melodic-software
@melodic-software Organization
Public Skills
claude-code-plugins
by melodic-software
"Bring a machine's plugin fleet current on demand: marketplace refresh, update the plugins that actually load (including in-repo project/local-scope installs), install new catalog plugins per policy, detect scope divergence, and surface (never silently fix) drift, with a terse actionable report; refuses to downgrade by default. Actions: sync (default, mutating), audit (read-only dry run), converge (explicit scope consolidation). Use when: 'sync plugins', 'update my plugins', 'are my plugins current', 'check plugin drift', 'converge plugin scopes', or before relying on a plugin that might be stale."
Point, don't copy
by melodic-software
"Re-anchor pointer-over-copy discipline, then audit the work in flight for copied content, internal-name coupling, and closed capability lists, and correct by pointing at the living source. Use when: 'point don't copy', 'you copied that', 'don't duplicate the docs', 'cite instead of paste', 'link don't restate', 'you enumerated the tools', 'that couples to internal names', 'this will drift', or at conversation start on documentation work."
claude-code-plugins
by melodic-software
"Find posture guidance an instruction component lacks that the official prompting guide says its purpose needs: delegation, guardrails, stop rules, destructive-action confirmation. Report-only. Use when: 'posture audit', 'audit prompting postures', 'is my skill missing guardrails', 'missing delegation criteria', 'should this component confirm destructive actions', 'does my CLAUDE.md say when to stop', 'align my components with the prompting guide'. Text present and wrong: audit-instructions."
Stateless
by melodic-software
"Inspect and turn off Claude Code's auto memory, the notes Claude writes itself per repo under ~/.claude/projects/<project>/memory/. Use when: 'make Claude stateless', 'stop Claude remembering', 'disable auto memory', 'turn off auto-memory', 'purge/clear/delete auto memory', 'wipe what Claude saved about this repo', 'does Claude have saved memories'. Actions: status (default, memory + settings across all scopes), disable (autoMemoryEnabled:false + CLAUDE_CODE_DISABLE_AUTO_MEMORY), purge (destructive delete, confirm-gated). Auto-memory only, not CLAUDE.md/rules (use /claude-memory:audit) and not transcripts/history."
Mind your maxims
by melodic-software
"Re-anchor cooperative communication (Grice's maxims plus AI-augmented transparency): audit recent responses and artifacts for completeness (neither too little nor too much), relevance, clarity, and disclosed boundaries. Use when: 'mind your maxims', 'communication quality', 'answer what I asked', 'you buried the answer', 'you didn't answer the question', 'too vague', 'stay on topic', 'is this clear', 'grice', 'maxims', or at conversation start to set the communication posture."
claude-code-plugins
by melodic-software
"Produce a structured 5-field bug report (title, steps to reproduce, expected vs actual, severity with justification, suggested fix location) from an informal description. Read-only, never modifies code, never opens PRs, never files issues by default. Use when the user names a defect they observed ('there is a bug in <X>', 'expected X got Y', 'I am seeing <error> in <file>') or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug'). Skip when: deep investigation is needed, a fix is already in progress, or the request is a feature request (missing capability) rather than a defect. Emits Markdown to stdout by default; with --file, persists a report file and can hand off to a work-item tracker for filing."
claude-code-plugins
by melodic-software
"Draw one entity's state diagram from an explicit XState createMachine block or a Stateless Configure/Permit table. Ad hoc status assignments are refused. Use when: 'map states', 'state diagram', 'state machine', 'unreachable state', 'dead-end state'. Skip when: the question is a request trace (/architecture:map-flow) or message topology (/architecture:map-events)."
claude-code-plugins
by melodic-software
"Trace 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)."
claude-code-plugins
by melodic-software
"Chart a repository and the systems it references as a C4 System Landscape plus an application-portfolio table: extract typed reference edges and portfolio facts from tested scripts, commit the result as a landscape record, report drift against it, and render both artifacts into the declared architecture home. Use when: 'map our landscape', 'system landscape', 'what systems do we have', 'what does this repo depend on', 'application portfolio', 'who owns which repo', 'what runtimes are we on', 'chart our repositories', 'C4 context across repos', 'inventory our systems', 'has our landscape drifted'. Skip when: the question is module-level structure inside one codebase (shallow modules, seam placement) which is /architecture:improve, fleet cleanup (stale branches, orphaned worktrees) which is /repo-fleet-hygiene:audit, org settings which is /github:audit, or doc-versus-code drift inside one repository which is /codebase-health:audit."
claude-code-plugins
by melodic-software
"Chart one software system's C4 system context from tracked configuration: the focal system, operator-stated actors, and external systems named by connection strings, base URLs, authority endpoints, broker namespaces, and storage accounts. Credentials are redacted before anything is written. 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: the question is many repositories (/architecture:map-landscape) or module depth inside one codebase (/architecture:improve)."
claude-code-plugins
by melodic-software
"Chart one software system as a C4 container diagram: deployables identified by project output, host builder, Dockerfile, or process manifest, the stores and brokers they bind in committed configuration, and the modules contained in one deployable. Use when: 'map containers', 'container diagram', 'what actually runs', 'deployables and databases', 'modular monolith', 'which services bind to which broker'. Skip when: the question is which repositories exist (map-landscape), what is inside one deployable (map-components), or environment topology."
claude-code-plugins
by melodic-software
"Draw an entity-relationship diagram from committed schema declarations, with no database connection. Prisma models win over Entity Framework fluent mappings, which win over SQL migrations, 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."
