Ship & operate
32,342 rows, by stacks then stars
1,245 of these skill files have been read, by 1,077 distinct authors, and what they tell an agent counted. What Ship & operate authors agree on, and what they forbid
waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/n8n-skills/skills/n8n-validation-expert Skill
no license0★ repoInterpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.
The same file is in 3 other repositories
waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/n8n-skills/skills/n8n-workflow-patterns Skill
no license0★ repoProven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
The same file is in 3 other repositories
waseemnasir2k26/skynetlabs-all-claude-code/skills/seo-content-copy/citation-monitor Skill
no license0★ repoTrack brand mention citations across 4 LLMs (Claude, ChatGPT, Perplexity, Gemini) for a configurable list of brand keywords. Daily cron pulls write to local sqlite. Weekly markdown report shows mention counts, position, and citation deltas. Powers citelift.app SaaS upgrade path. Local-first; Supabase + n8n optional later.
Salesforce release notes navigator
ayanme/salesforce-navigator-suite/skills/salesforce-release-notes-navigator Skill
0★ repoThis Navigator researches Salesforce product releases, new features, and change history from official release notes. Use when the user asks what changed, what's new, or what was released for Salesforce products: new features, GA, Beta, Pilot, deprecations, breaking changes, upgrade guidance, Agentforce, Data Cloud, Marketing Cloud, Marketing Cloud Personalization, CRM Analytics, and MuleSoft. Does not own developer API or SDK changelogs.
SkillMedev/incident-response-command/skills/observability-stack Skill
0★ repoInstruments systems with the three pillars - structured logs, RED/USE metrics, and distributed traces - correlated by one trace ID, with cardinality budgets and symptom-based alerts. Use when someone asks "how should I instrument this service", "what metrics should I emit", "why is my metrics bill exploding", "set up OpenTelemetry for my stack", or "we can't tell which service is slow". Do NOT use for tuning an existing noisy pager or alert thresholds - use alert-tuning instead; for defining SLO error-budget policy, use error-budget-policy; for the incident process when alerts fire, use sev-triage and postmortem-writer.
The same file is in 2 other repositories
SkillMedev/incident-response-command/skills/oncall-handoff Skill
0★ repoProduces a complete on-call shift handoff note - shift summary, open incidents, watch items with paging thresholds, silenced alerts, in-flight changes, and escalation contacts - checked against a completeness checklist. Use when someone asks "write my on-call handoff", "what should I tell the next on-call", "my shift ends in an hour, help me hand over", or "make a handoff template for our rotation". Do NOT use for writing the incident postmortem after resolution - use postmortem-writer instead. For live severity assessment during an incident, use sev-triage; for external customer-facing incident comms, use status-page-update.
The same file is in 1 other repository
SkillMedev/incident-response-command/skills/postmortem-writer Skill
0★ repoWrites blameless incident postmortems with a log-reconstructed timeline, multi-causal contributing factors, and owned, dated action items. Use when someone asks "write the postmortem for yesterday's outage", "run a blameless retro on this incident", "turn these incident notes into a postmortem doc", or after any SEV1 or SEV2 event. Do NOT use for customer-facing incident updates while the incident is live - use status-page-update instead; for transferring context at a shift change, use oncall-handoff; for classifying and running a live incident, use sev-triage.
The same file is in 1 other repository
SkillMedev/incident-response-command/skills/status-page-update Skill
0★ repoWrites customer-facing incident status updates for each lifecycle stage - investigating, identified, monitoring, resolved - with cadence rules and plain-language templates. Use when someone asks "write a status page update", "what do we tell customers about this outage", "draft the resolved notice", or during an active incident needing customer communication. Do NOT use for the internal post-incident analysis - use postmortem-writer once the incident is closed; for deciding severity and internal escalation flow use sev-triage; for summarizing an incident upward to executives use escalation-summary.
