nolte/claude-shared
Shared Claude Code skills and agents for consistent development workflows across projects.
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 30/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit nolte/claude-shared/.claude ./rig-claude-shared # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit nolte/claude-shared/plugins/nolte-claude-dev/skills/agent-review .claude/skills/agent-review $ npx degit nolte/claude-shared/plugins/nolte-claude-dev/skills/skill-agent-catalog-apply .claude/skills/skill-agent-catalog-apply $ npx degit nolte/claude-shared/plugins/nolte-claude-dev/skills/skill-management .claude/skills/skill-management $ npx degit nolte/claude-shared/plugins/nolte-claude-dev/skills/skill-review .claude/skills/skill-review $ npx degit nolte/claude-shared/plugins/nolte-claude-dev/skills/skills-agents-sweep .claude/skills/skills-agents-sweep $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/api-documentation-audit .claude/skills/api-documentation-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/api-error-check .claude/skills/api-error-check $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/bdd-scenario-generate .claude/skills/bdd-scenario-generate $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/capability-reach-audit .claude/skills/capability-reach-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/dependency-audit .claude/skills/dependency-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/deployment-chart-manage .claude/skills/deployment-chart-manage $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/dockerfile-audit .claude/skills/dockerfile-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/error-tracking-audit .claude/skills/error-tracking-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/guard-coverage-check .claude/skills/guard-coverage-check $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/kpi-derive .claude/skills/kpi-derive $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/license-check .claude/skills/license-check $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/maturity-assess .claude/skills/maturity-assess $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/observability-audit .claude/skills/observability-audit $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/quality-gate .claude/skills/quality-gate $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/release-regression-scope .claude/skills/release-regression-scope $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/source-code-review .claude/skills/source-code-review $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/test-cycle-orchestrate .claude/skills/test-cycle-orchestrate $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/test-pyramid-check .claude/skills/test-pyramid-check $ npx degit nolte/claude-shared/plugins/nolte-engineering/skills/webview-ui-optimize .claude/skills/webview-ui-optimize $ npx degit nolte/claude-shared/plugins/nolte-media/skills/gemini-image-handoff .claude/skills/gemini-image-handoff $ npx degit nolte/claude-shared/plugins/nolte-media/skills/image-generate .claude/skills/image-generate $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/feature-decompose .claude/skills/feature-decompose $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/mission-define .claude/skills/mission-define $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/mission-revise .claude/skills/mission-revise $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/roadmap-init .claude/skills/roadmap-init $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/roadmap-plan .claude/skills/roadmap-plan $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/roadmap-refine .claude/skills/roadmap-refine $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/sprint-execute .claude/skills/sprint-execute $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/sprint-plan .claude/skills/sprint-plan $ npx degit nolte/claude-shared/plugins/nolte-planning/skills/sprint-review .claude/skills/sprint-review $ npx degit nolte/claude-shared/skills/audience-identify .claude/skills/audience-identify $ npx degit nolte/claude-shared/skills/backlog-delivery-orchestrate .claude/skills/backlog-delivery-orchestrate $ npx degit nolte/claude-shared/skills/backstage-catalog-generate .claude/skills/backstage-catalog-generate $ npx degit nolte/claude-shared/skills/blog-author-trigger .claude/skills/blog-author-trigger $ npx degit nolte/claude-shared/skills/blog-author .claude/skills/blog-author
