mkl-bisect-regression SKILL.md skillA

mkl-bisect-regression from 00200200/maintainer-skills-lab is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add 00200200/maintainer-skills-lab/mkl-bisect-regression@git:20261016.4de5604

Pins git:20261016.4de5604 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
00200200/maintainer-skills-lab
Path
providers/windsurf/.windsurf/skills/mkl-bisect-regression/SKILL.md
Versions recorded
2
Latest version
git:20261016.4de5604, committed Oct 16, 2026
First version recorded
Oct 6, 2026
Size
3,132 bytes
Repository stars
48
License
MIT

Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Pinpoint regressions with automated git bisect

When a bug or regression appears between releases or commits, never manually read commit diffs across history. Reading hundreds of commits burns tens of thousands of LLM prompt tokens, causes hallucinated attributions, and exhausts context.

Instead, leverage Git's binary search: `git bisect run <test_script>`. The local shell automatically tests commits in $\mathcal{O}(\log_2 N)$ steps with zero intermediate tokens sent to the model. Inspect only the single culprit commit diff.

## 1. Author a standalone bisect test script

Author an executable script (`bisect_test.sh`) returning standard Git exit codes:
- **`0` (Good)**: Commit is good (bug absent).
- **`1` through `124`, `126` through `255` (Bad)**: Commit is bad (regression observed).
- **`125` (Skip)**: Commit untestable (broken build, syntax error unrelated to bug). Git picks an adjacent commit.

### Flakiness and build mitigation in the script

1. **Trap compilation/build failures**: Return `125` if compilation or dependencies fail so Git skips intermediate broken commits.
2. **Loop flaky checks**: If timing-sensitive, run the test 3 to 5 times. If any run fails, exit `1`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add 00200200/maintainer-skills-lab/mkl-bisect-regression@sha256:ae579239bbdc74f2

The line at the top of this page pins the label git:20261016.4de5604, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_moglqncvs5z4l2sf.svg)](https://markdownregistry.com/a/art_moglqncvs5z4l2sf)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 6, 2026 and Oct 16, 2026, about one every 10 days.

versioncommittedcommitsizeaudit
git:20261016.4de5604 latest2026-10-16 4de5604 3,132 BA view · diff
git:20261006.ca565702026-10-06 ca56570 4,789 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3132 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

00200200/maintainer-skills-lab · 48 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_moglqncvs5z4l2sf
GET https://markdownregistry.com/api/v1/resolve?ref=00200200/maintainer-skills-lab/mkl-bisect-regression
GET https://markdownregistry.com/api/v1/blob/ae579239bbdc74f27665cbadafc0705db423677b36b623238460226ac991c1c2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from 00200200/maintainer-skills-lab

AGENTS.md AGENTS.md file
00200200/maintainer-skills-lab · AGENTS.md
git:20261006.dacbcf4 · audit B · 48 stars
mkl-adversarial-review SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-adversarial-review/SKILL.md · Conduct a bounded 3-turn adversarial code review debate (Author vs. Skeptic) to uncover subtle edge cases and race…
git:20261015.deeb4bf · audit A · 48 stars
mkl-architect-editor SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-architect-editor/SKILL.md · Two-model pipeline routing high-level design to an Architect model, and mechanical search/replace edits to an Editor…
git:20261015.8dfd8a5 · audit A · 48 stars
mkl-audit-cve SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-audit-cve/SKILL.md · Audit CVE advisories against codebase usage with minimal token context.
git:20261017.c81de28 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261017.c81de28 · audit A · 48 stars
mkl-bump-version SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-bump-version/SKILL.md · Evaluate conventional commits since latest tag, determine next SemVer, and surgically update version files.
git:20261015.0f940b8 · audit A · 48 stars
mkl-debug-ml-training SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-debug-ml-training/SKILL.md · Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch…
git:20261007.b098ce2 · audit A · 48 stars
mkl-fix-type-errors SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-fix-type-errors/SKILL.md · Resolve static type checker errors (mypy, pyright) using localized symbol-level diagnostics without whole-file…
git:20261015.46e41d9 · audit A · 48 stars
mkl-generate-changelog SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-generate-changelog/SKILL.md · Generate grouped, token-compact changelogs and release notes from git log.
git:20261008.cae68bf · audit A · 48 stars
mkl-generate-commit SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-generate-commit/SKILL.md · Generate concise Conventional Commits under 50 tokens from staged git diffs.
git:20261015.d651c97 · audit A · 48 stars
mkl-humanize SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-humanize/SKILL.md · Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point…
git:20261017.c81de28 · audit A · 48 stars
mkl-isolated-scratchpad SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-isolated-scratchpad/SKILL.md · Offload verbose reasoning, trial commands, and intermediate drafts to ephemeral scratch files to preserve context…
git:20261015.e7124e4 · audit A · 48 stars

Every file in 00200200/maintainer-skills-lab

Other files named mkl-bisect-regression

mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/cursor/.cursor/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261017.c81de28 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/codex/.agents/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261017.c81de28 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/gemini/.gemini/antigravity/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261016.4de5604 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/opencode/.opencode/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261017.c81de28 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261017.c81de28 · audit A · 48 stars
mkl-bisect-regression SKILL.md skill
00200200/maintainer-skills-lab · skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
git:20261016.4de5604 · audit A · 48 stars

Browse by kind, by grade A, or by owner.