#SkillRepo stars
- 385Redact for Public Disclosurepjt222/agent-almanacRedact reverse-engineering findings for public disclosure while preserving methodology, generalizable patterns, and teaching value. Covers the private-vs-public repo split, deny-list pattern maintenance, orphan-commit publish pattern that prevents `git log` leaks, category-based redaction calibration (methodology/pattern/version-finding/internal), and the `check-redaction.sh`-style CI gate that blocks merges when a deny-listed pattern appears. Use when publishing findings about a CLI harness you don't own, when preparing upstream proposals to an unrelated project, or when archiving a private r45
- 386Release Package Versionpjt222/agent-almanacRelease a new version of an R package including version bumping, NEWS.md updates, git tagging, GitHub release creation, and post-release development version setup. Use when a package is ready for a new patch, minor, or major release, after CRAN acceptance to create the corresponding GitHub release, or when setting up the development version bump immediately after a release.45
- 387Resolve Git Conflictspjt222/agent-almanacResolve merge and rebase conflicts with safe recovery strategies. Covers identifying conflict sources, reading conflict markers, choosing resolution strategies, and continuing or aborting operations safely. Use when a git merge, rebase, cherry-pick, or stash pop reports conflicts, when a git pull results in conflicting changes, or when you need to safely abort and restart a failed merge or rebase operation.45
- 388Review Pull Requestpjt222/agent-almanacReview a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.45
- 389Git Commit Helperlifangda/claude-pluginsGenerate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.43
- 390Git Workflowwillvelida/code-minionsExecute a complete git workflow for collaborative development. Use when user asks to initialize a repo, create branches, commit changes, sync with upstream, open pull requests, resolve conflicts, merge PRs, create releases, or apply hotfixes. Supports Centralized, Feature Branch, Gitflow, and Forking workflows with conventional commits, branch naming standards, and code review guidelines.23
- 391MergeArogyaReddy/alirezarezvani-claude-skillsMerge the winning agent's branch into base, archive losers, and clean up worktrees.40
- 392Raise Pull Requestswillvelida/code-minionsRaise high-quality pull requests that are easy to review, provide clear context, and follow team conventions. Use when a user asks to open, write, prepare, or submit a pull request. Covers PR sizing, self-review, writing descriptions, submitting PRs, responding to review feedback, and reviewing others' PRs. Follows GitHub best practices for collaboration and code review.23
- 393Sharing Skillslifangda/claude-pluginsUse when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository43
- 394SpawnArogyaReddy/alirezarezvani-claude-skillsLaunch N parallel subagents in isolated git worktrees to compete on the session task.40
- 395Ac Branch Pi ModelUCSB-NLP-Chang/Skill-UsageAC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.49
- 396Analyze CIUCSB-NLP-Chang/Skill-UsageAnalyze failed GitHub Action jobs for a pull request.49
- 397Dialogue GraphUCSB-NLP-Chang/Skill-UsageA library for building, validating, visualizing, and serializing dialogue graphs. Use this when parsing scripts or creating branching narrative structures.49
- 398Power Flow DataUCSB-NLP-Chang/Skill-UsagePower system network data formats and topology. Use when parsing bus, generator, and branch data for power flow analysis.49
- 399Automated Review Setupsethdford/claude-skillsSet up automated code review tools (linters, SAST, dependency scanning) to reduce manual review burden. Use when configuring CI/CD toolchains.48
- 400CI CD Pipeline Designsethdford/claude-skillsGitHub Actions, GitLab CI, Jenkins; stages, artifacts, caching, and deployment automation.48
- 401Code Review Checklistsethdford/claude-skillsSystematic code review process, feedback templates, approval criteria, and review best practices.48
- 402Git Workflowsethdford/claude-skillsFeature branches, commit hygiene, rebasing vs. merging, and collaborative workflows.48
- 403Review Metricssethdford/claude-skillsTrack code review health metrics (cycle time, review participation, defect escape) to improve review process. Use when analyzing review effectiveness.48
- 404User Flow Diagramsethdford/claude-skillsCreate user flow diagrams showing paths, decisions, and branch logic.48
- 405Humanizer Rujeremybrasher/grokbot-skillsПроверяет русскоязычный текст на следы машинной генерации (40 regex-маркеров с реестром доказательств) и по явной просьбе пользователя переписывает его естественным языком. Демо: vladimir-human.github.io/humanizer-ru. Отвечает на просьбы вида «очеловечь», «убери гпт-шность», «звучит как нейросеть», «проверь на ИИ», «убери штампы», «убери канцелярит», «сделай живым». Detects AI-generated Russian text and humanizes it on request. Не предназначен для текста не на русском, исходного кода, юридических документов и художественной прозы.38