$ curl -fsSL --create-dirs -o .claude/agents/audience-doc-author.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/audience-doc-author.md $ curl -fsSL --create-dirs -o .claude/agents/audience-review.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/audience-review.md $ curl -fsSL --create-dirs -o .claude/agents/cicd-pipeline-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/cicd-pipeline-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/cookiecutter-template-author.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/cookiecutter-template-author.md $ curl -fsSL --create-dirs -o .claude/agents/diagram-opportunity-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/diagram-opportunity-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-freshness-checker.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/docs-freshness-checker.md $ curl -fsSL --create-dirs -o .claude/agents/lektorat-scanner.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/lektorat-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/link-rot-scanner.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/link-rot-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/mermaid-diagram-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/mermaid-diagram-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/portfolio-inflight-collector.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/portfolio-inflight-collector.md $ curl -fsSL --create-dirs -o .claude/agents/portfolio-manifest-collector.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/portfolio-manifest-collector.md $ curl -fsSL --create-dirs -o .claude/agents/project-structure-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/project-structure-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/prose-vale-curator.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/prose-vale-curator.md $ curl -fsSL --create-dirs -o .claude/agents/security-requirements-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/security-requirements-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-readiness-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/spec-readiness-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-stack-drift-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/tech-stack-drift-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-stack-fitness-reviewer.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/tech-stack-fitness-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/vocab-drift-scanner.md https://raw.githubusercontent.com/nolte/claude-shared/develop/agents/vocab-drift-scanner.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/scripts/guard_feature_branch_hook.py\""
}
]
}
]
}
} Skills (71)
agent-reviewskill-agent-catalog-applyskill-managementskill-reviewskills-agents-sweepapi-documentation-auditapi-error-checkbdd-scenario-generatecapability-reach-auditdependency-auditdeployment-chart-managedockerfile-auditerror-tracking-auditguard-coverage-checkkpi-derivelicense-checkmaturity-assessobservability-auditquality-gaterelease-regression-scopesource-code-reviewtest-cycle-orchestratetest-pyramid-checkwebview-ui-optimizegemini-image-handoffimage-generatefeature-decomposemission-definemission-reviseroadmap-initroadmap-planroadmap-refinesprint-executesprint-plansprint-reviewaudience-identifybacklog-delivery-orchestratebackstage-catalog-generateblog-author-triggerblog-authorcicd-pipeline-designcontinuous-improvement-triagecookiecutter-template-managedocs-audience-tracks-applydocs-dry-refactorgithub-issue-templates-applyissue-backlog-partitionissue-batch-orchestrateissue-orchestratelektorat-applylektorat-auto-revisemermaid-diagrams-applymkdocs-structure-applypermission-allowlist-maintainportfolio-auditportfolio-inflight-triageproject-structure-applypull-request-createpull-request-mergepull-request-runner-sweepreadme-structure-applyrelease-notes-curaterelease-publish-triggerrequirements-elicitspec-drift-auditspectech-stack-capturevocab-drift-auditworkflow-health-triageworking-copy-startyaml-json-schema
Subagents (18)
| audience-doc-author | Drafts or refines an audience-tailored doc (README, release notes, MkDocs pages, or any doc governed by spec/project/) against an existing `audience-identify` artifact. Invoke to write, draft, or refa |
| audience-review | Read-only review of an existing audience-analysis artifact against `spec/project/audience-identification/` (release notes also against release-notes-audience-analysis); returns a structured findings r |
| cicd-pipeline-reviewer | Read-only audit of a repository's CI/CD pipeline against spec/project/continuous-integration/, spec/project/continuous-delivery/, and spec/project/github-actions-best-practices/: stage sequence and om |
| cookiecutter-template-author | Scaffolds or refactors a Cookiecutter template (its pre_prompt/pre_gen/post_gen hooks and a pytest-cookies harness) so the rendered project conforms to the bound nolte spec corpus. Invoke to scaffold, |
| diagram-opportunity-reviewer | Read-only prose scanner that flags Markdown passages better expressed as a Mermaid diagram. Walks the in-scope set (default docs/<lang>/**/*.md), matches prose against the `spec/project/mermaid-diagra |
| docs-freshness-checker model: sonnet | Read-only audit of the current repo's MkDocs docs for freshness: multi-language parity (docs/en vs docs/de), dead internal links, stale references into spec/ or src/, ADR index/status hygiene, Mermaid |
