Architecture & codebase
12,712 rows, by stacks then stars
1,011 of these skill files have been read, by 858 distinct authors, and what they tell an agent counted. What Architecture & codebase authors agree on, and what they forbid
khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/android-clean-architecture Skill
no license5★ repoClean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
The same file is in 7 other repositories
khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/django-patterns Skill
no license5★ repoDjango architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
The same file is in 8 other repositories
khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/springboot-patterns Skill
no license5★ repoSpring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
The same file is in 8 other repositories
khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/research-utility/api-design Skill
no license5★ repoREST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
The same file is in 11 other repositories
khanhhuyenngo985-sys/character-scene-design-skills/skills/teach-impeccable Skill
no license5★ repoOne-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
khanhhuyenngo985-sys/character-scene-design-skills/skills/video-reverse-engineer Skill
no license5★ repo对广告/短视频进行结构化拆解,输出镜头语言、色彩、节奏、音频的完整分析报告,用于学习竞品手法、建立案例库、AI生成时做风格参考。触发词:「反推」「拆解视频」「分析广告」「视频反推」「学习这个视频」「竞品分析」「拉片」。
lteawoo/skills/skills/codebase-explainer Skill
no license5★ repoExplain the structure, responsibilities, entry points, and dependencies of a directory, module, or feature. Use it to understand an unfamiliar codebase or gather context before making changes.
TommyBez/skillsboard/.agents/skills/onboarding Skill
5★ repoWhen the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are signing up but not sticking around. For signup/registration optimization, see signup. For ongoing email sequences, see emails.
The same file is in 3 other repositories
TommyBez/skillsboard/.agents/skills/site-architecture Skill
5★ repoWhen the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions "sitemap," "site map," "visual sitemap," "site structure," "page hierarchy," "information architecture," "IA," "navigation design," "URL structure," "breadcrumbs," "internal linking strategy," "website planning," "what pages do I need," "how should I organize my site," or "site navigation." Use this whenever someone is planning what pages a website should have and how they connect. NOT for XML sitemaps (that's technical SEO — see seo-audit). For SEO audits, see seo-audit. For structured data, see schema.
The same file is in 5 other repositories
christopherlouet/claude-base/.claude/skills/dev-refactor Skill
5★ repoCode refactoring to improve quality. Trigger when the user wants to clean up, restructure, or improve existing code.
christopherlouet/claude-base/.claude/skills/qa-tech-debt Skill
5★ repoTechnical debt management and prioritization, including test-coverage analysis and Kaizen continuous improvement. Trigger when the user wants to identify, prioritize or plan the repayment of technical debt, analyse/improve test coverage, or run a PDCA continuous-improvement cycle.
christopherlouet/claude-base/.claude/skills/work-explore Skill
5★ repoExplore and understand an existing codebase. Use when the user wants to understand the code, explore a project, discover an architecture, or before modifying existing code.
recallnet/codecontext/skills/codecontext-setup Skill
no license5★ repoSet up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.
donald-ada/workinggenius/skills/setup-working-genius Skill
5★ repoOptional per-repo configuration — pin the work-file directory and verify commands so every stage runs them the same way.
amadeus-dlc/amadeus/.agents/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/.agents/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/.kimi-code/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/.kimi-code/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/amadeus/spaces/default/knowledge/amadeus-shared/software-design/clean-architecture Skill
5★ repoUse only when the user explicitly asks for Clean Architecture design, implementation, or review. Applies a domain, use case, interface adapter, and infrastructure layer model, with persistence and RPC adapters outside the domain and use-case rules. Do not trigger for generic architecture advice, hexagonal architecture, onion architecture, or ordinary design review unless Clean Architecture is named.
amadeus-dlc/amadeus/amadeus/spaces/default/knowledge/amadeus-shared/software-design/refactoring-packages Skill
5★ repoUse when actively refactoring an existing codebase's package or module structure. Detects cycles, oversized modules, misplaced responsibilities, and dependency direction problems, then proposes and executes a migration plan. Trigger for cleaning dependencies, breaking cycles, splitting modules, moving files, or structural refactoring work.