The same file is in 1 other repository
mohitkhandelwal242/ai-pm-operator/.claude/skills/release-notes-writer Skill
no license0★ repoGenerate slide content for the Product section of a leadership weekly / release-notes deck. Aggregates user-visible product ships from the last 4 weeks across all of the business's repos (the current git repo + every repo in business.json → stack.code_repos[]) plus Jira Done items in ${PROJECT_KEY}, groups them by theme, and produces per-experiment slides with measured impact tables. Use when asked for 'leadership product slides', 'product week deck', 'release notes deck', 'what shipped to production', '/leadership-product-weekly', or '/product-weekly'.
Drvivek34/Skill-Bazaar/devops-infrastructure/ci-cd-troubleshooter Skill
no license0★ repoUse when analyzing failing build/test logs in Github Actions, GitLab, or Jenkins, and fixing pipeline configuration files.
digitaldreams/tuhin/skills/deployment Skill
0★ repoProduces a release procedure for the current application, writing tasks/deployment.md. Inspects the repo (CI config, .env.example, migrations, queue/scheduler usage) plus tasks/architecture.md when present. Use whenever the user says "deployment plan", "release checklist", "how do we ship this", "prepare for production", or as the end-of-pipeline SDLC step.
digitaldreams/tuhin/skills/task-workflow Skill
0★ repoCore loop for executing tasks from the tasks.md board — claim, plan checkpoint, worktree, implement, quality gates, draft PR, review handoff, human notification. Use whenever asked to work the task board, run the next task, or continue a task in progress.
sayeediftekhar/Keel/skills/keel-ops Skill
0★ repoOperations & connectors lane router. Routes memory, workspace connectors, and meta/skills-management to the right tool — claude-mem, granola, slack, notion, zapier MCPs, plus find-skills and the claude-skills library. Defers to keel-v2. Use for persistent memory, pulling meeting notes, reading/writing Slack or Notion, wide app automation, or discovering/installing new skills.
bradmccloskey/claude-cisco-skills/cisco-netauto Skill
0★ repoGenerate Python scripts for Cisco network automation using RESTCONF, NETCONF, DNA Center, or Meraki APIs. Use when the user wants to automate Cisco devices using APIs and SDN controllers rather than CLI/SSH.
youki0p0/jen-marketplace/plugins/jen/skills/jen-release Skill
0★ repoJen release mode for PR summary, changelog, verification packet, rollback plan, and human deploy checklist.
lankyjo/lankyjo-core-skills/skills/code/codebase-audit Skill
no license0★ repoAudits a software codebase across 29 dimensions — security, privacy, accessibility, sector compliance (HIPAA/PCI/SOC 2/ISO 27001/FedRAMP/COPPA/ FERPA/GLBA/EU AI Act/NIS2/DORA/Quebec Law 25/etc.), architecture, testing, dependencies, code reuse / consolidation, workaround / root-cause detection, performance, speed, DevOps, cost, engineering practice, UX, product gaps, frontend modernization, i18n, SEO, AI/ML, and product-type platform idioms. Produces structured docs under `/docs/audits/` and files real remediation tickets. Use for any audit / review / analysis request, including narrow asks like "security review", "is this accessible", "are we GDPR/HIPAA/PCI/SOC 2 compliant", "is the app slow", "is this ready to ship", "audit our deployment", "find product gaps", "is our SEO any good", "are our deps current", "are we overpaying for infra", "can a new dev onboard". The `/audit` command is the user-facing entry point.
