[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQNACJB36T0A039HT89P38":3,"skill-same:01M7CQNACJB36T0A039HT89P38":225},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7CQNACJB36T0A039HT89P38","loom-visualization",null,"Show comparisons, flows, decisions, states or reasoning chains as tables, ASCII or Mermaid in coding chat, including when a Loom station reports to the user (intent restatement, choices, acceptance test results); not Obsidian notes.","kouko\u002Floom-plugins","kouko","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1480254?v=4","01M7CQCPAJR9C92XDGR0QDCQ98","01M7CQCPB8FTVY1BT26ENK1YP4",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: loom-visualization\ndescription: |\n  Show comparisons, flows, decisions, states or reasoning chains as tables, ASCII or Mermaid in coding chat, including when a Loom station reports to the user (intent restatement, choices, acceptance test results); not Obsidian notes.\n---\n\n# Loom Visualization\n\nDeliver local documents with actual absolute paths from the active worktree or\nexternal location, including in copyable instructions. For known local Markdown\nsupport, use the document's project-relative path as link text (external files:\nbasename) and absolute targets; otherwise show full absolute paths. Enclose\ntargets with spaces in angle brackets: `[doc.md](\u003C\u002Fworktree name\u002Fdoc.md>)`. Preserve bundled references, stored\nrelative paths, quoted examples and incidental filenames.\n\nPick the right shape and form for information in a coding-harness\nconversation, so the reader gets a table or a diagram that actually displays\nin their client instead of prose or broken Mermaid source.\n\n`\u003Cskill-dir>` is this skill's folder: `${CLAUDE_SKILL_DIR}` on Claude Code;\non any other host, the directory that holds this SKILL.md. Run every script\nas `python3 \u003Cskill-dir>\u002Fscripts\u002F\u003Cname>.py`; all other paths below are\nrelative to `\u003Cskill-dir>`. The scripts need only the Python standard library.\n\nA one-line fact needs no table. Reach for this skill when the answer has a\nshape: options side by side, three or more steps, a branch, a lifecycle, a\nmessage exchange, a structure, dates, or numbers to compare.\n\n## Boundary\n\n\u003C!-- gate: loom-visualization.obsidian-boundary -->\nWhen the output is written to a file, first run\n`python3 \u003Cskill-dir>\u002Fscripts\u002Fdetect_client.py --target \u003Cpath>`. Decline only when that\n`--target` check reports `obsidian_vault: true`, or when the user asks for a\nnote in their Obsidian vault: say this skill serves coding-harness chat, and\nname `obsidian:obsidian-mermaid-visualizer` as the skill for vault notes.\nA chat answer proceeds normally even when the working directory is inside an\nObsidian vault. Never\nput Obsidian-only syntax (wikilinks, callouts, `%%` comment lines) into\nanything this skill produces.\n\u003C!-- \u002Fgate -->\n\nAlso out of scope: diagram rules for commit messages, pull requests and\nrepository documents. Those follow the rules of the skill that owns the\nartifact (`loom-workflow:git-memory`, `loom-code:ship`,\n`loom-design:write-spec`).\n\nDocumented reasoning turned into a standalone page is page mode, below.\n\n## Plain language and conversation tables\n\nThese references sit beside the data-shape templates; the templates in\nStep 1 stay as they are.\n\n| Need | Read |\n|---|---|\n| A plainer explanation, a decision question, or a table for a conversation situation (decision, before and after, progress, checklist, confirmed and unconfirmed, findings, risks, support matrix) | `references\u002Fplain-language.md` |\n| A software document: incident postmortem or incident report, test plan, traceability or compatibility matrix, migration guide, API parameters, runbook, RACI, ADR or RFC options, technology selection, feature-flag rollout, release notes, risk register, RAID log, threat model (STRIDE), decision table, state-transition table, truth table, morphological box, risk matrix, feature table, confusion matrix, correlation matrix | `references\u002Ftables-software.md` |\n| A design document: heuristic evaluation, usability test report, content audit, design critique, design tokens, component states, accessibility audit, journey map, personas or JTBD, design decision log | `references\u002Ftables-design.md` |\n| A business document: weighted or Pugh matrix, RICE, ICE, MoSCoW or WSJF, SWOT or TOWS, competitive analysis, Five Forces, stakeholder analysis, scenario planning, business case, OKR, assumption log, go\u002Fno-go, pricing tiers, Kano, decisional balance sheet, roadmap, 2×2 quadrants | `references\u002Ftables-business.md` |\n\nRead only the one file whose row matches; a conversation-situation reply never opens a domain file.