Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills › Authors › melodic-software

melodic-software

@melodic-software on GitHub →

167 Claude Code skills authored by melodic-software.

updated 2026-11-15 · showing 1–60 of 167 by quality score

Average Pro QualityScore: 77.9/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Verify a measurable-improvement claim against a baseline captured BEFORE the change — two metric families (`performance`: wall time, memory, allocations, throughput, latency;…
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…
Apply, track, tune, and remove the community DLSS 5 Neural Rendering mod (OptiScaler forks) in a PC game on Windows.
C4 system context of one software system from tracked configuration: operator-stated actors and external systems named by connection strings, base URLs, and broker namespaces,…
Escalate research discipline to a heavy verification fan-out over a TYPED FULL INVENTORY of the session's claims — assumptions, asserted facts, concrete specifics (paths,…
Find and stress-test rhymes with Pat Pattison's discipline — identity check, stability-tier walk, vowel triangle, song-world vocabulary, mosaic/multi-word rhyme, cliche scan.
Style pack from a rotoscoped clip: measure its traces and drawings into knob values and statistic bands, prove the bands against adversarial controls, and check new scenes against…
Film production from a brief and one or more style packs: boards for the user to approve, then a shot list, rendered frames, a delivered file, and a review against the pack.
C4 container diagram of one software system: deployables, the stores and brokers they bind in tracked configuration, and the edges their configured endpoints resolve to.
Run 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,…
Generate a consumer-owned adapter for a tracker this plugin does not bundle: interview for the provider's shape, probe the real instance, write the adapter and conformance binding…
Measure how much code is typed, per file and per lane, for a change, a path, or the tree: `type-coverage` for TypeScript, mypy's any-expressions report for Python.
Inspect and turn off Claude Code's auto memory — the notes Claude writes itself per repo under ~/.claude/projects/<project>/memory/.
C4 deployment view of committed infrastructure: which containers sit on which declared nodes, per environment, and what differs between two environments.
Write one interface animation in any stack after deciding whether it should move at all, then build it from the project's own motion tokens and the stack's current documentation,…
Audit locally-owned Claude Code instruction surfaces — user + project CLAUDE.md, .claude/rules, skill bodies, agent definitions, prompt-type hooks, output styles — for…
Maps each finding in one review findings file to the cheapest deterministic check that could catch it (editorconfig severity, analyzer rule, custom analyzer, Semgrep rule,…
Prove a change achieved its intended outcome: a mechanical build+test+lint prerequisite (delegated to /toolchain:check and /toolchain:lint, STOPs if broken), then outcome…
Surface the USER's unknown-unknowns before they work in unfamiliar territory — an unfamiliar codebase area OR an unfamiliar domain vocabulary — and coach a sharper prompt.
Take an in-flight retrospective checkpoint mid-session: spawn a subagent to analyze the session transcript so far (reusing retro's parser), classify each finding by category and…
Extract and synthesize online video courses into repo-applicable recommendations via browser automation (Playwright + claude-in-chrome), transcript extraction, frame analysis, and…
Draft a paste-ready `autoMode` classifier block by interviewing the user about what should and should not be auto-approved, each entry in the shape the classifier reads well and…
Audit and remediate skill-encapsulation violations — external citations reaching into private surfaces inside `.claude/skills/<X>/` beyond the slash invocation.
Visual explainer for a concept or codebase topic, one idea per diagram, grounded in the real artifact and written as a markdown record plus an interactive page (markdown only on…
Read-only dry run of /harness-ops:plugins sync: predicts the marketplace refreshes, updates, installs, enables and scope divergences sync or converge would act on, and issues none…
Pull request explainer: a markdown digest of one PR (why, before and after, a checked risk map, annotated hunks, an optional quiz) with an optional interactive view, or its risk…
User research plans and instruments for the app being built: picks the method, then writes the discussion guide, screener, usability test script, survey or inclusive-research…
Audit whether a documentation file earns its existence — could a fresh agent re-derive its conclusions by exploring the code, config, metadata, and structure itself? Read-only…
Pixel-art tilesets as the target engine's sheet: terrain, autotiles (RPG Maker MZ A1-A5 and B-E, blob-47, 16-tile corner), seamless tiles, and parallax layers.
