object-writing
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/Kami-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 /songwriting:metaphor; for rhyme use /songwriting:rhyme; for daily curriculum use /songwriting:practice.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 30
- Forks
- 7
01 前言 Front Matter
- description
- 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/Kami-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 /songwriting:metaphor; for rhyme use /songwriting:rhyme; for daily curriculum use /songwriting:practice.
- argument-hint
- [object-writing|generate|cliche|pov|worksheet] [args]
- user-invocable
- true
- disable-model-invocation
- false
02 资源文件 1
- 参考文档evals/evals.json10.9 KB
03 SKILL.md 正文
Arguments. [object-writing|generate|cliche|pov|worksheet] [args]. e.g.,
/songwriting:object-writing, /songwriting:object-writing generate rain. Full actions in body.
Mandatory pre-flight. Response Filter
Before emitting any image, metaphor, sensory prompt, or rewrite, run §7 Image filter (object writing + metaphor) of response-filter (add §2 Line-writing when producing lines). NAME each box's pass / fail / skip-with-reason (aloud or in reasoning); correct before emission. Skips are valid; silent skips are not. Abstract telling and cliche imagery are the defaults this filter catches.
This skill is the source of concrete detail the other skills shape. Metaphor is its own skill
(/songwriting:metaphor); this skill feeds it.
Method content is Pat Pattison's, under the plugin-root ../../context/pat-pattison/; a future
author's method plugs in at context/<author>/ without changing this skill, the author seam per
the plugin-root ../../README.md "Method content and the author seam".
Action Router
/songwriting:object-writing <action> [args]. Parse $ARGUMENTS: first token = action when it
matches a listed action, remainder = args; otherwise treat all of $ARGUMENTS as payload for the
default. No action → issue one usable timed object-writing prompt immediately (do not assign a
curriculum).
| Action | Use when the user asks for | Load |
|---|---|---|
object-writing (default) |
sensory writing, showing instead of telling, raw material | object-writing, templates/object-writing-prompt |
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 |
cliche |
cliche phrase, cliche image, stale metaphor, cliche rhyme | cliche, worksheets, metaphor |
pov |
first/second/third person, direct address, dialogue, pronoun consistency, camera distance | point-of-view |
worksheet |
broader sense-bound worksheets (not rhyme worksheets) | worksheets |
Handlers
- If the user asks for a prompt, generate one usable timed exercise immediately (default
90 seconds). Do not assign the full curriculum unless asked; that is
/songwriting:practice. - Keep object writing sense-bound and personal; its job is to reveal specific, sensory detail, not to produce finished lines.
- A metaphor request routes to
/songwriting:metaphor, invoked via the Skill tool. Hand over the material mined here as its input; do not generate the metaphor here.
generate. Dispatch, never write it inline
Who writes matters more than what is loaded. Reading this skill's files and then writing a dive
in the main thread reliably produces a static scene description, because the discipline was read
rather than carried. Dispatch the object-writer agent, whose system prompt IS the discipline.
Dispatch rules:
-
One agent per seed, all in a single message so they run concurrently. Two agents on the same seed is a valid and useful play: same board, different dives.
-
Give each agent nothing but the seed, the timer, the category, and its own output path. Not the song, not the title, not the draft, not the diagnosis, not the other agents' seeds. The isolation is the mechanism; briefing an agent on the song destroys the divergence it exists to produce. This is a hard boundary, not a default.
-
Each agent writes to its own file under the song's
ideation/(per artifact-persistence). It returns only three things: the path, the seven channels each gradedstrong/thin/absent, and one sentence on where the pivot chain landed. The write itself and the phrase-quoting sense inventory live in the file; never ask an agent to return either in a message. -
Grade coverage on return, then mine. Read each file, honor thin-channel reports rather than overruling them, and pull individual images forward. Mining stays here because you hold the song context the writers deliberately lack.
-
For rounds: name what made the strongest write of a round work, then carry that as the standard into the next round's dispatch. The bar escalates; rounds are not independent repeats.