amadeus-dlc/amadeus/dist/claude/.claude/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/dist/claude/.claude/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/dist/codex/.agents/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/dist/codex/.agents/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/dist/kimi/.kimi-code/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/dist/kimi/.kimi-code/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/dist/kiro-ide/.kiro/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/dist/kiro-ide/.kiro/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
amadeus-dlc/amadeus/dist/kiro/.kiro/skills/amadeus-init Skill
5★ repoStart an AI-DLC workflow — run the whole Initialization phase (mint the intent, detect the workspace, build state) in one step, without typing a stage. The engine normally auto-births the first intent; this is opt-in packaging over that move. Pass `--scope <name>` to seed the initial scope (defaults to poc), or a freeform description of what to build.
amadeus-dlc/amadeus/dist/kiro/.kiro/skills/amadeus-observability-setup Skill
5★ repoRun the AI-DLC `observability-setup` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage observability-setup --single`: the engine emits one run-stage directive for observability-setup and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
mataeil/OODA-loop/skills/ooda-config Skill
5★ repoView, modify, and validate config.json settings via slash commands.
mataeil/OODA-loop/skills/ooda-setup Skill
5★ repo3-step project setup wizard. Auto-detects language, test framework, CI, and endpoints. Creates config.json from config.example.json.
Destynova2/cli-code-skills/cli-audit-tangle Skill
5★ repoDetect spaghetti code and dependency cycles using graph theory, spectral analysis, and biomimetic patterns. Finds god functions, circular dependencies, dead code, suboptimal module boundaries, CI/CD pipeline deadlocks, and inefficient call patterns. Uses call graph topology (not just line-level metrics) to identify structural problems invisible to linters. Provides concrete fix patterns per domain. Use when the user says 'spaghetti', 'tangle', 'untangle', 'god function', 'god object', 'circular dependency', 'cycle detection', 'call graph', 'module coupling', 'dead code', 'code topology', 'complexity analysis', 'who calls who', 'démêler', 'couplage', 'dépendances circulaires', 'fonction dieu', 'code mort', 'import cycle', 'ImportError', 'pipeline deadlock', 'CI stuck', 'needs deadlock', 'everything depends on everything'. Also triggers on 'refactor structure', 'split module', 'too coupled', 'architecture debt', 'dependency diagnostic', 'workflow cycle'.
Destynova2/cli-code-skills/cli-audit-wizard Skill
5★ repoAudit configuration wizard UX and lifecycle quality (setup, doctor, edit, migrate). Scores the 4 Laws (ask once, defaults, recap, config-as-code), credential discovery, multi-surface consistency (CLI/MCP/web), and scriptability. Detects wizard anti-patterns. Use on 'wizard', 'setup flow', 'config UX', 'init command', 'doctor mode', 'wizard audit', 'onboarding UX', 'first-run experience', 'config lifecycle', 'wizard broken', 'interactive setup', 'MCP config', 'config reload'.
Destynova2/cli-code-skills/cli-forge-doc Skill
5★ repoGenerate and audit comprehensive project documentation from a Git repository. Produces standard documentation (CONTRIBUTING.md, architecture, troubleshooting) in Diataxis structure with zero AI markers by default. Use this skill whenever someone asks to document a project, generate docs, create a README, write API docs, or improve existing documentation. Also trigger when someone mentions "doc", "documentation", "readme", "explain this codebase", "onboard developers", or "make this project understandable".
Destynova2/cli-code-skills/cli-forge-hld Skill
5★ repoGenerate a High-Level Design (HLD) document for a software system. Use when the user mentions 'HLD', 'system design', 'architecture document', 'design doc', 'ADR', 'C4 diagram', 'back-of-envelope', 'capacity planning', 'ATAM', 'arc42', 'design proposal', 'Gate review', or says 'design X', 'architect Y'. Produces C4 L1-L2 diagrams, capacity estimations, ADRs, tradeoff analysis, and deployment architecture. Do NOT use for low-level/detailed design (class diagrams, DB schemas, API specs) — use cli-forge-lld instead.
