melodic-software
@melodic-software Organization
Public Skills
claude-code-plugins
by melodic-software
"Verify and configure the bugs plugin for this repository. check inspects both surfaces read-only, the rendered output_dir userConfig value, and the tracked .claude/bugs.md lane config across its cascade layers; apply writes or updates that tracked file and nothing else. Use when: 'set up bugs', 'configure bugs', 'bugs setup', 'where do bug reports land', the user wants --file reports committed alongside code, or '/bugs:scan' needs project lanes and a filing posture. Actions: check (read-only, default) apply (creates or updates the tracked lane config; output_dir still routes through Claude Code's own configuration prompt)."
claude-code-plugins
by melodic-software
"Audit markdown prose for AI-writing tells (slop): em dashes (zero-tolerance by default), emoji formatting, AI vocabulary, negative parallelisms, chatbot phrases, filler, stacked hedging, citation artifacts, model-era phrases ('that's the unlock', 'the part most people skip'), and the rest of the catalog (distilled from Wikipedia's Signs of AI writing plus an evolving model-era inventory), plus a judgment rubric for superficial analysis, vague attribution, promotional tone, metaphor jargon ('load-bearing', 'seam'), and mechanism-free claims. Use when: 'check for AI slop', 'de-slop this doc', 'unslop this', 'find AI tells', 'does this read AI-written', 'remove em dashes', or before publishing agent-written prose. Read-only by default; 'fix' as an explicit argument applies rewrites behind a semantic-diff guard and may be chained ('detect and rewrite'). Empty target audits the repo's tracked markdown, high-impact and high-velocity files first."
claude-code-plugins
by melodic-software
"Iteratively reduce coupling at any altitude (documents, code modules, applications, repositories): scan for change-transmitting dependencies typed against a coupling model, verify each finding, apply a budgeted batch of safe behavior-preserving reductions, and ledger structural candidates for design routing so repeated runs continue where the last stopped; after a value changes, find and classify every site stating it. Use when: 'reduce coupling', 'decouple', 'loosen coupling', 'too tightly coupled', 'high cohesion low coupling', 'break this dependency', 'dependency injection pass', 'externalize this config', 'connascence', 'coupling scan', 'these files always change together', 'stop copying between repos', 'I changed this value everywhere'. Skip when: reviewing a diff before merge (review tools), designing one chosen boundary (/architecture:improve), general structural tidyings with no coupling focus (/code-tidying:tidy), or a docs noise or dedup pass (docs-hygiene)."
Rotoscope
by melodic-software
"Copy a reference animation drawing by drawing: decode the video into its distinct drawings, trace each to vector paths, render them through the ink.js brush engine in headless Chromium, and measure every drawing against its source (ink/paper XOR against a codec-noise floor, SSIM, edge-band SSIM, paper color), then fit per-shot brush overrides and review 1:1 crops until every drawing passes. Use when: 'rotoscope this', 'trace this clip', 'copy this animation one to one', 'replicate this video exactly', 'match the reference frame by frame', 'measure the replica against the source'. Not for an original film or a style study without a reference clip."
Scrutinize, don't coast
by melodic-software
"Re-anchor adversarial self-scrutiny: stop coasting on recent output, re-examine whether it is sound (not merely confident) in a fresh-context pass blind to its reasoning, and remediate with the user. Use when: 'scrutinize don't coast', 'wait, stop', 'are you sure about this', 'second-guess this', 'poke holes in what you just did', \"you're steamrolling\", 'push back on yourself', with an optional focus, or at conversation start to set the posture."
Script the deterministic work
by melodic-software
"Re-anchor: deterministic sub-work (counts, diffs, transforms, arithmetic) gets a script; reason over its output. Use when: 'script the deterministic work', 'you should have scripted that', 'don't eyeball that', 'you counted that by hand', 'compute that, don't estimate', 'diff it with a tool', 'stop hand-tallying', 'run it instead of guessing', or at conversation start on count-, diff-, transform-heavy work. Fires on drift, not a work order ('script it', 'diff these files', 'count the routes')."
Recheck against upstream. Deep
by melodic-software
"Escalate upstream-conformance discipline: fan fresh-context subagents doc-by-doc over a whole subsystem, framework, or repo against CURRENT official upstream docs, and report a divergence ledger. Use when: 'recheck the whole subsystem against upstream', 'audit every surface against the docs', 'deep upstream conformance pass', 'check the entire framework config against upstream', 'we depend on a lot of upstream surfaces and they may have drifted'. For one recheck, use recheck-against-upstream."
