GitHub collection

00200200/maintainer-skills-lab

Imported from GitHub — is this yours?

64 skills imported from this repository.

Claude Skill

mkl-debug-ml-training

Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch, Lightning, or TensorFlow/Keras. Use for a concrete training bug or regression, not an open-ended architecture or hyperparameter search.

LLM Mart

Claude Skill

mkl-localize-pl-en

Translate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.

LLM Mart

Claude Skill

mkl-match-voice

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

LLM Mart

Claude Skill

mkl-prepare-release

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

LLM Mart

Claude Skill

mkl-reproduce-bug

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

LLM Mart

Claude Skill

mkl-review-source-change

Review an upstream documentation change against the skills, agent instructions, or runbooks that cite it. Identify supported updates, unaffected instructions, and unresolved version or evidence gaps. Use with a supplied source diff or Skill Watch result.

LLM Mart

Claude Skill

mkl-triage-issue

Turn a repository issue into an evidence-backed triage note: observed behavior, missing reproduction details, possible duplicates, and the next useful action. Use for issue triage, not implementation or bulk issue closure.

LLM Mart

Claude Skill

mkl-verify-fix

Verify a proposed bug fix against an unchanged regression test and the relevant existing tests, reporting baseline and candidate outcomes separately. Use for fix verification, not a general claim that software is bug-free.

LLM Mart

Claude Skill

mkl-write-launch-post

Draft factual project announcements, GitHub launch posts, and development updates for a specified audience or platform. Use to explain shipped work clearly, with evidence and a useful invitation for feedback.

LLM Mart

Claude Skill

mkl-write-maintainer-reply

Draft clear, respectful replies to issues, PR discussions, and technical support reports from available evidence. Use to explain status, request a minimal reproduction, or communicate a project decision without inventing commitments.

LLM Mart

Claude Skill

mkl-write-readme

Create or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.

LLM Mart

Claude Skill

mkl-write-regression

Write a focused regression test from an established bug reproduction and public behavior. Use when a fix needs a test that fails on the affected version; avoid mirroring the implementation or weakening assertions.

LLM Mart

Claude Skill

mkl-write-tutorial

Build a step-by-step technical tutorial around a reproducible outcome, with prerequisites, checkpoints, and recovery steps. Use for hands-on guides when a README quickstart is too short.

LLM Mart

Claude Skill

mkl-write-ux-copy

Write or revise interface labels, errors, empty states, and confirmation text from actual product behavior. Use for UI microcopy with clear next actions, preserved localization tokens, and explicit length constraints.

LLM Mart

Claude Skill

mkl-debug-ml-training

Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch, Lightning, or TensorFlow/Keras. Use for a concrete training bug or regression, not an open-ended architecture or hyperparameter search.

LLM Mart

Claude Skill

mkl-humanize

Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point of view. Use when asked to humanize, de-AI, or make an existing draft sound more human, in its original language.

LLM Mart

Claude Skill

mkl-localize-pl-en

Translate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.

LLM Mart

Claude Skill

mkl-match-voice

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

LLM Mart

Claude Skill

mkl-prepare-release

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

LLM Mart

Claude Skill

mkl-reproduce-bug

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

LLM Mart

Claude Skill

mkl-review-pr

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

LLM Mart

Claude Skill

mkl-review-source-change

Review an upstream documentation change against the skills, agent instructions, or runbooks that cite it. Identify supported updates, unaffected instructions, and unresolved version or evidence gaps. Use with a supplied source diff or Skill Watch result.

LLM Mart

Claude Skill

mkl-triage-issue

Turn a repository issue into an evidence-backed triage note: observed behavior, missing reproduction details, possible duplicates, and the next useful action. Use for issue triage, not implementation or bulk issue closure.

LLM Mart

Claude Skill

mkl-verify-fix

Verify a proposed bug fix against an unchanged regression test and the relevant existing tests, reporting baseline and candidate outcomes separately. Use for fix verification, not a general claim that software is bug-free.

LLM Mart

Claude Skill

mkl-write-launch-post

Draft factual project announcements, GitHub launch posts, and development updates for a specified audience or platform. Use to explain shipped work clearly, with evidence and a useful invitation for feedback.

LLM Mart

Claude Skill

mkl-write-maintainer-reply

Draft clear, respectful replies to issues, PR discussions, and technical support reports from available evidence. Use to explain status, request a minimal reproduction, or communicate a project decision without inventing commitments.

LLM Mart

Claude Skill

mkl-write-readme

Create or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.

LLM Mart

Claude Skill

mkl-write-regression

Write a focused regression test from an established bug reproduction and public behavior. Use when a fix needs a test that fails on the affected version; avoid mirroring the implementation or weakening assertions.

LLM Mart

Claude Skill

mkl-write-tutorial

Build a step-by-step technical tutorial around a reproducible outcome, with prerequisites, checkpoints, and recovery steps. Use for hands-on guides when a README quickstart is too short.

LLM Mart

Claude Skill

mkl-write-ux-copy

Write or revise interface labels, errors, empty states, and confirmation text from actual product behavior. Use for UI microcopy with clear next actions, preserved localization tokens, and explicit length constraints.

LLM Mart

Cursor Skill

mkl-debug-ml-training

Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch, Lightning, or TensorFlow/Keras. Use for a concrete training bug or regression, not an open-ended architecture or hyperparameter search.

