[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MPYWZSBKCKCEZVZKV5PYV":3,"skill-same:01M77MPYWZSBKCKCEZVZKV5PYV":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M77MPYWZSBKCKCEZVZKV5PYV","object-writing",null,"Raw sensory material with Pat Pattison's methods: sense-bound object writing (timed dives, the pivot chain, the seven-channel sense inventory, Rusty's-collar\u002FKami-kazi), an agent that performs the write itself, cliche taxonomy and redemption, and point of view (camera distance, pronoun consistency). Use when: 'object writing', 'you do the object writing', 'make this less abstract', 'show don't tell', '90-second writing prompt', 'this line sounds cliched', 'who is speaking in this lyric'. For metaphor use \u002Fsongwriting:metaphor; for rhyme use \u002Fsongwriting:rhyme; for daily curriculum use \u002Fsongwriting:practice.","melodic-software\u002Fclaude-code-plugins","melodic-software","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58273638?v=4","01M77JVQTXNGKCE4MDFY2BC936","Melodic Software","01M77JVQVN9QDWKAH6W03ANP76",30,"MIT","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsongwriting\u002Fskills\u002Fobject-writing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Raw sensory material with Pat Pattison's methods: sense-bound object writing (timed dives, the pivot chain, the seven-channel sense inventory, Rusty's-collar\u002FKami-kazi), an agent that performs the write itself, cliche taxonomy and redemption, and point of view (camera distance, pronoun consistency). Use when: 'object writing', 'you do the object writing', 'make this less abstract', 'show don't tell', '90-second writing prompt', 'this line sounds cliched', 'who is speaking in this lyric'. For metaphor use \u002Fsongwriting:metaphor; for rhyme use \u002Fsongwriting:rhyme; for daily curriculum use \u002Fsongwriting:practice.\"\nargument-hint: \"[object-writing|generate|cliche|pov|worksheet] [args]\"\nuser-invocable: true\ndisable-model-invocation: false\n---\n\n**Arguments.** `[object-writing|generate|cliche|pov|worksheet] [args]`. e.g.,\n\u002Fsongwriting:object-writing, \u002Fsongwriting:object-writing generate rain. Full actions in body.\n\n## Mandatory pre-flight. Response Filter\n\nBefore emitting any image, metaphor, sensory prompt, or rewrite, run **§7 Image filter (object\nwriting + metaphor)** of [response-filter](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fresponse-filter.md)\n(add **§2 Line-writing** when producing lines). NAME each box's pass \u002F fail \u002F skip-with-reason\n(aloud or in reasoning); correct before emission. Skips are valid; silent skips are not. Abstract\ntelling and cliche imagery are the defaults this filter catches.\n\nThis skill is the source of concrete detail the other skills shape. Metaphor is its own skill\n(`\u002Fsongwriting:metaphor`); this skill feeds it.\n\nMethod content is Pat Pattison's, under the plugin-root `..\u002F..\u002Fcontext\u002Fpat-pattison\u002F`; a future\nauthor's method plugs in at `context\u002F\u003Cauthor>\u002F` without changing this skill, the author seam per\nthe plugin-root `..\u002F..\u002FREADME.md` \"Method content and the author seam\".\n\n## Action Router\n\n`\u002Fsongwriting:object-writing \u003Caction> [args]`. Parse `$ARGUMENTS`: first token = action when it\nmatches a listed action, remainder = args; otherwise treat all of `$ARGUMENTS` as payload for the\ndefault. No action → issue one usable timed object-writing prompt immediately (do not assign a\ncurriculum).\n\n| Action | Use when the user asks for | Load |\n| --- | --- | --- |\n| `object-writing` (default) | sensory writing, showing instead of telling, raw material | [object-writing](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fobject-writing.md), [templates\u002Fobject-writing-prompt](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Ftemplates\u002Fobject-writing-prompt.md) |\n| `generate` | **YOU** do the object writing. \"you write it\", \"do the object writing\", \"I don't want to write it\", or any request for raw sensory material the writer is not going to produce | dispatch the `object-writer` agent. See below |\n| `cliche` | cliche phrase, cliche image, stale metaphor, cliche rhyme | [cliche](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fcliche.md), [worksheets](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fworksheets.md), [metaphor](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fmetaphor.md) |\n| `pov` | first\u002Fsecond\u002Fthird person, direct address, dialogue, pronoun consistency, camera distance | [point-of-view](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fpoint-of-view.md) |\n| `worksheet` | broader sense-bound worksheets (not rhyme worksheets) | [worksheets](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fworksheets.md) |\n\n## Handlers\n\n- If the user asks for a prompt, generate one usable timed exercise immediately (default\n  90 seconds). Do not assign the full curriculum unless asked; that is `\u002Fsongwriting:practice`.