All authors

Claude Skills by zeljkoobrenovic
github.com/zeljkoobrenovic28 skills0 installs16 views
- Sokrates DecompositionsDesigns meaningful logical decompositions (components) for a Sokrates analysis and writes them as logicalDecompositions in _sokrates/config.json: folder depth, mixed depth for monorepos, build-system modules (Cargo, Maven, Gradle, npm workspaces, Bazel, Go, Python, .NET), CODEOWNERS ownership, layers, technology, several side by side, with a script that measures each candidate on the real tree. Use when the component view is one blob or hundreds of fragments, or components should match teams,...Votes: 0GitHub stars: 3
- Sokrates Features Of InterestDefines the features of interest (concerns) a Sokrates analysis tracks across the codebase by path or content regex: debt markers, deprecated code, feature flags, security-sensitive code, unsafe execution, error handling, concurrency, persistence, network, telemetry, configuration access, platform-specific code, integration libraries, domain terms, with a proposal script that measures each candidate with hits and sample lines. Use when Sokrates should track where X is or how much code touches...Votes: 0GitHub stars: 3
- Sokrates Landscape ConfigCreates and tunes a Sokrates landscape: _sokrates_landscape/config.json plus config-tags, config-teams and config-people.json, covering folder layout and discovery, repository filters and thresholds, virtual sub-landscapes, repository tags, contributor identity merging, bots, teams and embeds, with a checker that previews discovery and matching before updateLandscape runs. Use to set up or fix a landscape, group repositories, define teams, tag repositories, or find out why a repository or con...Votes: 0GitHub stars: 3
- Sokrates People ConfigBuilds and reviews the Sokrates config-people.json that merges contributor identities (several e-mails or user names of one person) from git history, for one repository or a whole landscape, with explicit confidence-rated rules and a review file of every merge and the candidates it did not apply. Use when contributor counts look inflated, one person appears under several addresses, to deduplicate contributors, fix bus-factor numbers, or set up people and teams before a landscape.Votes: 0GitHub stars: 3
- Sokrates Repo ConfigCreates and tunes the per-repository Sokrates configuration (_sokrates/config.json): source scope (srcRoot, extensions, ignore rules), classification into main/test/generated/build/other, components, concerns, goals and controls, history and contributor settings, limits and thresholds, with a preview script that simulates Sokrates' scoping on the real tree. Use to set up Sokrates for a repository, when files are missing or misclassified in a report, to exclude vendored or generated code, or t...Votes: 0GitHub stars: 3
- Sokrates Virtual LandscapesDefines virtual landscapes, the virtualLandscapes section of _sokrates_landscape/config.json that groups repositories into sub-landscapes by name patterns, from the user's own grouping (products, teams, org units) or from what the analyses reveal (naming conventions, folders, technology, activity, contributor domains, shared committers, tags), with nesting and a script that measures every candidate grouping. Use to split a large landscape into meaningful sub-landscapes or group repositories b...Votes: 0GitHub stars: 3
- Sokrates ImproveImproves source code where a Sokrates analysis says it matters and proves it with the same numbers: picks a target (a complex or long unit, a duplicated block, a churn-times-complexity hotspot, or an AI finding with a recommendation), makes one behaviour-preserving change on a branch, re-measures, and reports before/after; across a landscape it ranks targets of every repository together. Use to reduce complexity or duplication, refactor hotspots, fix the top findings, or pay down debt measura...Votes: 0GitHub stars: 3
- Architecture ScanInfers the implemented architecture: style and shape, component responsibilities, load-bearing boundaries and contracts, dependency direction and its violations, runtime communication, migrations in progress, and security boundaries (trust map, sandboxing, escape hatches). Use for how a codebase is structured, what depends on what, whether the architecture is eroding, where a feature should live, or to judge Sokrates' component decomposition.Votes: 0GitHub stars: 3
- Cicd ScanReconstructs the CI/CD process as an evidence-backed narrative: what triggers a build, how code is built and tested, the quality gates on merges, how releases are versioned and published, where artifacts go and how users get them, plus pipeline hygiene risks (unpinned actions, missing gates, secret exposure). Use for how a project is built, tested, released or deployed, "what happens when I push or tag", or a pipeline audit.Votes: 0GitHub stars: 3