- 406Code Reviewj4flmao/agent-skillsUse when the user asks to review this code, review a pull request for bugs, give feedback on an implementation, check a diff, or asks LGTM?. Produces a structured review with MUST/SHOULD/CONSIDER findings on correctness, security, performance and tests. Not for finding a bug's root cause (use dev-loop-debugging-strategy) or writing the PR text (use dev-loop-pr-writer).45
- 407Data Data Versioningj4flmao/agent-skillsUse when the user asks about data versioning with DVC or lakeFS, Git-like branches for data, data snapshots, rollback of a bad load or reproducible training data. Produces versioning workflow, branching model and reproducibility checks. Not for Iceberg/Delta time travel (use data-data-lake) or experiment logging (use ml-experiment-tracking).45
- 408Dev Loop Changelog Generatorj4flmao/agent-skillsUse when the user asks to generate a CHANGELOG.md, release notes, semantic versioning bumps, or automate changelogs from conventional commits with release-please, changesets or semantic-release. Produces changelog entries and release automation config. Not for PR descriptions (use dev-loop-pr-writer) or branching strategy (use dev-loop-git-workflow).45
- 409Dev Loop Git Workflowj4flmao/agent-skillsUse when the user asks about git branching strategy, trunk-based development vs git flow, rebase vs merge, a messy rebase or merge conflict, commit conventions, squash or history cleanup. Produces team git conventions and commands. Not for multi-team release trains (use enterprise-release-engineering) or changelogs (use dev-loop-changelog-generator).45
- 410Dev Loop PR Writerj4flmao/agent-skillsUse when the user asks to write a pull request description, PR title, PR template, summary of a diff for reviewers or split a large PR. Produces a reviewer-ready PR description with context, changes, testing and risk. Not for reviewing someone's code (use code-review) or release notes (use dev-loop-changelog-generator).45
- 411Devops Gitlab CIj4flmao/agent-skillsUse when the user asks about GitLab CI, .gitlab-ci.yml, stages and needs, rules, parent-child or multi-project pipelines, include templates, CI/CD components, GitLab runners, container builds, or GitLab SAST/DAST scanning. Produces GitLab pipeline configs. Not for GitHub Actions (use github-actions) or Jenkins (use jenkins).45
- 412Ecmwf Weather Feedbackecmwf/ecmwf-weather-skillsTurns what a task taught about the ECMWF weather skills into one anonymised, privacy-scanned issue for ecmwf/ecmwf-weather-skills — load this skill first, before running any `gh issue` command or filing, drafting or reporting any issue about these skills. The issue goes to GitHub, or to ECMWF JIRA project AS with the user's own token, or is given as text to paste — shown in full and filed only after an explicit yes, file it. Use when the user wants to send feedback about the ECMWF weather skills, report a problem with a skill or its instructions, suggest an improvement, file an issue for ecmwf23
- 413Enterprise Release Engineeringj4flmao/agent-skillsUse when the user asks about integration hell, long-lived branches across teams, trunk-based development at scale, release trains, branch by abstraction, dark launches or CODEOWNERS. Produces a multi- team integration and release model. Not for single-team git basics (use dev-loop-git-workflow) or canary rollouts (use devops-progressive-delivery).45
- 414Orchestratenathanonn/agent-skillsRun the main Claude Code session as an orchestrator for a non-trivial, multi-step request in a git repo. Builds a task list, routes each task to a sub-agent with an explicit model and effort (sonnet, opus or haiku; fable only with the user's say-so), runs up to 5 read-only agents at once and file-editing agents one at a time in the main checkout (git worktrees only when the user asks for them), then verifies and commits each checkpoint locally on the current branch, never pushing unless asked. Use it when the user asks to orchestrate, delegate, use sub-agents, fan out, or work in parallel, inc23
- 415Git Commit Helperdvcrn/openclaw-skills-marketplaceGenerate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.33
- 416Openclaw Version Monitordvcrn/openclaw-skills-marketplace监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明33
- 417Alterlab Pra PR WriterAlterLab-IEU/AlterLab-FC-SkillsThis skill should be used when the user asks about "press release", "media kit", "crisis communication", "PR writing", "public relations writing", "corporate communications", "media advisory", "speech writing", "spokesperson brief", "act as a PR writer", "PR writer mode", "media relations", "crisis statement", "internal communications", or needs expertise in writing professional public relations materials across all corporate communication formats. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).21
- 418Comms Whyjpoehnelt/skillsExplain why code is shaped the way it is, using git history, PRs, and connected MCP evidence, with citations and honest confidence. Use for "why does X work this way", "why did we pick Y", design rationale, regressions, and postmortems. Use comms-how for runtime behavior.23