| lektorat-scanner model: sonnet | Read-only editorial scanner dispatched by `lektorat-apply`: walks an in-scope Markdown set and returns a structured findings inventory across six dimensions (D1 readability, D2 comprehensibility, D3 g |
| link-rot-scanner model: sonnet | Read-only audit of the repo's docs for dead links: internal relative links, intra-page anchors, cross-tree references, and external http(s) URLs probed over the network. Wraps scripts/check_links.py a |
| mermaid-diagram-reviewer | Read-only static audit of every Mermaid block in docs/<lang>/ against spec/project/mermaid-diagrams/ plus the MkDocs setup (mkdocs.yml, docs/requirements.txt). Returns structured findings routed throu |
| portfolio-inflight-collector model: sonnet | Read-only in-flight data collector dispatched by `portfolio-inflight-triage`: gathers open issues, open PRs (incl. drafts), branches without an active PR to develop, and unresolved review threads plus |
| portfolio-manifest-collector model: sonnet | Read-only inventory collector dispatched by `portfolio-audit`: gathers each repo's project/portfolio.yml manifest across all nolte portfolio members and returns the raw tech-stack and capability inven |
| project-structure-reviewer | Read-only audit of the current repo against spec/project/project-structure/, producing a severity-sorted findings list routed through `project-structure-apply` or direct edits. Checks files/directorie |
| prose-vale-curator | Curates prose so it passes Vale, preferring shipped-vocabulary terms, and (only inside a repo that owns Vale vocabulary source, e.g. nolte/vale-style) extends an accept.txt for a legitimate technical |
| security-requirements-reviewer model: opus | Read-only security architect's review of a project's requirement/spec set (requirements, ADRs, spec docs) for security and privacy completeness, before or independently of implementation. Judges wheth |
| spec-readiness-reviewer model: sonnet | Read-only audit of specs under a target topic for downstream readiness along three dimensions: contradictions (intra- and cross-spec), audience fit, and domain completeness (Requirements-to-Acceptance |
| tech-stack-drift-reviewer | Read-only audit of a repo's declared tech-stack manifest (project/portfolio.yml tech_stack: for members; portfolio/tech-stack.yml globally) against spec/portfolio/tech-stack/ and tech-stack-discovery/ |
| tech-stack-fitness-reviewer model: opus | Read-only architect's review evaluating a project's declared tech stack for fitness against its own functional and non-functional requirements: coverage, gaps, over-/under-engineering, risks, and stac |
| vocab-drift-scanner model: sonnet | Read-only scanner dispatched by `vocab-drift-audit`: diffs repository-local Vale vocabulary files against the pinned upstream nolte/vale-style release and returns a two-section drift report (local ent |
Hooks (5)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/scripts/guard_feature_branch_hook.py" |
| SessionStart | * | python3 "$CLAUDE_PROJECT_DIR/scripts/wip_journal.py" --session-start |
| PreCompact | * | python3 "$CLAUDE_PROJECT_DIR/scripts/wip_journal.py" --compact |
| PostToolUse | Write|Edit|MultiEdit|NotebookEdit | python3 "$CLAUDE_PROJECT_DIR/scripts/wip_journal.py" |
| PostToolUse | Write|Edit|MultiEdit|NotebookEdit | python3 "$CLAUDE_PROJECT_DIR/scripts/validate_edited_artifact.py" |
Permissions
deny (0)
—
ask (0)
—
allow (29)
Bash(task lint)
Bash(task test)
Bash(task docs)
Bash(vale *)
Bash(gh label list)
Bash(gh label list *)
Bash(git fetch)
Bash(git fetch *)
Bash(git merge-base *)
Bash(git rev-list *)
Bash(git ls-remote *)
Bash(git check-ignore *)
mcp__github__get_me
mcp__github__list_repository_collaborators
mcp__github__list_issues
mcp__github__issue_read
mcp__github__search_issues
mcp__github__list_pull_requests
mcp__github__pull_request_read
mcp__github__search_pull_requests
mcp__github__list_branches
mcp__github__list_commits
mcp__github__get_file_contents
mcp__github__list_releases
mcp__github__get_latest_release
mcp__github__get_release_by_tag
mcp__github__list_discussions
mcp__github__get_discussion_comments
mcp__github__list_discussion_categories
Similar rigs
brunella328/andon
Andon — a human-in-the-loop SDLC for AI coding agents. Pull the cord, stop the line: five-phase governance + craft skills as a Claude Code plugin(人與 AI 協作的產品開發流程)
Skill Collector 597 tok · · Q0
jaemyeong-hwnag/claude-marketplaces
Claude Code plugin marketplace — hooks, skills and MCP that enforce naming conventions, GitHub workflow, AI test coverage, secret scanning, stress testing and evidence-based AI reviews.
Skill Collector 5.0k tok · · Q15
jcdendrite/claude-config
Portable Claude Code global configuration: custom skills, PreToolUse hooks, and a custom statusline. Runs on Linux, macOS, WSL.
Fort Knox 13.6k tok · · Q28
kamo-shika/chezmoi-dotfiles-starter
Claude Code のスキルを中央集権せずに chezmoi で配る dotfiles スターターキット
Minimalist 212 tok · · Q15