[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KEDTMRCF7R3DJ1Q1CXAMK":3,"skill-same:01M77KEDTMRCF7R3DJ1Q1CXAMK":52},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M77KEDTMRCF7R3DJ1Q1CXAMK","tighten-your-output",null,"Re-anchors terseness discipline (markdown in fewer words without semantic loss, code in fewer lines when readability holds), then audits the work in flight for avoidable verbosity and tightens 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.","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\u002Fdiscipline\u002Fskills\u002Ftighten-your-output\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Re-anchors terseness discipline (markdown in fewer words without semantic loss, code in fewer lines when readability holds), then audits the work in flight for avoidable verbosity and tightens 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.\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  discipline-batch: core  # every session produces output that can tighten; runs last so it never tightens text a later corrector rewrites\n  discipline-batch-rank: 110\n  workflow-stage: anytime\n  summary: Tighten prose and code. Fewer words, no semantic loss\n---\n\n# Tighten your output\n\nA drift corrector for terseness discipline. The shared method (re-anchor,\naudit the work in flight, correct forward, report) lives in\n[`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fre-anchor-audit-correct.md`](..\u002F..\u002Fcontext\u002Fre-anchor-audit-correct.md).\nRead it; this file adds only what is specific to terseness discipline.\n\n## The discipline this re-anchors\n\nSay it in fewer words or lines when nothing of value is lost. Two surfaces,\nresolved separately per the method doc's ladder.\n\n### Code, a standards convention owns this\n\nThe source of truth is the consuming organization's simpler-code\nconvention: prefer the smaller form when it costs no correctness,\nreadability, test coverage, observability, or convention conformance. Read\nit where it lives; re-anchor its two load-bearing parts rather than\nrestating them:\n\n- its **named failure modes**, the canonical smells a reduction must not\n  introduce (speculative generality, the wrong abstraction, YAGNI);\n- its **constraints never traded for line count**. Clarity, test coverage,\n  error handling at boundaries, established conventions, and observability\n  survive every cut.\n\nWhen the consuming project declares no such convention, re-anchor that same\nshape as the portable baseline: fewer lines is the default only when none\nof those constraints is spent to get there.\n\n### Markdown. A flagged standards gap with a routing owner\n\nSay the same thing in fewer words with **no semantic loss**. Drop filler,\nhedging, and restatement, never a directive, qualifier, threshold, or\nexample. Tightening selects what to include; it does not compress prose into\nfragments, abbreviations, arrow chains, or jargon, and it keeps complete\nsentences a reader who did not watch the work can follow. When brevity and\nreadability conflict, readability wins. Prose terseness usually has **no\ndedicated standards convention**: when the consuming project's standards\nsource declares one, route through it; when it does not, that is a flagged\ngap (a candidate upstream standards addition), not license to invent a rubric\nin this skill. Route reader-facing prose and batch prose work per the\nRouting section below.\n\n## Audit. What to look for\n\nName concrete, located findings (per the method doc's step 2, self-audit; on load-bearing work a fresh-context subagent confirms a clean result):\n\n- prose padded with filler, hedging, or a restatement of what an adjacent\n  sentence already said;\n- code carrying speculative parameters, dead branches, or hand-rolled\n  boilerplate a built-in would replace;\n- a long form kept where a shorter one loses nothing of value.\n\nCorrect each forward now, but only where the reduction is free: tighten the\nprose without dropping a directive\u002Fqualifier\u002Fthreshold\u002Fexample, and shrink\nthe code without spending clarity, tests, error handling, conventions, or\nobservability. When a cut would cost any of those, leave the longer form and\nsay why.\n\nResolve the verification level once with\n`bash \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fread-verification.sh\" --plugin discipline --skill tighten-your-output --file docs\u002Fconventions\u002Fdiscipline.yaml`\nand report its line ([levels](https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fdocs\u002Fcontracts\u002Fverification-level\u002FREADME.md)):\n`light` and `off` skip the method doc's step 2 and step 3 subagents, as it says, and the final reply then carries the line `verification: skipped (\u003Clevel>)` verbatim, such as `verification: skipped (light)`.\n\n## Routing, where batch and proactive work live\n\n- **Prose a person reads (a ticket comment, a pull-request body, a doc, a\n  status update) → `\u002Fwriting:be-concise`** when the `writing` plugin is\n  installed. It owns the point-first, scannable shape those readers need,\n  which this corrector does not. Without that plugin, reduce against the\n  markdown discipline above and say the point-first shape went unapplied.\n- **Batch prose remediation → the docs-hygiene compress capability** when\n  that plugin is installed (its semantic-diff safety net is the guardrail for\n  large prose cuts); otherwise run that same semantic-diff discipline as an\n  explicit in-thread pass rather than hand-rolling a rubric here.