- Configuration ScanReads how the software is configured: sources (config files, env vars, CLI flags, profiles, remote settings) and their precedence, the settings surface and defaults, how configuration reaches the code, how secrets are supplied and held, validation and failure on bad values, feature flags, runtime reload. Use for how an app is configured, config files, env vars, precedence, defaults, feature flags, where credentials come from, or a configuration review.Votes: 0GitHub stars: 3
- Domain Language ScanWrites down a codebase's domain language: a glossary with code-anchored definitions, which components own which concepts (bounded contexts), the concepts each capability rides on, and where the language drifts (one concept under two names, one name for two things). Use for domain concepts, a glossary, domain model, ubiquitous language or naming-consistency review. For features and entry points use functionality-scan.Votes: 0GitHub stars: 3
- Evolution ScanExplains how a codebase evolved from its git history: eras and what each was about, growth and origin of the code, the shift of activity between areas, who arrived and left, parts born, rewritten or abandoned, the work mix now, and the trajectory. Use for a project's history or timeline, momentum, stagnation, contributor turnover, "what changed last year", or the story behind Sokrates' churn and age numbers. Needs git-history.txt.Votes: 0GitHub stars: 3
- Full ScanOrchestrates the Sokrates AI scanners over one codebase: a basic scan (six descriptive scanners: what is this codebase), a deep dive (all evaluative scanners or one family: quality, runtime, security) or a full scan (all seventeen), in dependency order, validated, merged, diffed against earlier runs. Use for "scan this repo", a quick or full scan, an overview of an unfamiliar codebase, a whole-codebase audit, or a re-scan. Requires a _sokrates analysis.Votes: 0GitHub stars: 3
- Functionality ScanDescribes what the software actually does, reverse-engineered from the code: purpose and audience, feature inventory, entry points (commands, endpoints, screens, hooks), end-to-end workflows, managed data, integrations, hidden or dormant behaviour, and where the docs disagree with the code. Use for "what does this codebase do", a feature list, a product manual, a capability inventory, or a README-vs-code check.Votes: 0GitHub stars: 3
- Iac ScanReads a codebase's infrastructure as code: the IaC inventory and tooling (Terraform, Pulumi, CloudFormation, CDK, Kubernetes, Helm, Kustomize, Ansible, Compose, serverless), container and dev-environment definitions, declared resources and topology, environment variants, state and drift, and the hardening of what is declared (pinning, root, privileges, exposure, limits). Use for IaC, Terraform, Kubernetes, Dockerfiles, deployment topology, cloud resources in the repo, or an IaC review; report...Votes: 0GitHub stars: 3
- Landscape Synthesis ScanThe portfolio story over a whole Sokrates landscape's AI findings: where attention concentrates, which findings recur across repositories so one fix pattern resolves many, which repositories or scanners are uncovered, and what to do first across the estate. Use on a landscape (_sokrates_landscape/) whose repositories were scanned: risks across our repositories, what repeats, which repos need attention first. Needs findings in at least one repository.Votes: 0GitHub stars: 3
- Maintainability ScanGrades maintainability per sub-characteristic and component: modularity (change impact radius), reusability, analysability (can a newcomer find and understand the part to change), modifiability (complexity, size, duplication, temporal coupling, ownership, churn) and testability, rolled up from Sokrates' numbers and the other scanners' findings. Use for how maintainable a codebase is, technical-debt or maintainability assessments, whether code is easy to change, or to turn Sokrates' metrics in...Votes: 0GitHub stars: 3
- Network ScanMaps how a codebase talks over the network: what it listens on and connects to, protocols as used (HTTP, WebSocket, SSE, gRPC, MCP, raw sockets), connection management (pooling, keep-alive, reconnection, timeouts, TLS, proxies), endpoint configurability, behaviour offline, and the data that crosses the wire. Use for what a project connects to or listens on, protocols, proxies, TLS, timeouts, offline behaviour, what it sends where, or a connectivity review.Votes: 0GitHub stars: 3
