All authors
Claude Skills by EJRyan89
github.com/EJRyan8933 skills0 installs0 views
- Audit RepositoryRun this repository's audits per release: the release audit of the diff since the last tag, before tagging, and after it the rotation audit of one area read whole and the guidance audit of each runtime's published guidance. Writes the briefs for read-only readers, then files what they confirm.Votes: 0GitHub stars: 2
- Change SkillProcedure for adding or changing a skill in this repository, shipped under skills/ or repository-only under .claude/skills: its SKILL.md, scripts, metadata, or documentation. Use it when asked to add, create, change, fix, or extend a skill here. Not for deployer-only, repository-tool, or documentation-only changes.Votes: 0GitHub stars: 2
- Evaluate SkillRun a skill's fixed scenarios on each model from throwaway homes, once or several times, and judge each record by script: a review's, or whether a request started the skill. Use it before a pull request that changes a skill's prompt, description, model guidance, or reviewer instructions. Each run calls models.Votes: 0GitHub stars: 2
- Implement ChangeProcedure for making a change in a repository that publishes an implementation profile (docs/implementing-changes.md), from the worktree and the plan to the pull request. Use it when asked to implement an issue or make a change in such a repository.Votes: 0GitHub stars: 2
- Review RepositoryThis repository's own pull request reviewer: a specialists manifest that routes the deployer, the skills, the validation policies, the trust-boundary files, and the documents to briefed reviewers, which review-prs runs. Set it up on a machine, check it, or tune it from canary reviews.Votes: 0GitHub stars: 2
- Runtime CanaryCheck that Claude Code, Codex, and Copilot CLI find and run deployed skills, by deploying this checkout into a throwaway home and starting each runtime there. Use it before a pull request that changes skill paths, allowed-tools, runtime adapters, or agents. Each run calls a model.Votes: 0GitHub stars: 2
- Shepherd Pull RequestsRun one merge-shepherd tick from the hub over this repository's open pull requests: fast-forward main, arm auto-merge, merge main into behind branches, judge each red Validation check as a rerun or a defect, and name each merged worktree to retire.Votes: 0GitHub stars: 2
- Audit RepositoryRun this repository's audits per release: the release audit of the diff since the last tag, before tagging, and after it the rotation audit of one area read whole and the guidance audit of each runtime's published guidance. Writes the briefs for read-only readers, then files what they confirm.Votes: 0GitHub stars: 2
- Change SkillProcedure for adding or changing a skill in this repository, shipped under skills/ or repository-only under .claude/skills: its SKILL.md, scripts, metadata, or documentation. Use it when asked to add, create, change, fix, or extend a skill here. Not for deployer-only, repository-tool, or documentation-only changes.Votes: 0GitHub stars: 2
- Evaluate SkillRun a skill's fixed scenarios on each model from throwaway homes, once or several times, and judge each record by script: a review's, or whether a request started the skill. Use it before a pull request that changes a skill's prompt, description, model guidance, or reviewer instructions. Each run calls models.Votes: 0GitHub stars: 2
- Implement ChangeProcedure for making a change in a repository that publishes an implementation profile (docs/implementing-changes.md), from the worktree and the plan to the pull request. Use it when asked to implement an issue or make a change in such a repository.Votes: 0GitHub stars: 2
- Review RepositoryThis repository's own pull request reviewer: a specialists manifest that routes the deployer, the skills, the validation policies, the trust-boundary files, and the documents to briefed reviewers, which review-prs runs. Set it up on a machine, check it, or tune it from canary reviews.Votes: 0GitHub stars: 2
- Runtime CanaryCheck that Claude Code, Codex, and Copilot CLI find and run deployed skills, by deploying this checkout into a throwaway home and starting each runtime there. Use it before a pull request that changes skill paths, allowed-tools, runtime adapters, or agents. Each run calls a model.Votes: 0GitHub stars: 2
- Shepherd Pull RequestsRun one merge-shepherd tick from the hub over this repository's open pull requests: fast-forward main, arm auto-merge, merge main into behind branches, judge each red Validation check as a rerun or a defect, and name each merged worktree to retire.Votes: 0GitHub stars: 2
- DocsThis is the contract a skill must meet. The `change-skill` repository skill (`.claude/skills/change-skill/SKILL.md`) is the procedure for meeting it, and `python tools/new_skill.py <name> --description "<description>"` scaffolds a new skill's frontmatter, metadata, and reference section; run it with `--help` for the other options.Votes: 0GitHub stars: 2