Destynova2/cli-code-skills/cli-forge-infra Skill
5★ repoOps integration assistant — reads service docs, finds the simplest config path (CLI/Helm/Operator/Terraform), builds dependency trees, proposes upgrade paths, and tracks decisions in ADRs. Use when debugging infra, integrating services, bootstrapping platforms, upgrading versions, simplifying config, or reviewing infrastructure code. Triggers on ops tool names (OpenBao, Vault, Consul, Traefik, Gitea, ArgoCD, Prometheus, Grafana, cert-manager, Istio, Linkerd, Terraform, OpenTofu, Podman, Docker, K8s, etc.) or keywords like "bootstrap", "integrate", "simplify config", "upgrade infra", "ops stack", "service mesh", "dependency tree".
Destynova2/cli-code-skills/cli-forge-tree Skill
5★ repoUse this skill whenever the user wants to visualize, generate, audit, or scaffold a project directory structure. Triggers include: 'project structure', 'folder structure', 'directory layout', 'tree', 'arborescence', 'scaffold', 'init project', 'organize my files', 'naming conventions', or any request to understand or create how files and folders should be organized in a codebase. Also triggers when someone says 'create a new project', 'bootstrap', 'init', or asks 'where should I put this file'. Use for any language or framework. Do NOT use for file system operations unrelated to project organization (like disk cleanup or backup scripts).
gustavo-meilus/superpipelines/plugins/superpipelines/skills/pipeline-architect-protocol Skill
5★ repoLoaded by the pipeline-architect agent to design or mutate Superpipelines pipeline topology and data-only CAD artifacts.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/skill-architect-protocol Skill
5★ repoLoaded by the skill-architect agent to design or revise Superpipelines-compatible skills.
gustavo-meilus/superpipelines/skills/pipeline-architect-protocol Skill
5★ repoLoaded by the pipeline-architect agent to design or mutate Superpipelines pipeline topology and data-only CAD artifacts.
gustavo-meilus/superpipelines/skills/skill-architect-protocol Skill
5★ repoLoaded by the skill-architect agent to design or revise Superpipelines-compatible skills.
Syncfusion wpf getting started
syncfusion/wpf-ui-components-skills/skills/syncfusion-wpf-getting-started Skill
no license5★ repoComprehensive guide for setting up and getting started with Syncfusion WPF components in Windows Presentation Foundation applications. Covers installation methods (web installer, NuGet, offline installer), system requirements verification, adding controls to projects, configuring themes and localization, and troubleshooting setup issues. Use this skill when users need help with installing Syncfusion WPF, configuring NuGet packages, upgrading versions, or resolving setup and configuration problems.
syncfusion/wpf-ui-components-skills/skills/syncfusion-wpf-licensing Skill
no license5★ repoComprehensive guide for implementing, registering, and troubleshooting Syncfusion licensing across all platforms. Covers license key registration, license validation errors, RegisterLicense API, SyncfusionLicenseProvider configuration, trial vs. licensed versions, CI/CD build server setup, and platform-specific licensing requirements. Use this skill when users need help with Syncfusion license registration, licensing validation issues, or license-related troubleshooting.
sergeyklay/.agents/.agents/skills/review-arch Skill
5★ repoConduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use when someone says 'review this architecture', 'is this design sound', 'what's wrong with this topology', 'evaluate these tradeoffs', or 'audit this system'. Produces a structured verdict organized around critical risks, significant concerns, observations, strengths, and open questions, grounded in evidence from the codebase and cited against established methodology (ATAM, ISO/IEC 25010, documented anti-pattern catalogues). Do NOT use for line-by-line code review, spec-vs-implementation verification, or PR-level correctness checks.
IncommensurableHubris/fullstack-director/.agents/skills/02-designer Skill
5★ repoRealize the UX for a sprint — turn the spine's design-intent + the sprint's REQs into a tiered design system, per-screen specs, and a DM-ID manifest, all referencing REQs. The FIRST skill to run the Reconcile step: it challenges docs/spec/design-intent.md through the amendment protocol — fleshing out derived/[NEEDS CLARIFICATION] intent, and flagging where the realization violates a stated intent or the WCAG 2.2 AA floor (a brand color failing contrast is a computed contradiction) — and emits structured amendment rows. Use when the user says 'design sprint N', 'design the UI', 'wireframe the screens', 'build the design system', 'design tokens', or 'how should this look'. Writes docs/design/; appends docs/spec/amendment-log.json; never edits the spine's requirements. Do NOT plan epics/sprints — that is /01-planner. Do NOT design the system architecture, ADRs, or the data model — that is /03-architect.