lankyjo/lankyjo-core-skills/skills/code/vercel-composition-patterns Skill
no license0★ repoMy curated set of core Claude Code skills — gathered, not authored. Full credit to every original author. Install: npx skills add lankyjo/lankyjo-core-skills
The same file is in 23 other repositories
lankyjo/lankyjo-core-skills/skills/code/vercel-react-best-practices Skill
no license0★ repoReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
The same file is in 2 other repositories
DazzleML/dazzle-claude-code-config/dotclaude/skills/dev-workflow-process Skill
0★ repoInitiates a structured analysis of a problem using the DEV WORKFLOW PROCESS with specific contextual guidance.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-iteration-loop Skill
no license0★ repoOrchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the oncall-schedule-coverage-collapse task (<TASK_ID>) until Oracle scores 1.0 and rollout avg < <TARGET_MEAN> with both subscores varying and decorrelated. Delegates to oncall-task-guardian, oncall-validation-debugger, oncall-score-tuner, and horizon-agentic-reviewer at the right phases. The agent executes every step except triggering the rollout batch.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-score-tuner Skill
no license0★ repoDiagnose rollout regressions and tune difficulty for the oncall-schedule-coverage-collapse task (<TASK_ID>). Keeps avg rollout score < <TARGET_MEAN> with both subscores varying and decorrelated (coverage_restored vs monitoring_governance share the drift surface), and never weakens the hidden <metadata-key> / gap-rule variance gates. Picks the smallest safe lever for the observed symptom.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-task-guardian Skill
no license0★ repoEnd-to-end maintenance skill for the oncall-schedule-coverage-collapse task (<TASK_ID>). Owns the pre-push safety checks, local quality/anatomy gates, push, Oracle validation handoff, and rollout monitoring. Primary goal is to keep avg rollout score < <TARGET_MEAN> with healthy, decorrelated variance across both subscores. Calls oncall-validation-debugger when Oracle fails and oncall-score-tuner when rollouts regress.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-validation-debugger Skill
no license0★ repoFetches and interprets validation logs (No-Op and Oracle) for the oncall-schedule-coverage-collapse task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.
yujiyamane/pbi-ai-skills/.github/skills/pbi-deployer Skill
0★ repoDeploy a Power BI Project (PBIP) to Power BI Service / Microsoft Fabric using fabric-cicd. One-command deploy from a local PBIP folder to a target workspace. Use when user says: 'deploy dashboard', 'publish to Power BI', 'deploy to fabric', 'push PBIP', 'run deployer', 'deploy this report', 'fabric deploy', or provides a PBIP path with deployment intent.
yujiyamane/pbi-ai-skills/pbi-deployer Skill
0★ repoDeploy a Power BI Project (PBIP) to Power BI Service / Microsoft Fabric using fabric-cicd. One-command deploy from a local PBIP folder to a target workspace. Use when user says: 'deploy dashboard', 'publish to Power BI', 'deploy to fabric', 'push PBIP', 'run deployer', 'deploy this report', 'fabric deploy', or provides a PBIP path with deployment intent.
moses607/skillforge/skills/incident-postmortem Skill
0★ repoProduce a blameless incident postmortem from an outage description, timeline, or chat log. Use whenever the user mentions an outage, incident, downtime, "we had a P1/SEV", a production failure, a service degradation, or asks to write up what went wrong and how to prevent it. Trigger even for small incidents — the structure matters more than the size.
willianbs/skills/observability-designer Skill
0★ repoDesigns SLIs/SLOs, structured logs, traces, and alert quality for a feature or service. Use when shipping new paths or fixing noisy/missing alerts. Emits OBS_PLAN. Never recommends alert spam or metrics without a user/journey signal.
willianbs/skills/postmortem-writer Skill
0★ repoWrites blameless postmortems from incident and RCA artifacts. Use after incidents resolve. Emits POSTMORTEM. Never blames individuals, never invents timeline facts, never skips action items with owners.
willianbs/skills/quality-gate Skill
0★ repoFinal merge/deploy readiness gate that aggregates specialist reports and enforces mandatory blockers. Use before merge or release. Emits QG_REPORT. Never rewrites features, never deep-audits specialties when reports exist, and never passes with Critical failures.
goingli0324/muzi-going-skills/plugins/ui-ux-deploy-reviewer/skills/ui-ux-deploy-reviewer Skill
0★ repo以 20 項 UI/UX 原則(Nielsen 啟發法+互動心理學定律+可及性)審視前端程式碼與使用者體驗,輸出依嚴重度排序的問題清單與部署放行檢核表。當使用者明確要審查 UI/UX、易用性、heuristic evaluation,或問「這個網站好不好用」時觸發;未指明範圍的「部署前檢查」交給 agentic-dev-loop 走雙閘。也是該迴圈的 UI/UX 閘。
gmmh1/claude-paid-media-skills/skills/google-ads-api-automation Skill
0★ repoAutomate Google Ads work at scale using Google Ads Scripts or the Google Ads API — bulk changes, automated rules, scheduled reporting pulls, programmatic offline conversion imports. Triggers on 'automate my Google Ads', 'write a Google Ads script', 'bulk update my campaigns', 'automated bid rules', or 'pull Google Ads data via API'. For one-off manual campaign work, use google-ads-campaign-builder instead.