\n\n## Step 1 — Classify the information shape\n\nName the one shape the information has. If it has two, draw the one the\nreader must act on, and state the other in a sentence.\n\n| Shape | Signals | Template | Generator |\n|---|---|---|---|\n| Option comparison | 2+ options, shared criteria | `templates\u002F01-option-comparison.md` | `table` |\n| Linear steps | 3+ steps, fixed order, no branch; before\u002Fafter flows in titled panels | `templates\u002F02-linear-steps.md` | `flow` |\n| Branching decision | a question sends work down different paths | `templates\u002F03-branching-decision.md` | none |\n| Reasoning chain | causes or inferences leading to a conclusion | `templates\u002F04-reasoning-chain.md` | none |\n| State lifecycle | named states changed by named events | `templates\u002F05-state-lifecycle.md` | none |\n| Actor sequence | actors exchanging messages in time order | `templates\u002F06-actor-sequence.md` | `seq` |\n| Task dependencies | parallel prerequisites feeding a required join | `templates\u002F12-task-dependencies.md` | none |\n| Cross-role workflow | steps with different work ownership and handoffs | `templates\u002F13-cross-role-workflow.md` | none |\n| Hierarchy | parent-child, no cross-links | `templates\u002F07-hierarchy.md` | `tree` |\n| System architecture | components in layers with dependencies | `templates\u002F08-system-architecture.md` | `arch` |\n| Data model | entities, fields, cardinality | `templates\u002F09-data-model.md` | none (table substitute) |\n| Timeline | events on dates or periods | `templates\u002F10-timeline.md` | none |\n| Quantity | a few labelled numbers to compare | `templates\u002F11-quantity.md` | `bar` |\n\n## Step 2 — Read only that template\n\nRead the one template file from Step 1, and no other. Each template gives the\nshape's table form, ASCII form, Mermaid form and common mistakes, with a\nworked example to adapt.\n\n## Step 3 — Choose the form\n\nRun `python3 \u003Cskill-dir>\u002Fscripts\u002Fdetect_client.py`. It prints\n`{client, mermaid, remote_viewer, obsidian_vault, reason}`. What each client\ndisplays, with sources and a verified date, is in\n`references\u002Fclient-matrix.md`.\n\n\u003C!-- gate: loom-visualization.mermaid-only-when-confirmed -->\nUse Mermaid only when you have no shell and your own host is claude.ai or the\nClaude Desktop chat, where Mermaid is reported to render. If you can run the\nclient check at all, you have a shell, so do not use Mermaid. Everywhere else\nthe reply gets a markdown table, which every client in the matrix renders.\nA drawn ASCII diagram goes in a fenced code block when the shape itself is\nthe information, or when the answer is bound for a plain-text destination.\nA wrong Mermaid choice shows the user raw source; a markdown table reads\neverywhere.\n\u003C!-- \u002Fgate -->\n\nWhich of the two forms to send:\n\n- Shaped content in a chat reply gets a markdown table by default; the drawn\n  form is for a destination that does not render markdown, such as a code\n  comment, a commit message or a plain-text file.\n- Option comparison always uses a GFM markdown table, in every client. Use the\n  ASCII table generator only when the answer goes into a code block or a\n  plain-text destination.\n- Data model and quantity need only the markdown table.\n- A flow, a branch, a reasoning chain, a state machine, a sequence, a\n  hierarchy, an architecture, a timeline, task dependencies or a cross-role\n  workflow may still be drawn in the reply\n  when a table would lose what the reader needs: there the shape is the\n  information. Draw it, verify it, and keep a table beside it when exact\n  values matter.\n- The client never decides between the two. `remote_viewer` and the client\n  name tell you whether Mermaid is safe, and nothing more.\n\n## Step 4 — Generate and verify the ASCII\n\nWhere the template names a generator, generate; do not hand-pad:\n\n```\nprintf '%s' '\u003Cjson input from the template>' | python3 \u003Cskill-dir>\u002Fscripts\u002Fgenerate.py \u003Cshape>\n```\n\nShapes: `table`, `flow`, `seq`, `tree`, `arch`, `bar`. Pass the JSON as the\n`printf '%s'` argument so a `\\n` inside a label reaches the script as a line\nbreak request rather than a raw newline. `seq` and `bar` labels must be\nsingle-line.\n\nWhere there is no generator (branching decision, reasoning chain, state\nlifecycle, timeline, task dependencies, cross-role workflow), adapt the\ntemplate's ASCII by hand. The data model has\nno ASCII form; use its table substitute.\n\nFor how a node's text is structured and verified, see\n`references\u002Fnode-structure.md`.