All authors
Claude Skills by melodic-software
github.com/melodic-software364 skills1 installs570 views
- Map ComponentsChart the modules inside one deployable as a C4 component view, one directed arrow per internal build reference, each citing its declaration. Use when: 'map components', 'component diagram', 'what is inside this service', 'module dependencies', 'which way do the arrows point', 'C4 component view', 'layering of this deployable'. Skip when: which repositories exist (map-landscape), which deployables exist (map-containers), or module-design friction (improve).Votes: 0GitHub stars: 20
- Map ContainersChart one software system as a C4 container diagram: deployables, the stores and brokers they bind in tracked configuration, and the edges their configured endpoints resolve to. Use when: 'map containers', 'container diagram', 'what actually runs', 'deployables and databases', 'modular monolith', 'which services bind to which broker'. Skip when: which repositories exist (map-landscape), what is inside one deployable (map-components), or environment topology.Votes: 0GitHub stars: 20
- Map ContextChart one software system's C4 system context from tracked configuration: actors you state and external systems named by connection strings, base URLs, and broker namespaces, credentials redacted. Use when: 'map context', 'system context', 'C4 context', 'context diagram', 'what does this system talk to', 'who uses this system', 'external systems from config'. Skip when: many repositories (/architecture:map-landscape) or module depth (/architecture:improve).Votes: 0GitHub stars: 20
- Map DataDraw an entity-relationship diagram from committed schema declarations, with no database connection. Prisma models win over a stated subset of Entity Framework fluent mappings, which win over SQL migrations read from a stated subset of statements, and a disagreement is reported. Use when: 'map data', 'ERD', 'entity relationship', 'schema diagram', 'cardinality from mappings', 'which tables relate'. Skip when: the question is deployment topology, runtime state, or data volume.Votes: 0GitHub stars: 20
- Map DependenciesCite which project depends on which from build manifests, with the file and declaration on every edge. Use when: 'map dependencies', 'project reference graph', 'dependency graph', 'what references what', 'internal dependencies', 'package references', 'which projects depend on which'. Skip when: the question is which repositories exist, which is /architecture:map-landscape, shallow modules, which is /architecture:improve, or source imports and call graphs.Votes: 0GitHub stars: 20
- Map DeploymentChart committed infrastructure as a C4 deployment view: which containers sit on which declared nodes, per environment, and what differs between two environments. Use when: 'map deployment', 'deployment diagram', 'what is different in production', 'IaC topology', 'where does this container run'. Skip when: the question is a live cloud inventory, cost, or runtime health.Votes: 0GitHub stars: 20
- Map EventsChart async message topology from committed C# publish, send, and consumer registrations. Orphan publishers and consumers are findings. Same short name in two namespaces is two messages. Use when: 'map events', 'who publishes this message', 'message topology', 'orphan consumer', 'publish subscribe'. Skip when: the question is an in-process call trace (map-flow) or broker hosts and replicas (a deployment view).Votes: 0GitHub stars: 20
- Map FlowTrace one C# entry point into a mermaid sequence diagram. Each hop cites a tracked call site. An interface, service-locator, or reflection hop stays unresolved, and Publish or Send is a hand-off to map-events. Use when: 'map flow', 'sequence diagram', 'trace this request', 'walk me through what happens', 'dynamic diagram from this endpoint'. Skip when: the question is who publishes which message (/architecture:map-events) or which repositories exist (/architecture:map-landscape).Votes: 0GitHub stars: 20
- AuditAudit tracked markdown for prose restating content an external source owns without a pointer or a stamped record, and convert copies into links, citations, or stamped pointer records. Breadcrumb-first, then budgeted search. Two rubrics: copy, and restated fact (a default or limit, any wording). Evidence-gated tiers; only fingerprint-confirmed copies are fix-eligible. Only a unanimous restated fact that survives refutation relays, report-only. Also flags verification stamps past their expiry w...Votes: 0GitHub stars: 20
- SetupSet up and maintain this repository's attribution audit configuration: `.claude/attribution.json` across the config cascade's three layers. Manages the categorical exclusions (including the eval-fixture tree, which is a config entry by design and never a rule in a script), the per-candidate and corpus fetch budgets, the separation-rule constants, the stamp expiry window, the accuracy dials for nomination passes and judge sampling, and the fix-eligibility gates. Enables the off-by-default trig...Votes: 0GitHub stars: 20