\n- **Batch code reduction → the code-tidying batch-simplify capability** over a\n  change set when that plugin is installed; otherwise reduce in-thread against\n  the simpler-code convention, spending no clarity, test, error handling,\n  convention, or observability to do it.\n- **Proactive code-side enforcement is NOT here.** It lives in review and\n  design gates that cite the simpler-code convention; this corrector\n  re-anchors the discipline and corrects the work in flight.\n\n## Trigger ownership. One owner per brevity phrase\n\nTwo standing brevity postures exist, so the vocabularies are split rather\nthan shared. The test is what the phrase names: the output in front of us, or\nan artifact a reader will open. A phrase that names neither is a register\ndirective, and its default target is the conversation, so it stays here.\nEvery phrase has exactly one owner, and neither description claims a phrase\nthis table gives the other.\n\n| Phrase | Owner | Why |\n|---|---|---|\n| `'tighten your output'` | this skill | Names the assistant's own output |\n| `'tighten this'` | this skill | Unbound target, so the thing in flight |\n| `'too verbose'` | this skill | A verdict on what was just produced |\n| `'say it in fewer words'` | this skill | Re-saying inside the conversation |\n| `'this is bloated'` | this skill | Unbound target, most often code |\n| `'trim the code'` | this skill | Code terseness |\n| `'simpler form'` | this skill | Code terseness |\n| `'cut the wordiness'` | this skill | A register directive, no artifact named |\n| `'be more concise'` | this skill | A register directive, no artifact named |\n| `'write this for the PO'` | `writing:be-concise` | Names the reader |\n| `'shorten this ticket'` | `writing:be-concise` | Names the artifact |\n| `'make this scannable'` | `writing:be-concise` | A property only a human reader needs |\n| `'bottom line first'` | `writing:be-concise` | A property only a human reader needs |\n| `'nobody will read this'` | `writing:be-concise` | Names the reader |\n| `'rewrite this PR description for reviewers'` | `writing:be-concise` | Names the artifact and its readers |\n\nOnce either skill is loaded, route by the target in front of you, not by the\nphrase that reached it; the sections above say where.\n\n## Gotchas\n\n- Terseness is not duplication. Removing a second copy of a fact is\n  `\u002Fdiscipline:point-dont-copy`; removing wasted words from a single copy is\n  this skill.\n- The failure mode is over-cutting: a \"concise\" edit that quietly drops a\n  qualifier or a boundary case has traded meaning for length. Judge every\n  cut by what it costs, not by how many words it saves.\n","# Tighten your output\n\nA drift corrector for terseness discipline. The shared method (re-anchor,\naudit the work in flight, correct forward, report) lives in\n[`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fre-anchor-audit-correct.md`](..\u002F..\u002Fcontext\u002Fre-anchor-audit-correct.md).\nRead it; this file adds only what is specific to terseness discipline.\n\n## The discipline this re-anchors\n\nSay it in fewer words or lines when nothing of value is lost. Two surfaces,\nresolved separately per the method doc's ladder.\n\n### Code, a standards convention owns this\n\nThe source of truth is the consuming organization's simpler-code\nconvention: prefer the smaller form when it costs no correctness,\nreadability, test coverage, observability, or convention conformance. Read\nit where it lives; re-anchor its two load-bearing parts rather than\nrestating them:\n\n- its **named failure modes**, the canonical smells a reduction must not\n  introduce (speculative generality, the wrong abstraction, YAGNI);\n- its **constraints never traded for line count**. Clarity, test coverage,\n  error handling at boundaries, established conventions, and observability\n  survive every cut.\n\nWhen the consuming project declares no such convention, re-anchor that same\nshape as the portable baseline: fewer lines is the default only when none\nof those constraints is spent to get there.\n\n### Markdown. A flagged standards gap with a routing owner\n\nSay the same thing in fewer words with **no semantic loss**. Drop filler,\nhedging, and restatement, never a directive, qualifier, threshold, or\nexample. Tightening selects what to include; it does not compress prose into\nfragments, abbreviations, arrow chains, or jargon, and it keeps complete\nsentences a reader who did not watch the work can follow. When brevity and\nreadability conflict, readability wins. Prose terseness usually has **no\ndedicated standards convention**: when the consuming project's standards\nsource declares one, route through it; when it does not, that is a flagged\ngap (a candidate upstream standards addition), not license to invent a rubric\nin this skill. Route reader-facing prose and batch prose work per the\nRouting section below.\n\n## Audit. What to look for\n\nName concrete, located findings (per the method doc's step 2, self-audit; on load-bearing work a fresh-context subagent confirms a clean result):\n\n- prose padded with filler, hedging, or a restatement of what an adjacent\n  sentence already said;\n- code carrying speculative parameters, dead branches, or hand-rolled\n  boilerplate a built-in would replace;\n- a long form kept where a shorter one loses nothing of value.