\n- Keep object writing sense-bound and personal; its job is to reveal specific, sensory detail, not\n  to produce finished lines.\n- A metaphor request routes to `\u002Fsongwriting:metaphor`, invoked via the Skill tool. Hand over the\n  material mined here as its input; do not generate the metaphor here.\n\n## `generate`. Dispatch, never write it inline\n\n**Who writes matters more than what is loaded.** Reading this skill's files and then writing a dive\nin the main thread reliably produces a static scene description, because the discipline was read\nrather than carried. Dispatch the `object-writer` agent, whose system prompt IS the discipline.\n\nDispatch rules:\n\n1. **One agent per seed**, all in a single message so they run concurrently. Two agents on the same\n   seed is a valid and useful play: same board, different dives.\n2. **Give each agent nothing but the seed, the timer, the category, and its own output path.** Not\n   the song, not the title, not the draft, not the diagnosis, not the other agents' seeds. The\n   isolation is the mechanism; briefing an agent on the song destroys the divergence it exists to\n   produce. This is a hard boundary, not a default.\n3. **Each agent writes to its own file** under the song's `ideation\u002F` (per\n   [artifact-persistence](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fartifact-persistence.md)). It returns\n   only three things: the path, the seven channels each graded `strong` \u002F `thin` \u002F `absent`, and\n   one sentence on where the pivot chain landed. The write itself and the phrase-quoting sense\n   inventory live in the file; never ask an agent to return either in a message.\n4. **Grade coverage on return**, then mine. Read each file, honor thin-channel reports rather than\n   overruling them, and pull individual images forward. Mining stays here because you hold the song\n   context the writers deliberately lack.\n5. **For rounds:** name what made the strongest write of a round work, then carry that as the\n   standard into the next round's dispatch. The bar escalates; rounds are not independent repeats.\n6. **Set the model explicitly on every agent call; never let the fleet inherit the session's.** The\n   `object-writer` agent's frontmatter pins `opus` as a fail-safe, so a call that forgets the model\n   does not simply inherit the session's model, a tier picked for the orchestrator's work, not the\n   writers'. Whether the pin can still resolve to the session's own model is the Choose a model\n   pointer below's to state; check it before relying on the pin.\n   The pin is not the fleet tier: every call still names the fleet default below. Stop to ask\n   before spawning when a setting that puts every subagent on one model (pointer below) is on and\n   would put the fleet on a tier above the fleet default, or on the session's model and so on the\n   orchestrator's tier.\n\n   - **Pointer**: before trusting a per-call `model` to set the fleet's tier, fetch\n     [Choose a model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-a-model) and\n     [Run every subagent on one model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#run-every-subagent-on-one-model)\n     live, and read the session's subagent-model environment variables against them.\n\n   **The fleet default is the tier whose writing has cleared the writer's bar**, not a fixed model\n   name, which goes stale at the next release. Resolve it from the consuming project's own\n   configuration for creative fan-out; where the project states none, ask before spawning rather\n   than inheriting. When a new tier appears it becomes eligible by clearing the same bar, not by\n   being newer.\n\n   **Never run a fleet on a tier priced above the fleet default.** A fan-out multiplies a tier's\n   per-token rate by the agent count. A tier above the default belongs at a judge or verifier stage\n   at most, where one call reads many writes. Pointer for the rates:\n   [Model pricing](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing#model-pricing).