- CheckRead-only check that biome and node resolve for the biome-format hook. Use when a hook notice says biome or node is missing, or before assuming Biome formatting ran. Does not install.Votes: 0GitHub stars: 20
- PrerequisitesRead-only report of external tools the enabled plugin fleet declares, and which of them are missing. Use when a hook says a formatter or CLI is missing, or when asking whether this machine has what the enabled plugins need. Never installs.Votes: 0GitHub stars: 20
- ReportThe return contract every agent a plugin skill dispatches reports in: problems first, one fenced block, every claim graded off disk by the parent, preloaded into the agent definition and dispatched only.Votes: 0GitHub stars: 20
- CheckRead-only check that goimports and node resolve for the go-format hook. Use when a hook notice says goimports or node is missing, or before assuming Go formatting ran. Does not install.Votes: 0GitHub stars: 20
- CheckRead-only check that markdownlint-cli2 and node resolve for the markdown-format hook. Use when a hook notice says markdownlint-cli2 or node is missing, or before assuming Markdown formatting ran. Does not install.Votes: 0GitHub stars: 20
- Audit PostureAudit the MCP servers configured in Claude Code for supply-chain posture, meaning whether each one is safe to run. Use when: 'is it safe to run my MCP servers', 'mcp supply chain', 'floating MCP versions', 'npx @latest MCP', 'MCP server inventory', 'mcp posture', 'unpinned MCP server', 'which MCP servers run on my host'. Reads user, local, project, managed, and passed-in config statically through a bundled inventory script and returns a dated, diffable inventory (scope, transport, launcher, p...Votes: 0GitHub stars: 20
- AnimateAnimate pixel-art sprites: idle, walk, run, attack, jump, hurt, death and custom cycles in 1, 4 or 8 directions, exported as sprite sheets laid out for the target engine (RPG Maker MZ, Godot, PICO-8, plain strips) with Aseprite-shaped frame data and looping GIF previews, with no external tools. The model authors pose-parameterised frames, the bundled stdlib renderer writes sheet, frame data and GIFs, and a render-review loop fixes timing and poses. Use when: 'animate this sprite', 'walk cycle...Votes: 0GitHub stars: 20
- SceneBuild animated pixel-art scenes as one self-contained HTML file (Canvas 2D, no libraries, no external assets): cutscenes, title screens, dialogue beats, ambient loops, short pixel films, card reveals, and backgrounds with parallax, particles, lighting by palette steps, bitmap text and dither transitions. Reuses sprite specs from /pixel-art:sprite and /pixel-art:animate, takes an optional audio file, and reviews itself through browser screenshots when a browser tool is present. Use when: 'pixe...Votes: 0GitHub stars: 20
- SpriteCreate static pixel-art sprites (characters, items, icons, portraits, faces, battlers, props) as engine-ready PNG sheets with no external tools: the model authors a palette-locked spec or a procedural generator, the bundled stdlib renderer writes the files, and a render-review loop iterates until the sprite reads. Use when: 'make a sprite', 'pixel art of X', 'draw a 32x32 icon', 'character portrait', 'RPG Maker face', 'item icons', 'pixel-art character design'. Not for movement cycles (use /p...Votes: 0GitHub stars: 20
- TilesetCreate pixel-art tilesets with no external tools: terrain, autotiles (RPG Maker MZ A1-A5 and B-E, blob-47, 16-tile corner sets), seamless backgrounds, and parallax layers, laid out as the target engine's sheet. The model authors a palette-locked spec or a procedural generator, the bundled stdlib renderer writes the sheet, and a render-review loop iterates until the seams read. Use when: 'tileset', 'autotile', 'terrain tiles', 'blob tileset', 'parallax background', 'RPG Maker tileset', 'seamle...Votes: 0GitHub stars: 20
- UiCreate pixel-art UI with no external tools: window skins (RPG Maker MZ Window.png and generic 9-slice frames), icon grids (MZ IconSet.png), HUD elements, and bitmap fonts (a glyph grid or a BMFont .fnt beside it). The model authors a palette-locked spec, the bundled stdlib renderer writes the sheet, and a render-review loop iterates until the skin reads. Use when: 'window skin', '9-slice frame', 'icon set', 'HUD', 'bitmap font', 'Window.png', 'IconSet'. Not for a single item icon or character...Votes: 0GitHub stars: 20