gmmh1/claude-paid-media-skills/skills/meta-ads-api-automation Skill
0★ repoAutomate Meta Ads work at scale using the Marketing API — bulk campaign creation, automated rules, and scheduled reporting pulls. Triggers on 'automate my Meta Ads', 'Marketing API script', 'bulk create Meta campaigns', or 'automated rules for Facebook Ads'. For one-off manual campaign work, use meta-ads-campaign-builder instead.
gitsukrit/claude-skills/phi-safe-logging-enforcer Skill
0★ repoEnforce HIPAA Safe Harbor de-identification (45 CFR §164.514(b)(2)) and Security Rule audit controls (45 CFR §164.312(b)) whenever generating Python code that logs, traces, or emits telemetry involving PHI. Use this skill whenever the user asks to build, modify, review, or refactor code that touches Python `logging`, `structlog`, `loguru`, Langfuse, LangSmith, OpenTelemetry, Sentry, Datadog, or any other observability/telemetry surface in a healthcare AI, clinical, patient-facing, or PHI-adjacent context. Also use when the user asks for audit trail implementations, LLM API call logging, error tracking, or any code that will send request/response bodies to a third-party observability service. Do not wait for explicit "HIPAA" framing — trigger on any healthcare-adjacent logging or telemetry request, since PHI leakage into observability tools is one of the most common breach patterns and is invisible in code review without this discipline.
rabius-sunny/agent-skills/vercel-composition-patterns Skill
no license0★ repoSelected agent skills
The same file is in 23 other repositories
rabius-sunny/agent-skills/vercel-react-best-practices Skill
no license0★ repoReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
The same file is in 17 other repositories
allenlee0430/allenlee-lab-skills/lab-pi-ops Skill
0★ repoRecurring PI/lab-management tasks for Bowen Li — group-meeting decks, weekly trainee updates, reference/recommendation letters, teaching materials (PHM142), committee and seminar prep, and trainee tracking. Triggers on "group meeting", "weekly update", "recommendation letter", "reference letter", "PHM142", "committee meeting", "seminar", "onboarding".
lexthirteen-ai/founder-survival-kit/skills/ship-it-for-real Skill
0★ repoTurns "it worked when I tried it" into a repeatable check that survives real users. Helps a founder write down the handful of things their app must always do, turn those into a simple test they can rerun after every change, and close the gap between a demo that works and a product that holds up on real, messy input. Use when an app or agent works in the demo but breaks on real users, when changes keep breaking things that used to work, or before relying on something in production. Builds a repeatable check, not a test suite.
ccpowerpack/claude-code-skills/skills/release-notes Skill
0★ repoGenerate release notes / changelog from git history, grouped by audience with breaking changes first. Use when the user asks for release notes, a changelog entry, "what changed since", or is cutting a release/tag.
chsistrying/swift-ship-skills/skills/swift-release-flow Skill
0★ repoDrives a clean, end-to-end release of a macOS/Swift app hosted on GitHub — preflight checks, version bump, CHANGELOG update, DMG build, git tag, and GitHub release. Use when asked to cut a release, publish a version, ship a new build, create a GitHub release DMG, or tag and release a macOS app. Trigger with "/swift-release-flow".
natexai2026/2030-skills/skills/protect-the-skill Skill
0★ repoBefore adopting AI or automation for a task, locate the real bottleneck (is it inside or outside the automatable step?) and flag which human capability will atrophy from offloading — so you automate the right thing without deskilling yourself or your team. Use whenever deciding to adopt an AI tool for a workflow, whether to automate a task or role, how to integrate AI into learning or professional practice, or "will AI replace this job." Triggers on "should we automate X," "will AI take this job," "should I use AI for this," tool-adoption decisions, curriculum/training design, and worries about skill loss or over-reliance. Applies to individuals, teams, and educators.