\n   Recheck trigger: that section prices a higher tier at or below the fleet default's rate.\n\n   **Reach for effort before reaching for a cheaper tier.** Effort scales the tokens one agent\n   spends; tier scales the price of every token AND changes which model wrote the lines. Across a\n   fleet both multiply, but only one of them changes the writing. A fan-out that needs the lever\n   sets it on the spawn, not through a workflow (the pointer below, to\n   [Choose an effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level),\n   says which spawns take it). A spawn of `object-writer` omits `effort` unless the writer asks for\n   another level.\n\n   - **Pointer**: before relying on the effort of an agent spawn, whether or not it passes\n     `effort`, fetch \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level> live.\n\n   **A tier step-down is a per-stage decision, never a fleet default.** Mechanical legs (rhyme-field\n   enumeration, word-pool merge, syllable counting, dedup) are reading-heavy and low-reasoning, and\n   in this skill's judgment (no eval measures it) a cheaper tier fits there. Object writing is neither. Dropping the writing fleet's own tier\n   to save cost is the writer's call, not the plugin's: ask, and never record the answer as his\n   without a source that says so.\n\n   Model tier is not what makes the fleet diverge; rule 2's isolation is. Any creative fan-out this\n   plugin adds later inherits this rule.\n\n**Never transcribe a write into lines.** The whole page is ore; Pat's discipline is to pull one\nimage out of it. Moving a dive wholesale into a section is the failure this action exists to\nprevent. What replaces transcription is `\u002Fsongwriting:co-write`'s three-step gate, Mine → adapt →\nsay it aloud: the mined image is rewritten in plain sung English before it enters a slot, then said\nout loud. Rule 4's \"then mine\" ends at the mining; the adapting and the saying belong to the\nemitting skill.\n\nNothing else in this skill dispatches agents. Metaphor generation is `\u002Fsongwriting:metaphor`;\nline-writing is not this skill's job at all (see the boundary below).\n\n## Persistence and template overrides\n\nWrite generated files to the paths in\n[artifact-persistence](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fartifact-persistence.md) \"Where\ngenerated work persists\", and honor a consuming project's own songwriting layout when it defines\none. Before loading any bundled `templates\u002F\u003Cname>.md`, check\n`${CLAUDE_PROJECT_DIR}\u002Fsongwriting\u002Ftemplates\u002Fpat-pattison\u002F\u003Cname>.md` first: a project-level\noverride wins over the bundled default, first match, per that file's \"Template override\".\n\n## Boundary. What this skill must NOT emit\n\nThis skill produces raw sensory material and figurative language. It does **not** produce finished\nlyric lines, and being mid-conversation about a song does not authorize it to.\n\n| If you are about to emit | STOP and route to |\n| --- | --- |\n| A finished verse, chorus, or bridge line | `\u002Fsongwriting:co-write` line-brainstorm |\n| A rhyme partner or rhyme list | `\u002Fsongwriting:rhyme` |\n| A section rewrite, or a judgment about where a section's material belongs | `\u002Fsongwriting:song-form` |\n| A scansion or stress-map claim | `\u002Fsongwriting:meter-prosody` |\n\nRouting means invoking that skill, not summarizing what you believe it would say. Emitting a lyric\nline from here is the specific failure the boundary exists to catch: the generative discipline\nlives in the skill that owns it, and material that skips that skill arrives as an LLM default\nwearing the vocabulary.\n\n## Related skills\n\n- Metaphor generation and diagnosis → `\u002Fsongwriting:metaphor`\n- Rhyme choice and rhyme cliche → `\u002Fsongwriting:rhyme`\n- Daily practice curriculum and numbered exercises → `\u002Fsongwriting:practice`\n- Whole-draft diagnosis (where images fail in context) → `\u002Fsongwriting:diagnose`\n","**Arguments.** `[object-writing|generate|cliche|pov|worksheet] [args]`. e.g.,\n\u002Fsongwriting:object-writing, \u002Fsongwriting:object-writing generate rain. Full actions in body.