- VfxCreate pixel-art effects with no external tools: particles, hit sparks, spell and explosion cycles, as sprite-sheet animations. RPG Maker targets the MV-style img/animations cell sheet. The model authors a palette-locked spec, the bundled stdlib renderer writes the sheet and a GIF, and a render-review loop iterates until the motion reads. Use when: 'hit spark', 'pixel effect', 'spell animation', 'explosion', 'particle sheet', 'MZ animation cells'. Not for a character walk cycle (use /pixel-ar...Votes: 0GitHub stars: 20
- SyncMove every canonical checkout in a fleet onto the remote default branch and fast-forward it. Divergent dirty work is parked in a linked worktree. Bare invocation prints a dry-run plan. Mutation requires --apply and one confirmation. Use when: 'sync the fleet', 'update all repos to main', 'fast-forward canonical checkouts', 'park my dirty branches and pull'.Votes: 0GitHub stars: 20
- MusicRender a chiptune loop from MML text to WAV with pulse, triangle, and noise presets, standard library only. Use when: 'chiptune', '8-bit music', 'retro game loop', 'MML to wav'. Not for a one-shot effect (use /retro-audio:sfx) or lyrics.Votes: 0GitHub stars: 20
- SfxRender a retro sound effect to WAV from an sfxr-style parameter set, standard library only. Use when: 'sound effect', '8-bit sfx', 'pickup sound', 'jump sound', 'explosion sfx', 'chiptune effect'. Not for a song or loop (use /retro-audio:music) or a picture.Votes: 0GitHub stars: 20
- Pr ExplainerRenamed to /review:explain-change. This stub stays for one release and only points there. Use when: '/review:pr-explainer' is typed by name.Votes: 0GitHub stars: 20
- UnattendedAuthor an unattended PowerShell script for work that is fully scriptable but not agent-launchable: the human is only the privilege or policy boundary (UAC, an elevated shell, or a run the repo reserves for the operator). The agent authors the script and never launches the real run. The human launches it once. The script writes cutover.result/1 JSON the agent reads back. Use when: 'run this elevated', 'I have to launch it', 'UAC', 'operator must apply', 'unattended cutover', 'scriptable but I ...Votes: 0GitHub stars: 20
- Plugin EvalGuided practice around the `claude plugin eval` CLI, which runs and scores a plugin's eval suite: preflight (version floor, sandbox backend, target type), static validation with no model call, a cost estimate under the configured ceiling, the run, and the with-versus-without delta read correctly. Use when: 'run my plugin evals', 'plugin eval', 'evaluate this plugin', 'eval my skill', 'does my skill actually fire', 'what is the delta', 'read my eval results', 'compare two eval runs', 'did my c...Votes: 0GitHub stars: 17
- ValidateStatically validate a `claude plugin eval` suite (`prompt.md`, `case.yaml`, `graders/*.md`) before any run spends money. A standard-library Python script reports FAIL for what the binary rejects at load (unknown frontmatter key, unknown grader option, no grader, duplicate grader name, non-positive weight, out-of-range runs / max_turns / timeout_seconds, an env key outside EVAL_[A-Z0-9_]*, an unsupported schema_version major) and WARN for the documented authoring mistakes (target: files, inlin...Votes: 0GitHub stars: 17
- Dlss5Apply, track, tune, and remove the community DLSS 5 Neural Rendering mod (OptiScaler forks) in a PC game on Windows. Action router: assess (eligibility, launcher, anti-cheat signals), apply (snapshot, then install; anti-cheat risk only with a typed acknowledgement), remove (byte-exact uninstall from the manifest), status (drift and stale-build report against the manifest), reset (back to stock ini plus preset, after confirmation), tune (in-game overlay guidance), capture (save overlay tuning ...Votes: 0GitHub stars: 17
- SetupVerify and provision the gaming plugin's DLSS 5 mod prerequisites on Windows. check (read-only): pwsh, NVIDIA GPU and driver, data directory, runtime DLL, installed games per launcher (Steam, Epic, EA app, Battle.net, GOG, Ubisoft Connect, Xbox app), provisioned fork builds, orphaned state. apply: create the data directory, seed the ledger, place the runtime DLL from a configured path, an installed DLSS 5 title, or the configured runtime source, and download the pinned fork builds. Use when: ...Votes: 0GitHub stars: 17
- MigrateMove instruction content to AGENTS.md as the one content home, keeping a one-line CLAUDE.md shim while a shim is what makes it load. Plans first; every write is operator-gated. Use when: 'migrate to AGENTS.md', 'plan the AGENTS.md migration', 'move CLAUDE.md content to AGENTS.md', 'add the AGENTS.md shim', 'our CLAUDE.md should be one line', 'share instructions with Codex and Cursor', 'can we drop the CLAUDE.md shims yet'. Not the placement sweep (audit) or applying findings (realign).Votes: 0GitHub stars: 17