Permission and autonomy friction audit for Claude Code sessions: denials, approval prompts, hook blocks, asks and hand-offs, traced to their cause and ending in one decision…
Sweep stale references after renames — the syntactic forms token-only grep misses (slash-tokens, paths, chain prose, numbered table rows, frontmatter chains and globs).
Emit the file-name gate into a consuming repository: a standalone bash checker plus its own test suite, with the casing rule, roots, and exemptions inlined from the resolved…
Actively maintain a consuming project's ubiquitous-language glossary as domain understanding changes: resolve ambiguous or overloaded terms, choose canonical language, record…
Attend the human-in-the-loop queue for loop-lane operation: ONE attention view merging worker-escalated items (human-gated role label + machine-marked escalation comment) with…
End-to-end live app verification — check prerequisites, start the app, drive UI/API flows, and capture evidence (screenshots, responses, logs); includes a non-UI smoke-test…
Migrate legacy .claude/commands/ to .claude/skills/ directory structure. Actions: discover, analyze, migrate, audit, validate, fix.
Author 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…
Read-only audit of `~/.claude` and `~/.claude.json`: the deep inventory of unmanaged files. Use when: 'what is in my ~/.claude', 'why is my Claude Code install so big', 'does…
Read-only hunt for dead and unused code across four labeled lanes (Knip for TS/JS, vulture for Python, gopls for Go, grep for shell, C# and files no lane owns), each candidate…
Scan lines and make structure serve meaning with Pat Pattison's methods — meter (scansion, Paradigms I/II/III, Pentad, Goldilocks, the 'into' rule, In Memoriam quatrain,…
Run the full explore workflow in an isolated forked subagent so verbose file reads and search output stay out of the main conversation; only a short summary returns, with findings…
Design navigation architecture including menus, breadcrumbs, and mega-menus. Generates structured navigation with accessibility.
Audit a repo's Claude Code automation landscape (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy, producing PASS/REJECT/CONDITIONAL…
Find posture guidance an instruction component lacks that the official prompting guide says its purpose needs: delegation, guardrails, stop rules, destructive-action confirmation.
Async message topology from committed C# publish, send, and consumer registrations. Orphan publishers and consumers are findings; one short name in two namespaces is two messages.
Ingest a single online documentation page (a docs-site URL) into a verified knowledge slice — fetch the original, inventory it into an INDEX, fan out per-section digest agents,…
Design media and DAM architecture including storage, processing, and delivery. Covers images, video, and documents.
C4 System Landscape plus application-portfolio table of a repository and the systems it references, with drift reported against a committed landscape record.
Background sweep of the whole AI-assisted development process (this session's work, git, hooks, the rest of the setup) for ways to go faster without losing accuracy, returning…
Delegate the task to a fresh background agent that continues it NOW — produce a save-point, then launch a detached claude --bg session seeded with the resume prompt.
Measure lines per file for the changed files (the default), explicit paths, or the whole tree (`--all`), every text file in every lane, each beside a configurable reference with…
Classify code comments for four residue shapes — history narration (\"used to… now…\"), plan/session references (\"Task 2 replaces the old…\", \"in this PR\"), conversational…
Drawing-by-drawing copy of a reference animation clip: decode it into distinct drawings, trace each to vector paths, render them through the ink.js brush engine, measure each…
Dringende bugfix of kleine config-wijziging snel live zetten. Fast-gate only, geen E2E. Alleen voor team-release.
Babysit your own open GitHub pull requests as a tiered fleet loop. The safe default discovers YOUR PRs under the current repo's owner, checks readiness, fixes clear branch-owned…
Generate raw sensory material and images with Pat Pattison's methods — object writing (sense-bound, 90-second timed dives, Rusty's-collar/Kami-kazi), metaphor (3 types, 8 recipes,…
Apply a file-name rename plan one file at a time, one human acceptance each: git mv, rewrite only the reference shapes each citing file's tier allows, rebuild generated records,…
Ranked menu of the skills that fit this moment, hiding nothing: Now, Next, Skipped upstream, Later, and a rotating Spotlight, drawn from the full installed catalog, not the…
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,…
Measure duplicated code as clone classes over a change, a path, or the tree, with every instance's file and line range, subtracting replication the repo declares sanctioned.
Search all 167 skills by melodic-software →