claude-code-plugins
by melodic-software
"Chart 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)."
claude-code-plugins
by melodic-software
"Verify and converge the architecture plugin's consumer configuration: the convention-home binding, and the architecture topic doc declaring where landscape and portfolio artifacts land (architecture_dir) and which landscape dialect to emit (landscape_dialect). Use when: 'set up architecture', 'where should the landscape go', 'declare our architecture directory', 'map-landscape says there is no architecture home', 'switch the landscape dialect to structurizr', before a first /architecture:map-landscape run in a repository, or after changing the convention home. Actions: check (read-only), apply (writes the pointer region and topic doc, on explicit request)."
claude-code-plugins
by melodic-software
"Chart the modules inside one deployable as a C4 component view: group them by directory, namespace, or a declared layering, and draw a directed arrow for every internal build reference, each citing the declaration it came from. 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: the question is which repositories exist (map-landscape), which deployables exist (map-containers), or module-design friction (improve)."
claude-code-plugins
by melodic-software
"Cite 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."
Learn style
by melodic-software
"Learn a drawn animation style from a rotoscoped clip into a style pack: measure its traces and source drawings into knob values and statistic bands (edge straightness and roughness, solid black, boil of the frame and caption, the hold mix on 1s/2s/3s, palette), prove the bands against adversarial controls, then prove the pack by authoring a new scene with ink.js and checking its render against it. Use when: 'learn this style', 'make a style pack', 'extract the style from this clip', 'does my film match the style', 'check this scene against the woodcut pack', 'which statistics separate styles'. Needs a rotoscope work dir; not for copying a clip one to one."
Pick for the problem
by melodic-software
"Re-anchor choosing a tool, library, framework, language, or approach to fit the problem, not habit, incumbency, or preconception; re-derive the choice. Use when: 'pick for the problem', 'right tool for the job', 'which library should we use', 'what framework', 'should we build this or use X', 'is this the right approach', 'you defaulted to X', 'we always reach for X', 'evaluate the options', 'choose a dependency', or at conversation start on a build-vs-buy or technology-selection decision."
Do your research. Deep
by melodic-software
"Fan out verification over a typed full inventory of the session's claims (assumptions, facts, specifics, premises, recommendations) against primary sources at a configurable depth, with a per-item ledger. Use when: 'deep research pass', 'verify every claim', 'audit all our claims', 'fact-check everything', 'go make sure those are all right', 'we've made a lot of load-bearing claims', or the session's judgment is the suspected bias. For one fact-check ('fact-check that'), use do-your-research."
claude-code-plugins
by melodic-software
"Enforce self-describing code: delete zero-info comments, dissolve the rest into names, keep only terse load-bearing ones. Modes 'safe', 'aggressive', 'strip'. Use when: 'dissolve comments', 'remove comments', 'strip all comments', 'strip agent comments', 'too many comments', 'aggressive comment removal', 'make it self-documenting', 'make the code expressive', 'comments must earn their keep'. Skip residue (audit-comment-residue), tidyings (tidy), or batch-simplify."
claude-code-plugins
by melodic-software
"Audit tracked markdown for prose restating content an external source owns without a pointer or a stamped record, and convert copies into links, quoted citations, or four-part stamped records. Breadcrumb-first: citations in or near a passage are the first confirm targets; budgeted search runs only when no breadcrumb exists. Findings carry evidence-gated tiers (fingerprint-confirmed, source-fetched-similar, llm-suspected, not-found); only fingerprint-confirmed copies are fix-eligible. Also flags verification stamps past their expiry window. Use when: 'find copied content', 'is this copied from the docs', 'check our docs for copied text', 'replace copies with links', 'find stale verification stamps', 'audit provenance', 'where did this paragraph come from', or before publishing prose that restates an upstream page. Read-only by default; explicit 'fix' applies dispositions behind a semantic-diff guard and live pointer checks, and 'sweep' adds per-file closure. Empty target audits tracked markdown."
claude-code-plugins
by melodic-software
"Audit a codebase for drift between docs, config, code, and architecture. Verifies every factual claim against reality via parallel subagent fan-out, severity-rates findings and reports read-only; remediation is delegated to the implementation/verification lanes (--fix hands the findings to /implementation:implement then /verification:confirm). Use when: 'audit codebase', 'check for drift', 'verify docs', 'full audit'. Flags: --fix (hand findings to the remediation lanes after reporting), --docs-only, --code-only, --config-only, --arch-only."
claude-code-plugins
by melodic-software
"Verify or configure an ai-briefing profile and, only when explicitly requested, install the deterministic HTML/PDF/PPTX build toolchain. Use when: 'set up ai-briefing', 'configure ai-briefing', 'add an ai-briefing profile', 'is ai-briefing working', or 'ai-briefing setup'. Actions: check (read-only verification, default) apply (scaffold the profile) apply install-build-deps (also install the build toolchain). Idempotent, safe to re-run."
claude-code-plugins
by melodic-software
"Verify claude-config's readiness for this repository: the external CLI prerequisites its audit scripts need, jq (the JSON-parsing audit scripts) and curl (the plugin-drift check), and the tracked suppression record audit-pass reads at .claude/audit-pass.md, so the audit skills run instead of failing. Use when: 'set up claude-config', 'configure claude-config', 'is claude-config working', 'set up audit-pass suppressions', or an audit skill reported a missing prerequisite. Actions: check (read-only verification, default) apply (resolve what check found). Re-runnable and safe."