\n\n## Mandatory pre-flight. Response Filter\n\nBefore emitting any image, metaphor, sensory prompt, or rewrite, run **§7 Image filter (object\nwriting + metaphor)** of [response-filter](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fresponse-filter.md)\n(add **§2 Line-writing** when producing lines). NAME each box's pass \u002F fail \u002F skip-with-reason\n(aloud or in reasoning); correct before emission. Skips are valid; silent skips are not. Abstract\ntelling and cliche imagery are the defaults this filter catches.\n\nThis skill is the source of concrete detail the other skills shape. Metaphor is its own skill\n(`\u002Fsongwriting:metaphor`); this skill feeds it.\n\nMethod content is Pat Pattison's, under the plugin-root `..\u002F..\u002Fcontext\u002Fpat-pattison\u002F`; a future\nauthor's method plugs in at `context\u002F\u003Cauthor>\u002F` without changing this skill, the author seam per\nthe plugin-root `..\u002F..\u002FREADME.md` \"Method content and the author seam\".\n\n## Action Router\n\n`\u002Fsongwriting:object-writing \u003Caction> [args]`. Parse `$ARGUMENTS`: first token = action when it\nmatches a listed action, remainder = args; otherwise treat all of `$ARGUMENTS` as payload for the\ndefault. No action → issue one usable timed object-writing prompt immediately (do not assign a\ncurriculum).\n\n| Action | Use when the user asks for | Load |\n| --- | --- | --- |\n| `object-writing` (default) | sensory writing, showing instead of telling, raw material | [object-writing](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fobject-writing.md), [templates\u002Fobject-writing-prompt](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Ftemplates\u002Fobject-writing-prompt.md) |\n| `generate` | **YOU** do the object writing. \"you write it\", \"do the object writing\", \"I don't want to write it\", or any request for raw sensory material the writer is not going to produce | dispatch the `object-writer` agent. See below |\n| `cliche` | cliche phrase, cliche image, stale metaphor, cliche rhyme | [cliche](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fcliche.md), [worksheets](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fworksheets.md), [metaphor](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fmetaphor.md) |\n| `pov` | first\u002Fsecond\u002Fthird person, direct address, dialogue, pronoun consistency, camera distance | [point-of-view](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fpoint-of-view.md) |\n| `worksheet` | broader sense-bound worksheets (not rhyme worksheets) | [worksheets](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fworksheets.md) |\n\n## Handlers\n\n- If the user asks for a prompt, generate one usable timed exercise immediately (default\n  90 seconds). Do not assign the full curriculum unless asked; that is `\u002Fsongwriting:practice`.\n- Keep object writing sense-bound and personal; its job is to reveal specific, sensory detail, not\n  to produce finished lines.\n- A metaphor request routes to `\u002Fsongwriting:metaphor`, invoked via the Skill tool. Hand over the\n  material mined here as its input; do not generate the metaphor here.\n\n## `generate`. Dispatch, never write it inline\n\n**Who writes matters more than what is loaded.** Reading this skill's files and then writing a dive\nin the main thread reliably produces a static scene description, because the discipline was read\nrather than carried. Dispatch the `object-writer` agent, whose system prompt IS the discipline.\n\nDispatch rules:\n\n1. **One agent per seed**, all in a single message so they run concurrently. Two agents on the same\n   seed is a valid and useful play: same board, different dives.\n2. **Give each agent nothing but the seed, the timer, the category, and its own output path.** Not\n   the song, not the title, not the draft, not the diagnosis, not the other agents' seeds. The\n   isolation is the mechanism; briefing an agent on the song destroys the divergence it exists to\n   produce. This is a hard boundary, not a default.\n3. **Each agent writes to its own file** under the song's `ideation\u002F` (per\n   [artifact-persistence](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fartifact-persistence.md)). It returns\n   only three things: the path, the seven channels each graded `strong` \u002F `thin` \u002F `absent`, and\n   one sentence on where the pivot chain landed. The write itself and the phrase-quoting sense\n   inventory live in the file; never ask an agent to return either in a message.\n4. **Grade coverage on return**, then mine. Read each file, honor thin-channel reports rather than\n   overruling them, and pull individual images forward. Mining stays here because you hold the song\n   context the writers deliberately lack.