\n\nCorrect each forward now, but only where the reduction is free: tighten the\nprose without dropping a directive\u002Fqualifier\u002Fthreshold\u002Fexample, and shrink\nthe code without spending clarity, tests, error handling, conventions, or\nobservability. When a cut would cost any of those, leave the longer form and\nsay why.\n\nResolve the verification level once with\n`bash \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fread-verification.sh\" --plugin discipline --skill tighten-your-output --file docs\u002Fconventions\u002Fdiscipline.yaml`\nand report its line ([levels](https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fdocs\u002Fcontracts\u002Fverification-level\u002FREADME.md)):\n`light` and `off` skip the method doc's step 2 and step 3 subagents, as it says, and the final reply then carries the line `verification: skipped (\u003Clevel>)` verbatim, such as `verification: skipped (light)`.\n\n## Routing, where batch and proactive work live\n\n- **Prose a person reads (a ticket comment, a pull-request body, a doc, a\n  status update) → `\u002Fwriting:be-concise`** when the `writing` plugin is\n  installed. It owns the point-first, scannable shape those readers need,\n  which this corrector does not. Without that plugin, reduce against the\n  markdown discipline above and say the point-first shape went unapplied.\n- **Batch prose remediation → the docs-hygiene compress capability** when\n  that plugin is installed (its semantic-diff safety net is the guardrail for\n  large prose cuts); otherwise run that same semantic-diff discipline as an\n  explicit in-thread pass rather than hand-rolling a rubric here.\n- **Batch code reduction → the code-tidying batch-simplify capability** over a\n  change set when that plugin is installed; otherwise reduce in-thread against\n  the simpler-code convention, spending no clarity, test, error handling,\n  convention, or observability to do it.\n- **Proactive code-side enforcement is NOT here.** It lives in review and\n  design gates that cite the simpler-code convention; this corrector\n  re-anchors the discipline and corrects the work in flight.\n\n## Trigger ownership. One owner per brevity phrase\n\nTwo standing brevity postures exist, so the vocabularies are split rather\nthan shared. The test is what the phrase names: the output in front of us, or\nan artifact a reader will open. A phrase that names neither is a register\ndirective, and its default target is the conversation, so it stays here.\nEvery phrase has exactly one owner, and neither description claims a phrase\nthis table gives the other.\n\n| Phrase | Owner | Why |\n|---|---|---|\n| `'tighten your output'` | this skill | Names the assistant's own output |\n| `'tighten this'` | this skill | Unbound target, so the thing in flight |\n| `'too verbose'` | this skill | A verdict on what was just produced |\n| `'say it in fewer words'` | this skill | Re-saying inside the conversation |\n| `'this is bloated'` | this skill | Unbound target, most often code |\n| `'trim the code'` | this skill | Code terseness |\n| `'simpler form'` | this skill | Code terseness |\n| `'cut the wordiness'` | this skill | A register directive, no artifact named |\n| `'be more concise'` | this skill | A register directive, no artifact named |\n| `'write this for the PO'` | `writing:be-concise` | Names the reader |\n| `'shorten this ticket'` | `writing:be-concise` | Names the artifact |\n| `'make this scannable'` | `writing:be-concise` | A property only a human reader needs |\n| `'bottom line first'` | `writing:be-concise` | A property only a human reader needs |\n| `'nobody will read this'` | `writing:be-concise` | Names the reader |\n| `'rewrite this PR description for reviewers'` | `writing:be-concise` | Names the artifact and its readers |\n\nOnce either skill is loaded, route by the target in front of you, not by the\nphrase that reached it; the sections above say where.\n\n## Gotchas\n\n- Terseness is not duplication. Removing a second copy of a fact is\n  `\u002Fdiscipline:point-dont-copy`; removing wasted words from a single copy is\n  this skill.\n- The failure mode is over-cutting: a \"concise\" edit that quietly drops a\n  qualifier or a boundary case has traded meaning for length. Judge every\n  cut by what it costs, not by how many words it saves.\n",{"metadata":24,"description":7,"user-invocable":29,"disable-model-invocation":20},{"summary":25,"workflow-stage":26,"discipline-batch":27,"discipline-batch-rank":28},"Tighten prose and code. Fewer words, no semantic loss","anytime","core",110,true,"main","4f2dcaaff35e8f9fccc6a9f4d82a5830ab17a5c5","plugins\u002Fdiscipline\u002Fskills\u002Ftighten-your-output",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":40,"prompt":50,"zipAvailable":29},[41,44,47],{"tool":42,"command":43},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill tighten-your-output",{"tool":45,"command":46},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill tighten-your-output",{"tool":48,"command":49},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill tighten-your-output","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscipline\u002Fskills\u002Ftighten-your-output\u002FSKILL.md",[],[53,60,67,74,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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",[],[]]