- Observability ScanMaps how a codebase observes itself: logging practice and hygiene, metrics and what they measure, tracing and context propagation, error and crash reporting, health surfaces, and what monitoring can exist downstream and what stays dark. Use for logging, metrics, tracing, telemetry, monitoring or alerting questions, swallowed errors, what data leaves the machine, or an observability audit.Votes: 0GitHub stars: 3
- Performance ScanStatic performance review: the workload model (what scales with input, hot loops, data volumes), hot-path algorithms and data structures, I/O and memory behaviour, concurrency and contention, caching and recomputation, explicit limits, ranked into likely bottlenecks and the highest-leverage optimizations. Use for why a project is slow, bottlenecks, what scales badly, memory, parallelism, caching, or a performance or efficiency review.Votes: 0GitHub stars: 3
- Reliability ScanMaps how a codebase behaves when things go wrong: the error model, failure handling on the paths that matter, isolation and blast radius, recovery (retries, backoff, timeouts, circuit breakers, idempotency), degradation and offline modes, resource cleanup, crash safety and orderly shutdown. Use for error handling, resilience, robustness, fault tolerance, "what happens when X fails", retries and timeouts, or a reliability review or hardening plan.Votes: 0GitHub stars: 3
- Risk Synthesis ScanTurns Sokrates' quantitative risk signals into explained, actionable findings: what each hotspot file does, why its metrics (complexity, churn, single ownership, change coupling) make it risky, and what to do. Use for where the risks are, which files to refactor first, debt hotspots, bus factor or knowledge risk, "what should we worry about", or to have Sokrates results explained and prioritized. Requires a _sokrates analysis.Votes: 0GitHub stars: 3
- Security ScanSecurity review in one pass, design first and code second: identity, authentication and permission design, secrets by design and in the tree, boundary validation and injection (command, SQL, path, template), crypto and randomness, unsafe and dynamic code, trust in third-party code (plugins, models, dependencies), with a posture stating what was swept clean and what was not covered. Use for security reviews or audits, auth or permission design, secrets, injection, crypto, unsafe code, plugin t...Votes: 0GitHub stars: 3
- Sokrates Scan CoreShared foundation of every Sokrates AI scanner: the findings format with file/line evidence, the evidence rules, how to read a _sokrates analysis, and the validate / render / merge / diff / re-check / summarize scripts. Load when running any *-scan skill, writing a new scanner, or validating, rendering, diffing or summarizing findings files.Votes: 0GitHub stars: 3
- Storage ScanMaps how a codebase works with persistent data: what lives in files, databases, caches and object stores and in which formats, how it is accessed (ORM vs raw SQL, transactions, locking, streaming), how schemas and formats are versioned and migrated, integrity and corruption handling, and the data lifecycle (retention, cleanup, backup, export). Use for where a project stores its data, migrations, file formats, data integrity, retention, or a storage review.Votes: 0GitHub stars: 3
- Tech Stack ScanDeep technology-stack inventory: languages, frameworks, libraries, build tooling, CI/CD, infrastructure, databases, external services and protocols, each with file/line evidence, written as validated findings. Use for what technologies a codebase uses, a tech inventory or radar input, a dependency overview, or when another analysis needs a reliable picture of the stack first.Votes: 0GitHub stars: 3
- Testing ScanReads the tests as a system: the test model as implemented (layers, frameworks, locations, test-to-main ratio per component), the coverage map inferred from what tests reference, test quality (assertions, mocking, determinism, flakiness, skips, duplication), the infrastructure and how to run them, and the gaps on load-bearing paths. Use for how well a project is tested, what the tests cover, flaky or untrustworthy tests, where coverage is missing, or a test strategy review.Votes: 0GitHub stars: 3
- SokratesStart here for anything about Sokrates (sokrates.dev), the source-code analysis tool: analyze a repository, understand a codebase, set up or improve the Sokrates config, scan for risks, build a landscape of many repositories, improve code where it matters. Finds out where the user is and routes to the right sokrates-skill, running Sokrates when that is the next step.Votes: 0GitHub stars: 3