Reuse or replace
by melodic-software
"Re-anchor anti-fragmentation: where an established way exists, new work REUSES it or openly REPLACES it (migrate, record why), never a SILENT second way. Use when: 'reuse or replace', 'we already have a way of doing this', 'don't invent a second way', 'keep it one way', 'follow the existing pattern or replace it', 'be consistent', 'you added a parallel way', 'this diverges from how we do it elsewhere', or at conversation start on work that extends an established codebase, structure, or process."
Hold my hand
by melodic-software
"Standing posture for multi-step work: only the current phase (exact steps, expected output, common failure, who acts, advancing reply), later ones as a 'Phase 1 of 8' count. Use when: 'hold my hand', 'walk me through this', 'one step at a time', 'one phase at a time', 'don't show me the next step yet', 'guide me through all of this', 'exact steps', 'hand-hold'. Not adhd:shape (shows every step), adhd:clarify (one message), wizard:generate (human-run script), session-flow:workflow (next stage)."
Sweep all disciplines
by melodic-software
"Batch this plugin's discipline correctors into ONE pass; needs fork subagents (subagent_type: fork), else (and at conversation start) it reports only a posture digest and audits nothing. Use when: 'sweep all disciplines', 'ground ourselves', 're-anchor everything', 'run the whole re-anchor bundle', 'posture batch', 'set our posture before we start', 'batch the correctors', or at conversation start to set posture across every discipline at once. For one discipline, invoke that corrector."
Follow our standards
by melodic-software
"Re-anchor to the organization's engineering standards, then audit the work in flight against them and correct violations with doc citations. Use when: 'follow our standards', 'follow the standards', 're-anchor to standards', 'does this match our conventions', 'audit against standards', 'you're drifting from our conventions', or at conversation start on a repo governed by shared conventions."
claude-code-plugins
by melodic-software
"Verify and configure the code-tidying plugin for this repository. check inspects the tracked .claude/tidy-lanes/<lane>.md project lanes and the optional .claude/code-tidying/exclusion-overrides.md read-only (presence, required sections, unreplaced placeholders, override glob shape and protection collisions, tracked-not-ignored) and reports the stored hard_exclusions posture; apply interviews the repo, infers which lane patterns fit, and scaffolds project lane files from the bundled templates. Use when: 'set up code-tidying', 'is code-tidying configured', 'configure tidy lanes', 'code-tidying setup', 'scaffold a tidy lane', 'override the tidy exclusions for this repo', or the tidy skill reports no project lanes. Re-runnable. Safe to invoke again to add or retune lanes."
claude-code-plugins
by melodic-software
"Verify the computer-use plugin's prerequisites and report the environment settings that end a screen-control session mid-run. Use when: 'set up computer use', 'is computer use working', 'why did my computer use session die', 'check computer use', 'computer use preflight', or before a long unattended screen-control run. Action: check (read-only, default). It probes the surface, the tool availability, and the idle/screensaver/sleep timeouts that no amount of Claude activity can hold off, then reports PASS/FAIL/INFO with one remediation line each. Check-only by contract: every prerequisite is external or a system setting this plugin must not write."
claude-code-plugins
by melodic-software
"Verify or configure the code-metrics plugin for this repository: check probes the interpreter, every configuration layer (user-global, team, local overlay, and the consumer's ecosystem files) for the YAML subset and the tracked-file guard, prints every reference with the layer that supplied it, and probes each collector adapter (a version, or missing with its install hint); apply writes the tracked .claude/code-metrics.yaml team layer per key, idempotently, never installing a tool and never editing .gitignore. Use when: 'set up code-metrics', 'configure code metrics', 'is code-metrics configured', 'which collectors are installed', 'set the cyclomatic reference', 'change the file length reference', 'code-metrics setup', or an audit skill reports a configuration layer it could not read."
claude-code-plugins
by melodic-software
"Diagnose unexpected behavior from Claude Code's built-in computer-use MCP server (desktop screen control). Use when: 'computer use', 'control my screen', 'screenshot is blurry', 'why is the screenshot low resolution', 'zoom in on the screen', 'screenshot capture failed', 'empty capture', 'clicks are landing in the wrong place', 'the screensaver killed the session', 'UIPI', 'app is not in the allowed applications', 'escape is not closing this menu', or before driving a native desktop app. Resolves a symptom to a cause instead of retrying: the fixed screenshot pixel budget and when zoom recovers detail, the capture and input failure ladders, and the per-OS quirks that make synthesized input behave unlike a human's. Not for: browser work (use Claude in Chrome), shell work (use Bash), or a service with its own MCP server."
claude-code-plugins
by melodic-software
"Record an architecture decision into the repository's existing ADR convention: discovers the ADR directory, numbering scheme, and record shape in use and writes one record that follows them; when no convention exists it names what it searched, offers common shapes, and writes nothing until the human chooses. Use when: 'record this decision', 'write an ADR', 'architecture decision record', 'capture this decision', 'document why we chose X', or after a design handoff or interview resolves a decision worth keeping. Skip when: the decision is easily reversed and unsurprising (no ADR earned), or the ask is supersession, an index, or status lifecycle beyond what the convention already defines."