IncommensurableHubris/fullstack-director/.agents/skills/03-architect Skill
5★ repoRealize the system architecture — turn architecture-constraints + sprint REQs (+ 02's design contract) into a lean arc42/C4 system.md, MADR ADRs, and per-feature specs with gradeable Verification Contracts, all referencing REQs. Second skill to run Reconcile, first via a context-isolated subagent: challenges docs/spec/architecture-constraints.md through the amendment protocol, flagging realization-vs-constraint contradictions and fleshing out forced decisions via the tech-mandate flow (amend the constraint AND record a resolving ADR). Use when the user says 'architect the system', 'system design', 'write an ADR', or 'architect sprint N'. Writes docs/architecture/; appends docs/spec/amendment-log.json; amends architecture-constraints.md only via a gated Tier-2; never touches requirements. Sole ADR-ID allocator. Do NOT plan epics/sprints — that is /01-planner. Do NOT design the UX — that is /02-designer. Do NOT implement — that is /04-builder.
IncommensurableHubris/fullstack-director/.agents/skills/05-reviewer Skill
5★ repoVerify the sprint build in isolation - a reviewer spawned FRESH, seeded ONLY with 04's build-handoff + spec-slice paths, checked against the spine's Gherkin + the 02 contract; emits SHIP / FIX REQUIRED / BLOCK + a severity tally + attestation. READ-ONLY: writes only the QA report, attestation, and tests (RED per defect - 05 owns RED, 04 owns GREEN); never edits implementation. Re-derives judgment (EXECUTED/OBSERVED/INFERRED states); SHIP is unreachable while anything is INFERRED or a MUST/P0 REQ is uncovered. A non-amender but honest escalator (code/test to 04, spec to 03, declaration to 00/gate). Use when the user says 'review sprint N', 'verify the build', or 'QA'. Writes docs/quality/qa-report-sprint-NN.md + tests under src/**; never edits src/**, docs/spec/**, docs/architecture/**, or docs/design/**. Do NOT build or fix code - /04-builder. Do NOT refactor - /08-refactor. Do NOT audit security - /07-security. Do NOT plan sprints - /01-planner. Do NOT architect - /03-architect.
IncommensurableHubris/fullstack-director/.agents/skills/07-security Skill
5★ repoAudit the built system for vulnerabilities - a bounded parallel READ-ONLY OWASP panel + a sequential synthesizer emitting a severity-keyed PASS / REMEDIATE / BLOCK verdict. Spawns four blind read-only readers across a fixed OWASP partition, plus a conditional 5th for LLM/agentic parts; the synthesizer de-dupes, takes MAX severity, builds the matrix. PASS: zero Critical/High. REMEDIATE: a code-fixable High to /04-builder. BLOCK: a Critical, an arch-level High to /03-architect, or missing declaration to /00. A non-amender: classifies, escalates, appends no amendment-log row; never edits code. Use when the user says 'security audit', 'OWASP check', or 'pen test'. Writes docs/security/security-audit-sprint-NN.md (or -full.md); appends security-guardrails.md; never writes src/** or docs/{spec,architecture,design,quality}/**. Do NOT build or fix code - /04-builder. Do NOT re-architect - /03-architect. Do NOT verify - /05-reviewer. Do NOT deploy - /06-release. Do NOT refactor - /08-refactor.