AmanKrSahu/zeroday-auditor/skills/zeroday-auditor Skill
0★ repoUse when the user wants a COMPLETE / comprehensive / full engineering audit or production-readiness assessment covering all dimensions at once — architecture, security, performance, code quality, platform/ops, product, technical debt, and modernization — or says things like 'audit the whole repo', 'review everything', 'find everything wrong', 'is this production-ready?'. Produces an enterprise-grade, evidence-backed, multi-specialist report of 10 cross-referenced Markdown documents under engineering-audit/. For a SINGLE dimension, prefer the focused skills instead: security-audit, performance-audit, architecture-review, code-quality-review, modernization-audit. Analysis and documentation only; never modifies application source.
manman1414/frontend-refactor-skills/skills/strangler-refactor Skill
0★ repoReplaces legacy frontend modules incrementally using the strangler fig pattern — Vue 2 to Vue 3, Options API to Composition API, class components to hooks, old design system to new — with feature flags, parallel routes, and rollback paths. Use when migrating frameworks, replacing large legacy components, or rewriting modules without a big-bang release.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-incident/.claude/skills/incident-response Skill
0★ repoLive incident protocol when production is impacted — triage blast radius and "what changed", mitigate first (rollback / flag / failover), preserve evidence before state-destroying actions, keep a timestamped timeline, diagnose production-safely, fix through normal gates, verify with a monitoring window. Use the moment production impact (users, data, money, security) is detected or imminent; not for ordinary bugs.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-incident/.claude/skills/postmortem Skill
0★ repoBlameless postmortem after a resolved incident — reconstruct the timeline, compute time-to-detect / time-to-mitigate / time-to-resolve, separate root cause from contributing factors, mine what-went-well and what-was-lucky, produce action items through three lenses (detect faster / prevent the class / mitigate faster), and route lessons into rules via retro. Use after incident-response closes; the incident is not done until this exists.
lightarktech/founder-coding-skills/skills/grill-founder Skill
0★ repoInterview a non-technical founder to surface blind spots before executing any deliverable — code or otherwise. Use before a feature request, a launch, publishing or any external content, marketing copy and positioning decisions, pricing, deploy, hosting, domain or migration work, infrastructure changes, or dispatching agents/subagents to do the building. Trigger on any vague instruction ("add a login page", "refresh the site", "make it feel warmer", "just ship it") and on any request with irreversible side effects or more than an hour of work.
sumitake/agent-collab/plugins/agent-collab/skills/incident-responder Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/kubernetes-specialist Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/sre-engineer Skill
no license0★ repoBuilds and improves system reliability through SLO design, error-budget policy, toil reduction, and resilience architecture. Use when the user says "help me define SLOs for this service", "what's our error budget burn rate", or "reduce the toil in this on-call rotation", or "/agent-collab:sre-engineer." Also offer this proactively when a reliability review, capacity plan, or alert-quality audit is warranted ahead of a launch or growth milestone.
sumitake/agent-collab/plugins/agent-collab/skills/terraform-engineer Skill
no license0★ repoDesigns, refactors, and reviews Terraform infrastructure-as-code across cloud providers, with a focus on module contracts, state safety, and reviewable plans. Use when the user says "review this Terraform plan", "help me design a reusable module", or "why did this apply want to replace my resource", or "/agent-collab:terraform-engineer." Also offer this proactively when a change touches module interfaces, state backend configuration, or resource lifecycle blocks.
soreavis/claude-audit-skills/plugins/audit/skills/deploy Skill
0★ repoPre-deployment production readiness checklist. Checks build health, debug code, dev URLs, env vars, error tracking, analytics, SEO, legal pages, and git state. Run before every production push.