- Analyze Skill CostAudit an agent skill for cost and efficiency: token footprint, tool calls, deterministic work left to prose, subagent overhead, runtime adapters, model, and allowed-tools. Read-only findings report. Use it when asked what a skill costs, why it is slow or expensive, or to check one before shipping it.Votes: 0GitHub stars: 2
- Audit Ai ConfigRead-only assessment of a repository's AI agent configuration for Claude Code, Codex, and Copilot that reports findings and never writes files. Use it when asked to audit or check a repository's agent instructions or setup, not to create or change them.Votes: 0GitHub stars: 2
- Code Review CoreInternal support for the code-review operations bundle. Not intended for direct invocation.Votes: 0GitHub stars: 2
- Curate Agent MemoryAudit and clean up Claude Code auto-memory for a project: find stale, duplicated, or misplaced memories, move durable rules to their proper home, and apply only the changes the user approves. Use it when asked to review, tidy, or prune a project's memories.Votes: 0GitHub stars: 2
- Dotnet DependenciesAnswer why a package or assembly is in a legacy or SDK-style C# solution, which projects reference an assembly, and where versions and binding redirects conflict, from a read-only dependency graph of the solution's project files. Use it when asked why a package is referenced, what pulls a dependency in, which projects use an assembly, or whether versions or binding redirects disagree, and not to restore, build, or change references.Votes: 0GitHub stars: 2
- Dotnet FormatRun dotnet format (whitespace + style + analyzers) and region layout checks on C# files changed on the current branch and optionally auto-fix violations. Use it when asked to format or style-check C# changes before a commit or pull request.Votes: 0GitHub stars: 2
- Flag Review FindingAdd, list, edit, or resolve a structured code-review improvement flag. Use it when the user says a review finding was wrong, noisy, or missed something and wants that recorded.Votes: 0GitHub stars: 2
- Github Activity ReportReport one user's GitHub contributions in one organization month by month: pull requests authored and merged, commits, pull requests reviewed, and reviews submitted. Use it when asked what someone contributed or reviewed over recent months.Votes: 0GitHub stars: 2
- Repo CleanupClean up GitHub repos: switch to default branch, prune gone branches, remove stale worktrees, and fast-forward remaining branches. Sweeps all repos under {{REPOS_ROOT}} or targets a single repo by name/path.Votes: 0GitHub stars: 2
- Review DocumentReview one document from its file path, such as a design draft on disk or a document with uncommitted edits, or the documents a pull request changes, through the code-review pipeline's design reviewer, and write a validated report and record. Use it when asked to review a design document, a Word or PDF draft, another text file, or a pull request's documents rather than its code.Votes: 0GitHub stars: 2
- Review InsightsAnalyze structured code-review findings and open flags for an explicit date range and repository set, and recommend guidance, reviewer, and analyzer changes. Use it when asked what reviews keep flagging, which findings were accepted or rejected, or what to change in review guidance.Votes: 0GitHub stars: 2
- Review PrsReview eligible pull requests in explicitly configured repositories, review or re-review explicit pull requests, or run isolated canaries of pull requests or local fixtures, and produce validated structured reports. Use it when asked to review or re-review pull requests.Votes: 0GitHub stars: 2
- Skill CoreInternal Python modules shared by other skills' scripts. Not intended for direct invocation.Votes: 0GitHub stars: 2
- Update Coding Agent SkillsFast-forward the coding-agent-skills clone these skills were deployed from to origin/main, then redeploy every skill: at the latest release on origin/main by default, or at main on the main channel. Stops before a release that raises the major version until the user passes --cross-major, and over a deployment the user pinned with deploy.py --at until the user passes --unpin.Votes: 0GitHub stars: 2
- Update Pr DashboardUpdate the owned dashboard section for pull requests the configured user authors, reviews, or participates in. Use it when asked to refresh the pull request dashboard or tracker, or to see which pull requests need attention.Votes: 0GitHub stars: 2
- Runtime Canary ProbeTest fixture for this repository's runtime canary. Use it only when a prompt names it.Votes: 0GitHub stars: 2
- Report PreviewList the reports a repository's site would publish, by reading its reports folder. Use it when asked which reports the site shows.Votes: 0GitHub stars: 2
- Report PreviewList the reports a repository's site would publish, and build the site to preview them. Use it when asked which reports the site shows or how they look.Votes: 0GitHub stars: 2