\n5. **For rounds:** name what made the strongest write of a round work, then carry that as the\n   standard into the next round's dispatch. The bar escalates; rounds are not independent repeats.\n6. **Set the model explicitly on every agent call; never let the fleet inherit the session's.** The\n   `object-writer` agent's frontmatter pins `opus` as a fail-safe, so a call that forgets the model\n   does not simply inherit the session's model, a tier picked for the orchestrator's work, not the\n   writers'. Whether the pin can still resolve to the session's own model is the Choose a model\n   pointer below's to state; check it before relying on the pin.\n   The pin is not the fleet tier: every call still names the fleet default below. Stop to ask\n   before spawning when a setting that puts every subagent on one model (pointer below) is on and\n   would put the fleet on a tier above the fleet default, or on the session's model and so on the\n   orchestrator's tier.\n\n   - **Pointer**: before trusting a per-call `model` to set the fleet's tier, fetch\n     [Choose a model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-a-model) and\n     [Run every subagent on one model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#run-every-subagent-on-one-model)\n     live, and read the session's subagent-model environment variables against them.\n\n   **The fleet default is the tier whose writing has cleared the writer's bar**, not a fixed model\n   name, which goes stale at the next release. Resolve it from the consuming project's own\n   configuration for creative fan-out; where the project states none, ask before spawning rather\n   than inheriting. When a new tier appears it becomes eligible by clearing the same bar, not by\n   being newer.\n\n   **Never run a fleet on a tier priced above the fleet default.** A fan-out multiplies a tier's\n   per-token rate by the agent count. A tier above the default belongs at a judge or verifier stage\n   at most, where one call reads many writes. Pointer for the rates:\n   [Model pricing](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing#model-pricing).\n   Recheck trigger: that section prices a higher tier at or below the fleet default's rate.\n\n   **Reach for effort before reaching for a cheaper tier.** Effort scales the tokens one agent\n   spends; tier scales the price of every token AND changes which model wrote the lines. Across a\n   fleet both multiply, but only one of them changes the writing. A fan-out that needs the lever\n   sets it on the spawn, not through a workflow (the pointer below, to\n   [Choose an effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level),\n   says which spawns take it). A spawn of `object-writer` omits `effort` unless the writer asks for\n   another level.\n\n   - **Pointer**: before relying on the effort of an agent spawn, whether or not it passes\n     `effort`, fetch \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level> live.\n\n   **A tier step-down is a per-stage decision, never a fleet default.** Mechanical legs (rhyme-field\n   enumeration, word-pool merge, syllable counting, dedup) are reading-heavy and low-reasoning, and\n   in this skill's judgment (no eval measures it) a cheaper tier fits there. Object writing is neither. Dropping the writing fleet's own tier\n   to save cost is the writer's call, not the plugin's: ask, and never record the answer as his\n   without a source that says so.\n\n   Model tier is not what makes the fleet diverge; rule 2's isolation is. Any creative fan-out this\n   plugin adds later inherits this rule.\n\n**Never transcribe a write into lines.** The whole page is ore; Pat's discipline is to pull one\nimage out of it. Moving a dive wholesale into a section is the failure this action exists to\nprevent. What replaces transcription is `\u002Fsongwriting:co-write`'s three-step gate, Mine → adapt →\nsay it aloud: the mined image is rewritten in plain sung English before it enters a slot, then said\nout loud. Rule 4's \"then mine\" ends at the mining; the adapting and the saying belong to the\nemitting skill.\n\nNothing else in this skill dispatches agents. Metaphor generation is `\u002Fsongwriting:metaphor`;\nline-writing is not this skill's job at all (see the boundary below).\n\n## Persistence and template overrides\n\nWrite generated files to the paths in\n[artifact-persistence](..