supermodo/skills/skills/release Skill
0★ repoRun a versioned release with git-flow discipline: deterministic preflight (branch, clean tree, Conventional Commits since last tag → suggested semver bump), changelog entry written from fragments/commits into the changelog file automatically, then the exact squash-merge/tag/push/GitHub-release sequence printed and consent-gated by default (configurable auto mode). Two configurable modes: light (dev → main) and full git-flow (release/* stabilization + hotfix/* branches). Use for 'release', 'cut a release', 'ship a version', 'bump the version', 'publish vX.Y.Z', 'hotfix production' — whenever accumulated work should become a tagged, published version.
tamasbege/staff-engineer-skills/plugins/staff-engineer-skills/skills/cold-start-optimizer Skill
0★ repoProduce a tailored cold-start and first-load performance optimization plan for frontend apps (bundle size, FCP/LCP, code splitting, caching) and backend/serverless services (JVM startup, AWS Lambda / Azure Functions cold starts, container boot). Use when the user reports a slow first load, poor Lighthouse or Core Web Vitals scores, large JS bundles, serverless cold starts, slow Spring Boot startup, or asks how to make an app start or load faster.
tamasbege/staff-engineer-skills/plugins/staff-engineer-skills/skills/event-pipeline-architect Skill
0★ repoDesign production-grade event-driven pipelines with implementation-ready depth - event catalogs, payload schemas, producers and consumers with the outbox pattern, retries, DLQs, idempotency, schema evolution, scaling, observability, and infrastructure-as-code. Use when adding async processing between services, decoupling producers from consumers, migrating from synchronous to event-driven communication, designing Kafka / Azure Service Bus / AWS SQS-SNS / RabbitMQ / Pub-Sub topologies, or redesigning retry and failure handling for existing events.
nbsp1221/agent-skills/skills/docker-compose Skill
no license0★ repoWrite and review Docker Compose files with consistent best practices and conventions (file naming, override strategy, service naming, key ordering, env handling, ports, and healthchecks). Use when creating or standardizing compose.yaml/docker-compose.yml.
theinterneti/TTA.dev/.claude/skills/generated/observability Skill
0★ repoObservability subsystem in TTA.dev: demo_hierarchical_trace, handle_api_active_agents, handle_api_agent_actions and related code. 115 symbols | 38 files | Cohesion: 73%
theinterneti/TTA.dev/.claude/skills/sdd-workflow Skill
0★ repoUse this skill when the user asks to build a new feature or write implementation code. Enforces the Spec-Driven Development (SDD) 4-phase workflow before any code is written.
theinterneti/TTA.dev/.github/skills/incident-response Skill
0★ repoEmergency response workflow for production issues
theinterneti/TTA.dev/.github/skills/package-release Skill
0★ repoMulti-persona workflow for releasing TTA.dev packages to PyPI with full quality validation
theinterneti/TTA.dev/.github/skills/sdd-workflow Skill
0★ repoUse this skill when the user asks to build a new feature, implement code, or start development work. Enforces the Spec-Driven Development (SDD) 4-phase workflow before any code is written. Invoke when the user says "build", "implement", "create a feature", "write code for", or "add support for".
gabriel-f-santos/coding-agents/skills/github-actions Skill
no license0★ repoGenerate and secure GitHub Actions workflows. Use to scaffold or review CI/CD — "criar workflow", "github actions", "pipeline CI/CD", "workflow de deploy", "gera o GHA", "configurar deploy no push da main", "set up CI", "revisar segurança do workflow", "audit workflows", "GHA security review". GENERATE mode interviews the pipeline shape (lint/test/build/deploy; trigger on PR/MR vs push-to-main vs tag; deploy target + approvals) and writes secure-by-default workflows (least-privilege GITHUB_TOKEN, third-party actions pinned to SHA, no ${{ }} in run: blocks, OIDC deploy, concurrency, path filters, dependency cooldown/osv). REVIEW mode audits existing .github/workflows for exploitation vulns (pwn request, expression injection, comment-triggered commands, credential escalation, supply chain) with concrete attack paths — security art adapted from Sentry's gha-security-review. Do not use for non-GitHub CI (GitLab/CircleCI) or to write app code.