- ProtectLock in a verified performance win: ratchet its counter in CI with a checked-in ceiling, so a regression fails the build and a lower count proposes a lower ceiling by PR. Proposes files; a human approves and merges. Use when: 'protect this win', 'ratchet this counter', 'stop this regressing', 'add a performance guardrail to CI'. Runs once after /performance:verify reports MET on a counter. Skip when the result is a duration only, or NOT MET.Votes: 0GitHub stars: 17
- Repo SweepRun a playbook of hygiene skills through one repository per sweep: one branch, one draft PR whose body holds the step checklist, one commit per step, /clear between steps, resumable from any session or machine. Actions: plan (recommend run, rerun, or not-applicable per catalog entry, open the selection page, open the draft PR), next (run the first unticked step), review (file skill defects found in the last step). Use when: 'sweep this repo', 'run the hygiene playbook', 'repo sweep', 'next sw...Votes: 0GitHub stars: 17
- Output CustomizationCentral authority for Claude Code output styles. Covers built-in output styles (Default, Explanatory, Learning), custom output styles, output style frontmatter (name, description, keep-coding-instructions), /output-style command, style switching, output style creation and customization, output style comparisons (vs CLAUDE.md, vs agents, vs slash commands), and output style settings. Assists with selecting appropriate output styles, creating custom styles, configuring output behavior, and unde...Votes: 0GitHub stars: 13
- Api Portal DesignAPI documentation and developer portal designVotes: 0GitHub stars: 13
- SetupVerify the actionlint-check hook's runtime prerequisites and configuration for this repository. Use when: 'set up actionlint', 'configure actionlint', 'is actionlint working', workflow lint silently isn't happening, or the hook reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found). Re-runnable and safe.Votes: 0GitHub stars: 13
- Feedback ConversationsNavigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.Votes: 0GitHub stars: 13
- Ml System DesignEnd-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.Votes: 0GitHub stars: 13
- Agent Expert CreationCreate specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.Votes: 0GitHub stars: 13
- Agentic Layer AssessmentAssess agentic layer maturity using the 12-grade classification system (Class 1-3). Use when evaluating codebase readiness, identifying next upgrade steps, or tracking progress toward the Codebase Singularity.Votes: 0GitHub stars: 13
- Agentic Layer AuditAudit codebase for agentic layer coverage and identify gaps. Use when assessing agentic layer maturity, identifying investment opportunities, or evaluating primitive coverage.Votes: 0GitHub stars: 13
- Conditional Docs SetupSet up conditional documentation loading to prevent context pollution. Use when organizing project docs, implementing progressive disclosure, or reducing CLAUDE.md token consumption with on-demand loading.Votes: 0GitHub stars: 13
- Context AuditAudit current context composition and identify optimization opportunities. Use when context window is overloaded, agents are underperforming, or applying the R&D framework to optimize token usage.Votes: 0GitHub stars: 13
- Expertise File DesignDesign YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, defining expertise schema, or structuring knowledge for Act-Learn-Reuse workflows.Votes: 0GitHub stars: 13
- Hook Event ArchitectureDesign hook-based event systems for ADW observability. Use when implementing real-time event broadcasting, creating hook pipelines, or building agent activity monitoring.Votes: 0GitHub stars: 13
- Reduce Delegate FrameworkApply R&D framework to optimize prompts and context. Use when optimizing context window usage, reducing prompt size, delegating to specialized agents, or applying systematic context management.Votes: 0GitHub stars: 13
- CleanAudit an arbitrary directory tree for orphaned, temporary, stale-lock, failed-write, partial-download, and empty leftover artifacts; classify evidence into confidence tiers; and optionally remove exact validated paths after explicit per-tier approval. Read-only by default and manual-only. Use when: 'audit this directory', 'find orphaned files', 'what junk can I clean up', 'reclaim disk space', 'find temp or lock leftovers', 'clean up my home directory'. Skip when: repository cache/build clean...Votes: 0GitHub stars: 13
- Adr- Status: accepted - Date: 2026-08-23Votes: 0GitHub stars: 13
- ClarifyFaithfully clarify a dense, decision-heavy message so the reader can act on it. Chunk it into one-decision-at-a-time, define the session's own jargon, and surface exactly what the reader must decide, with operative terms quoted verbatim and no loss of precision. Decision-dense content gets an HTML decision table with numbered rows. Use when: 'make this clear', 'clarify this', 'help me digest this', 'break this down', 'I can't parse this', 'what am I actually deciding here', 'this is a wall of...Votes: 0GitHub stars: 13