Tighten your output
by melodic-software
"Re-anchor terseness discipline, say markdown in fewer words without semantic loss, write code in fewer lines when readability holds, then audit the work in flight for avoidable verbosity and tighten it. Use when: 'tighten your output', 'tighten this', 'too verbose', 'say it in fewer words', 'this is bloated', 'trim the code', 'simpler form', 'cut the wordiness', 'be more concise', or at conversation start on prose- or code-heavy work."
Write For Agents
by melodic-software
"Write agent-consumed markdown well at the moment of writing — CLAUDE.md or AGENTS.md content, .claude/rules files, agent-loaded reference/context docs, navigation-pointer lines, and doc-plus-pointer extractions. Use when: 'add this to CLAUDE.md', 'write a rule for X', 'write this up for the agent', 'add a pointer to the docs', 'move this section into its own doc', 'draft an AGENTS.md section', or any drafting or editing of a markdown file an agent will load. NOT for: creating or editing a SKILL.md (playbooks:skill-authoring and skill-quality:check own that), auditing existing docs (the docs-hygiene audit skills own that), or human-facing docs such as end-user READMEs and changelogs."
claude-code-plugins
by melodic-software
"Validate the education plugin's quiz, report-library, and teach workspace-root configuration and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up education', 'configure education', 'education setup', quiz offers feel wrong, report recall cannot find prior quizzes, or teach workspaces land somewhere unexpected. Actions: check (read-only verification, default and only action — this plugin's entire configuration is native userConfig, so there is nothing an apply could write)."
claude-code-plugins
by melodic-software
"Interactive multi-session learning coach for general topics or repo-grounded concepts; also a single-session domain primer (primer action). Use when: 'teach me', 'study session', 'help me learn', 'onboard me to', 'learn this codebase'. Coaches through the Knowledge-Skills-Wisdom progression with persistent per-topic learning state. Not for one-off inline questions (answer directly)."
claude-code-plugins
by melodic-software
"Read-only progressive-disclosure audit for agent-facing instruction markdown — grades every target against a three-tier load-cost model (always-loaded / invocation-loaded / on-demand) and classifies seven finding shapes in two lanes: split opportunities (oversize vs tier-calibrated Anthropic-prescribed caps, mixed-concerns, tier-mismatch — procedures, path-local, or sometimes-only content sitting in an always-loaded file) and disclosure-structure defects (blind-pointer lacking a when-to-read clause or read-vs-run intent, orphan-spoke, deep-nesting past one level, missing-toc on long references). Emits Tier 1/2/3 findings with per-shape treatment guidance; read-only, no edits applied. Use when: 'progressive disclosure', 'split this file', 'this file is too long', 'too much context', 'mixed concerns', 'hub and spoke', 'is my CLAUDE.md too big', 'audit context loading', 'what should always be loaded', or before splitting any instruction file — not for prose flavor (/docs-hygiene:compress), in-page noise (/docs-hygiene:audit-noise), whole-doc existence (/docs-hygiene:audit-derivability), or skill frontmatter QA (/skill-quality:check)."
claude-code-plugins
by melodic-software
"Generates weekly usage reports."
Disk hygiene
by melodic-software
"Audit 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 cleanup belongs to repo-hygiene, a product has its own prune/GC command, or the target is an OS-managed root."
claude-code-plugins
by melodic-software
"Compress (tighten, shorten, trim) markdown files by dropping flavor — filler, hedging, articles — while preserving all content (directives, qualifiers, thresholds, examples), with a mandatory semantic-diff subagent that reverts any SEMANTIC LOSS or AMBIGUITY. Use when: 'compress this doc', 'tighten markdown', 'cut prose', 'shorten without losing meaning', 'trim onboarding doc', or verbose prose in docs/, READMEs, rule bodies, skill bodies, or third-party pasted text — actions: default (snapshot → backend → semantic-diff subagent → revert-pass → markdownlint) and audit (read-only dry-run classifying SKIP/COMPRESS/UNCERTAIN per file); empty target + clean tree in an interactive session offers a confirmation-gated repo-wide run (audit-first interview with prescribed defaults) instead of the no-op; flags: --force (bypass <3% revert rule), --keep-snapshot; not for: session compaction (/compact), markdown noise classification (/audit-noise), code-comment trimming, or content relocation/SSOT consolidation (/extract-ssot)."