\u002F..\u002Fcontext\u002Fpat-pattison\u002Fresearch\u002Fartifact-persistence.md) \"Where\ngenerated work persists\", and honor a consuming project's own songwriting layout when it defines\none. Before loading any bundled `templates\u002F\u003Cname>.md`, check\n`${CLAUDE_PROJECT_DIR}\u002Fsongwriting\u002Ftemplates\u002Fpat-pattison\u002F\u003Cname>.md` first: a project-level\noverride wins over the bundled default, first match, per that file's \"Template override\".\n\n## Boundary. What this skill must NOT emit\n\nThis skill produces raw sensory material and figurative language. It does **not** produce finished\nlyric lines, and being mid-conversation about a song does not authorize it to.\n\n| If you are about to emit | STOP and route to |\n| --- | --- |\n| A finished verse, chorus, or bridge line | `\u002Fsongwriting:co-write` line-brainstorm |\n| A rhyme partner or rhyme list | `\u002Fsongwriting:rhyme` |\n| A section rewrite, or a judgment about where a section's material belongs | `\u002Fsongwriting:song-form` |\n| A scansion or stress-map claim | `\u002Fsongwriting:meter-prosody` |\n\nRouting means invoking that skill, not summarizing what you believe it would say. Emitting a lyric\nline from here is the specific failure the boundary exists to catch: the generative discipline\nlives in the skill that owns it, and material that skips that skill arrives as an LLM default\nwearing the vocabulary.\n\n## Related skills\n\n- Metaphor generation and diagnosis → `\u002Fsongwriting:metaphor`\n- Rhyme choice and rhyme cliche → `\u002Fsongwriting:rhyme`\n- Daily practice curriculum and numbered exercises → `\u002Fsongwriting:practice`\n- Whole-draft diagnosis (where images fail in context) → `\u002Fsongwriting:diagnose`\n",{"description":7,"argument-hint":24,"user-invocable":25,"disable-model-invocation":20},"[object-writing|generate|cliche|pov|worksheet] [args]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fsongwriting\u002Fskills\u002Fobject-writing",7,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins","https:\u002F\u002Fgithub.com\u002Fmelodic-software","https:\u002F\u002Fmelodicsoftware.com","Independent software studio building developer tools, automation, and application services, with roots in music.","2026-11-15 05:15:06",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":25},[37,40,43],{"tool":38,"command":39},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill object-writing",{"tool":41,"command":42},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill object-writing",{"tool":44,"command":45},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill object-writing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsongwriting\u002Fskills\u002Fobject-writing\u002FSKILL.md",[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"evals\u002Fevals.json","REFERENCE","参考文档",11210,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsongwriting\u002Fskills\u002Fobject-writing\u002Fevals\u002Fevals.json",[55,62,69,76,81,88],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DYYDG31B9YX7N9MB9QW2GW","track","Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-flow\u002Fevals\u002Frecall-still-reports-reopened-bug\u002Fwork-items-stub\u002Fskills\u002Ftrack\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DYXVBAVG3NV30PA7GKW9Q6","reviewer-media","Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from \u002Freview:explain-change's digest, has \u002Fexplainer-video:produce render it and hands the manifest to \u002Fsource-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Freview\u002Fskills\u002Freviewer-media\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DYRZ5YD44AMYH26YR25GZ8","route","Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-pin-without-override\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":77,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7DYRTVT4FWTGDJY0HCCFJMZ","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-override-from-route\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7DYNZC8PNW3T27V2ADKECKJ","principles","Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is \u002Farchitecture:improve.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fskills\u002Fprinciples\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7DYNMCZNEWBFHV9KTSS6H60","write","Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fevals\u002Fdeepening-defect-goes-to-bugs-write\u002Fbugs-stub\u002Fskills\u002Fwrite\u002FSKILL.md",[],[]]