Claude Code +9 - 0.591score
wrap-up-branch
reidemeister94
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
refactor
reidemeister94
Audit an existing project against its standards and apply selected improvements while preserving behavior.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
resolve-merge
reidemeister94
Resolve an active merge or rebase conflict, including safe renumbering of colliding plans and chronicles.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
bro
reidemeister94
Use when the user says an explanation was unclear, too technical, or full of jargon, or asks for plain language.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
phone-a-friend
reidemeister94
Get an independent second opinion on a plan or code change from the other CLI, Claude Code or Codex.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
update-deps
reidemeister94
Update Python dependencies or pre-commit hooks while preserving the project's pin and configuration style.
SkillBFreshness: B★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Sep 19, 2026 (1 month ago)
- Last release
- Sep 20, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from reidemeister94
- 0.596score
create-test
reidemeister94
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
SkillBFreshness: B★ 12Claude Code +9 - 0.594score
handoff
reidemeister94
Create a self-contained temporary handoff document when the user asks to transfer the session to a new chat or runs /handoff.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
ai-agent-bench
reidemeister94
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
align-docs
reidemeister94
Align stale repository docs and task records; use --clean for a full documentation cleanup.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
explain-diff
reidemeister94
Explain a code change, its reasons, effects, trade-offs, and verification limits.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
changelog
reidemeister94
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
SkillBFreshness: B★ 12Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get eval-regression running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
eval-regression skill. Agent Mart. https://agentmart.dev/skills/reidemeister94-eval-regression (last updated 2026-10-24)