- 419Eng Cutover Verificationjpoehnelt/skillsProve a migration, module split, library swap, datastore or deploy-tool cutover, compatibility removal, or multi-PR cleanup is complete. Use when retiring paths, adapters, dependencies, generated outputs, or config, validating merged main, or proving a rebase preserved a patch series.23
- 420Gh CI Triagejpoehnelt/skillsDiagnose failing GitHub Actions CI from log evidence and choose a fix, rerun, merge-forward, or escalation. Use when a PR or default-branch run is red, cancelled, or flaky, or a visual baseline or artifact is missing.23
- 421Gh PR Commit Reviewjpoehnelt/skillsReview new commits on open GitHub PRs against their actual base without stale or duplicate findings. Use for cutoff-based or scheduled review sweeps, stacked or rebased PRs, cleaning up review threads, or posting actionable inline findings. Read-only except comments and thread resolution.23
- 422Gh PR Feedback Loopjpoehnelt/skillsPublish a GitHub pull request and carry it through CI, review feedback, rebases, and merge readiness, merging only with explicit authorization. Use when opening or updating a PR, addressing review comments, monitoring checks, rebasing, or continuing a PR to a terminal state. For read-only review of new commits, use gh-pr-commit-review.23
- 423Sentry Bugfixjpoehnelt/skillsTriage Sentry errors for one environment, trace a finding to current code, reproduce it locally, and deliver a focused fix PR. Use when sweeping an environment's errors, decomposing catch-all log or 5xx issues, or driving a supplied Sentry issue to a fix. Use sentry-perf for latency and gh-ci-triage for CI.23
- 424Abrir PRvcampitelli/slides-agente-skills-de-verdadeAbre ou atualiza um Pull Request no GitHub para a branch atual usando o CLI `gh`, sempre como Draft, com título e corpo em português brasileiro vinculados a uma issue. Use sempre que o usuário pedir para "abrir PR", "criar pull request", "subir PR", "fazer PR dessa branch", "atualizar o PR" ou similar — mesmo que ele não diga explicitamente qual issue referenciar, pois a skill tenta detectar automaticamente. Não use para apenas commitar ou dar push (a skill nunca faz isso), nem para revisar/mergear PRs existentes.9
- 425Navigating Github to Konflux Pipelineskonflux-ci/agent-pluginsUse when GitHub PR or branch has failing checks and you need to find Konflux pipeline information (cluster, namespace, PipelineRun name). Teaches gh CLI commands to identify Konflux checks (filter out Prow/SonarCloud), extract PipelineRun URLs from builds and integration tests, and parse URLs for kubectl debugging.9
- 426Changelog Newslettertomique34/claude-skill-creatorTransform technical changelog entries into user-friendly newsletter content for email, blog posts, and release notes. Use when converting CHANGELOG.md files, git commit logs, or release notes into customer-facing communications.9
- 427Carly Code Reviewcarlymr/carlys-claude-skillsComprehensive code review using 7 parallel specialized sub-agents (correctness, security, performance, simplicity, UX, codebase integration, documentation). Every finding needs a concrete failure scenario; Critical/Warning findings are then challenged by adversarial refuter agents before they reach the report. Repos can add their own reviewers via an `Extra reviewers:` list in CLAUDE.md. Use when reviewing code changes, pull requests, or local diffs. Supports local git diff (no arguments) or GitHub PR (pass PR number or URL as argument).9
- 428Push Checkcharlie947/skills-for-everyoneCheck everything before work goes to GitHub, then push it. Runs the repo's own checks, a sweep for leaked keys, personal paths, oversized files and dead links, a second Claude reading the changes cold, and a fresh-copy rehearsal of what a new user does first. Pushes only after two clean passes in a row, then drafts the short note to send people, if there is anything for them to do. Use when the user says "push", "push this", "ship it", "put it on GitHub", "release", "send it to them", "is it ready to push", or is about to share a repo other people will download.10
- 429Repo Wiki Detectboweneos/repo-wiki-agent-skillsDetect code changes since last wiki update using git diff. Identifies added, modified, deleted, and renamed files to determine which documentation pages need updates.9
- 430Zephyr Exploreprocessmission/agent-skillsUse when Zephyr source, branch history, external precedent, or design constraints must be investigated before a decision can be made.9
- 431Design Revieweralmansouri/skillsDesign review of a codebase area, branch, or PR. Maps its bounded contexts, vertical slices, and modules, then judges where rules live and whether flexibility sits where change actually happens. Use when the user asks for a design or architecture review, or when a review should judge structure rather than bugs or style.9
- 432Auto Experimentzxl696/smallmodel-auto-experiment-skill自动化超参数/架构搜索循环。给定模型代码、数据集和优化目标,自动生成 train.py,经双 agent 审计门禁通过后,循环调用 DeepSeek 提出改进建议、训练、用 git 追踪每轮变更,保留最优配置和 checkpoint。5