IncommensurableHubris/fullstack-director/.agents/skills/08-refactor Skill
5★ repoImprove codebase structure WITHOUT changing behavior - a cross-cutting activity refactoring under a non-negotiable test-oracle safety net and reconciling realization docs LOCALLY. One spine wiring: appends an amendment row only for a DECLARATION contradiction (a mere realization drift is fixed LOCALLY, no amendment). Two modes (assess, sprint N). SEQUENTIAL - no subagents; Reconcile runs INLINE. Use when the user says 'refactor', 'tech debt', 'clean up the code', or 'refactor sprint N'. Writes src/** + docs/refactoring/{health-assessment,refactor-plan,refactor-report}-sprint-NN.md; reconciles docs/architecture/**, docs/design/**, quality-guardrails.md; appends docs/spec/amendment-log.json; amends architecture-constraints.md via gated Tier-2; requests ADR max+1. Do NOT fix bugs or verify - /05-reviewer. Do NOT fix vulnerabilities - /07-security. Do NOT build features - /04-builder. Do NOT re-architect - /03-architect. Do NOT tidy only sprint-modified files - /05's within-sprint pass.
VersoXBT/claude-initial-setup/skills/code-review/automated-review-setup Skill
4★ repoSet up automated code quality tools: ESLint, Prettier, pre-commit hooks, and CI linting. Activate whenever the user sets up a new project, asks about code formatting, configures linters, sets up Git hooks, or mentions Husky, lint-staged, CODEOWNERS, or pre-commit hooks. Also activate when discussing consistent code style enforcement.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/express-node/rest-api-node Skill
4★ repoRESTful API design conventions for Node.js including resource naming, pagination, filtering, sorting, HATEOAS links, versioning, and content negotiation. Use when the user is designing REST APIs, asking about pagination or filtering patterns, implementing API versioning, or building CRUD endpoints. Trigger on mentions of REST API design, API pagination, query parameters, HATEOAS, API versioning, or RESTful conventions.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/security/secret-management Skill
4★ repoManage secrets, API keys, and sensitive configuration securely. Activate whenever the user handles API keys, passwords, tokens, database credentials, .env files, CI/CD pipelines, or any configuration that contains sensitive values. Also activate when the user asks about secret rotation, vault integration, or gitignore setup.
VersoXBT/claude-initial-setup/skills/testing/test-architecture Skill
4★ repoTest organization, fixtures, factories (factory_boy/faker), test isolation, database cleanup, and test configuration. Use when the user is setting up a test suite, organizing test files, creating test fixtures, or dealing with test isolation issues.
irfad7/claude-power-skills/skills/codebase-insight Skill
4★ repoWhen the user wants to deeply understand a codebase, map its architecture, or build a persistent mental model for future sessions. Use when the user says "explain this codebase," "map the architecture," "codebase insight," "understand this repo," "what does this project do," "how does this work," "analyze the codebase," or when starting work on an unfamiliar project. Produces a persistent insight file that survives across sessions.
irfad7/claude-power-skills/skills/magic-docs Skill
4★ repoWhen the user wants to generate documentation from their codebase. Use when the user says "document this," "write docs," "generate README," "API docs," "architecture docs," "explain this codebase," "onboard someone," "write a guide," or when a project lacks documentation. Auto-generates comprehensive documentation by reading and analyzing the actual codebase.
rfxlamia/pocketto/skills/pocket-init Skill
4★ repoOnboards an existing (brownfield) project onto Pocket. Scans the codebase and writes a project memory file (CLAUDE.md or AGENTS.md), optionally enables Pocket Enterprise (mode init) and scaffolds GitHub issue/PR templates. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "enable enterprise mode".
hereinthehive/kickstart/.claude/skills/onboarding Skill
no license4★ repoSet up Claude Code for this project — interviews you, builds CLAUDE.md and settings, then has the curator subagent review everything before handing off
Maudeunfledged834/startup-founder-skills/skills/cicd-setup Skill
4★ repoWhen the user needs to set up or improve CI/CD pipelines — GitHub Actions, GitLab CI, deployment automation, or says "set up CI", "automate deployment", "add tests to pipeline", "fix my build".
Maudeunfledged834/startup-founder-skills/skills/onboarding-flow Skill
4★ repoWhen the user needs to design, improve, or audit a post-signup activation flow to get new users to their first value moment. Activate when activation is lagging, time-to-value feels excessive, or first sessions lack impact.