-
Set the model explicitly on every agent call; never let the fleet inherit the session's. The
object-writeragent's frontmatter pinsopusas a fail-safe, so a call that forgets the model does not simply inherit the session's model, a tier picked for the orchestrator's work, not the writers'. Whether the pin can still resolve to the session's own model is the Choose a model pointer below's to state; check it before relying on the pin. The pin is not the fleet tier: every call still names the fleet default below. Stop to ask before spawning when a setting that puts every subagent on one model (pointer below) is on and would put the fleet on a tier above the fleet default, or on the session's model and so on the orchestrator's tier.- Pointer: before trusting a per-call
modelto set the fleet's tier, fetch Choose a model and Run every subagent on one model live, and read the session's subagent-model environment variables against them.
The fleet default is the tier whose writing has cleared the writer's bar, not a fixed model name, which goes stale at the next release. Resolve it from the consuming project's own configuration for creative fan-out; where the project states none, ask before spawning rather than inheriting. When a new tier appears it becomes eligible by clearing the same bar, not by being newer.
Never run a fleet on a tier priced above the fleet default. A fan-out multiplies a tier's per-token rate by the agent count. A tier above the default belongs at a judge or verifier stage at most, where one call reads many writes. Pointer for the rates: Model pricing. Recheck trigger: that section prices a higher tier at or below the fleet default's rate.
Reach for effort before reaching for a cheaper tier. Effort scales the tokens one agent spends; tier scales the price of every token AND changes which model wrote the lines. Across a fleet both multiply, but only one of them changes the writing. A fan-out that needs the lever sets it on the spawn, not through a workflow (the pointer below, to Choose an effort level, says which spawns take it). A spawn of
object-writeromitseffortunless the writer asks for another level.- Pointer: before relying on the effort of an agent spawn, whether or not it passes
effort, fetch https://code.claude.com/docs/en/sub-agents#choose-an-effort-level live.
A tier step-down is a per-stage decision, never a fleet default. Mechanical legs (rhyme-field enumeration, word-pool merge, syllable counting, dedup) are reading-heavy and low-reasoning, and 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 to save cost is the writer's call, not the plugin's: ask, and never record the answer as his without a source that says so.
Model tier is not what makes the fleet diverge; rule 2's isolation is. Any creative fan-out this plugin adds later inherits this rule.
- Pointer: before trusting a per-call
Never transcribe a write into lines. The whole page is ore; Pat's discipline is to pull one
image out of it. Moving a dive wholesale into a section is the failure this action exists to
prevent. What replaces transcription is /songwriting:co-write's three-step gate, Mine → adapt →
say it aloud: the mined image is rewritten in plain sung English before it enters a slot, then said
out loud. Rule 4's "then mine" ends at the mining; the adapting and the saying belong to the
emitting skill.
Nothing else in this skill dispatches agents. Metaphor generation is /songwriting:metaphor;
line-writing is not this skill's job at all (see the boundary below).
Persistence and template overrides
Write generated files to the paths in
artifact-persistence "Where
generated work persists", and honor a consuming project's own songwriting layout when it defines
one. Before loading any bundled templates/<name>.md, check
${CLAUDE_PROJECT_DIR}/songwriting/templates/pat-pattison/<name>.md first: a project-level
override wins over the bundled default, first match, per that file's "Template override".
Boundary. What this skill must NOT emit
This skill produces raw sensory material and figurative language. It does not produce finished lyric lines, and being mid-conversation about a song does not authorize it to.
| If you are about to emit | STOP and route to |
|---|---|
| A finished verse, chorus, or bridge line | /songwriting:co-write line-brainstorm |
| A rhyme partner or rhyme list | /songwriting:rhyme |
| A section rewrite, or a judgment about where a section's material belongs | /songwriting:song-form |
| A scansion or stress-map claim | /songwriting:meter-prosody |
Routing means invoking that skill, not summarizing what you believe it would say. Emitting a lyric line from here is the specific failure the boundary exists to catch: the generative discipline lives in the skill that owns it, and material that skips that skill arrives as an LLM default wearing the vocabulary.
Related skills
- Metaphor generation and diagnosis →
/songwriting:metaphor - Rhyme choice and rhyme cliche →
/songwriting:rhyme - Daily practice curriculum and numbered exercises →
/songwriting:practice - Whole-draft diagnosis (where images fail in context) →
/songwriting:diagnose
04 同仓库更多 Skills
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.
reviewer-media
Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from /review:explain-change's digest, has /explainer-video:produce render it and hands the manifest to /source-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.
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.
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.
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 /architecture:improve.
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').