LLM Mart

Cursor Skill

mkl-humanize

Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point of view. Use when asked to humanize, de-AI, or make an existing draft sound more human, in its original language.

LLM Mart

Cursor Skill

mkl-localize-pl-en

Translate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.

LLM Mart

Cursor Skill

mkl-match-voice

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

LLM Mart

Cursor Skill

mkl-prepare-release

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

LLM Mart

Cursor Skill

mkl-reproduce-bug

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

LLM Mart

Cursor Skill

mkl-review-pr

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

LLM Mart

Cursor Skill

mkl-review-source-change

Review an upstream documentation change against the skills, agent instructions, or runbooks that cite it. Identify supported updates, unaffected instructions, and unresolved version or evidence gaps. Use with a supplied source diff or Skill Watch result.

LLM Mart

Cursor Skill

mkl-triage-issue

Turn a repository issue into an evidence-backed triage note: observed behavior, missing reproduction details, possible duplicates, and the next useful action. Use for issue triage, not implementation or bulk issue closure.

LLM Mart

Cursor Skill

mkl-verify-fix

Verify a proposed bug fix against an unchanged regression test and the relevant existing tests, reporting baseline and candidate outcomes separately. Use for fix verification, not a general claim that software is bug-free.

LLM Mart

Cursor Skill

mkl-write-launch-post

Draft factual project announcements, GitHub launch posts, and development updates for a specified audience or platform. Use to explain shipped work clearly, with evidence and a useful invitation for feedback.

LLM Mart

Cursor Skill

mkl-write-maintainer-reply

Draft clear, respectful replies to issues, PR discussions, and technical support reports from available evidence. Use to explain status, request a minimal reproduction, or communicate a project decision without inventing commitments.

LLM Mart

Cursor Skill

mkl-write-readme

Create or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.

LLM Mart

Cursor Skill

mkl-write-regression

Write a focused regression test from an established bug reproduction and public behavior. Use when a fix needs a test that fails on the affected version; avoid mirroring the implementation or weakening assertions.

LLM Mart

Cursor Skill

mkl-write-tutorial

Build a step-by-step technical tutorial around a reproducible outcome, with prerequisites, checkpoints, and recovery steps. Use for hands-on guides when a README quickstart is too short.

LLM Mart

Cursor Skill

mkl-write-ux-copy

Write or revise interface labels, errors, empty states, and confirmation text from actual product behavior. Use for UI microcopy with clear next actions, preserved localization tokens, and explicit length constraints.

LLM Mart

Claude Skill

mkl-debug-ml-training

Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch, Lightning, or TensorFlow/Keras. Use for a concrete training bug or regression, not an open-ended architecture or hyperparameter search.

LLM Mart

Claude Skill

mkl-localize-pl-en

Translate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.

LLM Mart

Claude Skill

mkl-match-voice

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

LLM Mart

Claude Skill

mkl-prepare-release

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

LLM Mart

Claude Skill

mkl-reproduce-bug

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

LLM Mart

Claude Skill

mkl-review-pr

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

LLM Mart

Claude Skill

mkl-review-source-change

Review an upstream documentation change against the skills, agent instructions, or runbooks that cite it. Identify supported updates, unaffected instructions, and unresolved version or evidence gaps. Use with a supplied source diff or Skill Watch result.

LLM Mart

Claude Skill

mkl-triage-issue

Turn a repository issue into an evidence-backed triage note: observed behavior, missing reproduction details, possible duplicates, and the next useful action. Use for issue triage, not implementation or bulk issue closure.

LLM Mart

Claude Skill

mkl-verify-fix

Verify a proposed bug fix against an unchanged regression test and the relevant existing tests, reporting baseline and candidate outcomes separately. Use for fix verification, not a general claim that software is bug-free.

LLM Mart

Claude Skill

mkl-write-launch-post

Draft factual project announcements, GitHub launch posts, and development updates for a specified audience or platform. Use to explain shipped work clearly, with evidence and a useful invitation for feedback.

LLM Mart

Claude Skill

mkl-write-maintainer-reply

Draft clear, respectful replies to issues, PR discussions, and technical support reports from available evidence. Use to explain status, request a minimal reproduction, or communicate a project decision without inventing commitments.

LLM Mart

Claude Skill

mkl-write-readme

Create or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.

LLM Mart

Claude Skill

mkl-write-regression

Write a focused regression test from an established bug reproduction and public behavior. Use when a fix needs a test that fails on the affected version; avoid mirroring the implementation or weakening assertions.

LLM Mart

Claude Skill

mkl-write-tutorial

Build a step-by-step technical tutorial around a reproducible outcome, with prerequisites, checkpoints, and recovery steps. Use for hands-on guides when a README quickstart is too short.

LLM Mart

Claude Skill

mkl-write-ux-copy

Write or revise interface labels, errors, empty states, and confirmation text from actual product behavior. Use for UI microcopy with clear next actions, preserved localization tokens, and explicit length constraints.

LLM Mart

Claude Skill maintainer-skills-lab

mkl-humanize

Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point of view. Use when asked to humanize, de-AI, or make an existing draft sound more human, in its original language.

LLM Mart

Claude Skill maintainer-skills-lab

mkl-review-pr

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

LLM Mart

Claude Skill mkl-humanize

mkl-humanize

Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point of view. Use when asked to humanize, de-AI, or make an existing draft sound more human, in its original language.

LLM Mart