\n\nAlways verify before sending:\n\n```\nprintf '%s' '\u003Cyour diagram>' | python3 \u003Cskill-dir>\u002Fscripts\u002Falign.py -\n```\n\nIt prints a per-line width report, then either `line N: col C: message` for\neach drift or `✓ no drift`, exiting 0 when clean and 1 on drift. Fix only the\nflagged lines and rerun until it is clean. The checks it runs are the vertical\nseam (`scripts\u002Fchecks_seam.py`), table equal width\n(`scripts\u002Fchecks_table.py`), kink plus arrowhead landing\n(`scripts\u002Fchecks_kink.py`) and node structure (`scripts\u002Fchecks_nodes.py`). The\none exception is `seq` output: it is correct\nby construction, its blank off-span lifelines sit outside the seam model, and\nit is sent unedited.\n\nWidth rules the checks depend on:\n\n- Chinese and Japanese characters take two cells; the scripts measure this,\n  so never count characters by eye.\n- Keep emoji and pictographic symbols out of box labels and table cells.\n  Their width differs between terminals, so no check can make them align.\n- Keep ambiguous-width symbols (`→`, `★`, `·`, `°`, Greek letters) out of\n  the column that sets a box's width. Use the generators' arrows (`▼ ▲ ► ◄`).\n\n## Page mode\n\nPage mode turns reasoning that already exists (in a document, a folder, or\nthis conversation) into one self-contained HTML page whose core is a\nchain-of-thought Mermaid diagram. It is for how a conclusion was reached, not\nfor what a function does, and not for doing the thinking itself. The page is\na file the user opens, so the chat client check does not apply to it.\n\nRead `references\u002Fpage-mode.md` in full before starting. It holds the whole\nprocedure: resolve the source, extract the chain before drawing, build the\ndiagram to `references\u002Fmermaid-cot-spec.md`, write the markdown from\n`assets\u002Fcot-report-template.md`, convert and verify, then run the fidelity\ncheck in `references\u002Ffidelity-check.md` before the page is shared.\n\nAsk once whether the user wants an Artifact; do not publish unprompted, and\nnever publish before the fidelity check passes.\n\n## Failure modes to refuse\n\n- **Prose for a shaped answer.** Three options described in paragraphs make\n  the reader build the table themselves.\n- **Mermaid \"because it looks better\".** Outside a confirmed client the user\n  sees raw source. The client check decides, not taste.\n- **Hand-padded CJK boxes sent without `scripts\u002Falign.py`.** Eyeballed widths\n  break on the first full-width character.\n- **Editing generator output by hand.** Change the JSON input and regenerate.\n- **A diagram for a trivial answer.** Two steps or one fact is a sentence.\n- **Reading every template \"to be safe\".** Read the one the shape names.\n- **Writing a vault note.** Decline and name\n  `obsidian:obsidian-mermaid-visualizer`.\n- **A page drawn without reading the source, or padded to reach five nodes.**\n  Page mode's extraction is the work; three reasoning states get prose.\n- **Unstructured multi-line box.** A box interior with multiple content lines\n  and no separator row — the node structure was skipped.\n- **Empty separator.** A separator row with no body line after it — the\n  container rule was violated.\n","# Loom Visualization\n\nDeliver local documents with actual absolute paths from the active worktree or\nexternal location, including in copyable instructions. For known local Markdown\nsupport, use the document's project-relative path as link text (external files:\nbasename) and absolute targets; otherwise show full absolute paths. Enclose\ntargets with spaces in angle brackets: `[doc.md](\u003C\u002Fworktree name\u002Fdoc.md>)`. Preserve bundled references, stored\nrelative paths, quoted examples and incidental filenames.\n\nPick the right shape and form for information in a coding-harness\nconversation, so the reader gets a table or a diagram that actually displays\nin their client instead of prose or broken Mermaid source.\n\n`\u003Cskill-dir>` is this skill's folder: `${CLAUDE_SKILL_DIR}` on Claude Code;\non any other host, the directory that holds this SKILL.md. Run every script\nas `python3 \u003Cskill-dir>\u002Fscripts\u002F\u003Cname>.py`; all other paths below are\nrelative to `\u003Cskill-dir>`. The scripts need only the Python standard library.\n\nA one-line fact needs no table. Reach for this skill when the answer has a\nshape: options side by side, three or more steps, a branch, a lifecycle, a\nmessage exchange, a structure, dates, or numbers to compare.\n\n## Boundary\n\n\u003C!-- gate: loom-visualization.obsidian-boundary -->\nWhen the output is written to a file, first run\n`python3 \u003Cskill-dir>\u002Fscripts\u002Fdetect_client.py --target \u003Cpath>`. Decline only when that\n`--target` check reports `obsidian_vault: true`, or when the user asks for a\nnote in their Obsidian vault: say this skill serves coding-harness chat, and\nname `obsidian:obsidian-mermaid-visualizer` as the skill for vault notes.\nA chat answer proceeds normally even when the working directory is inside an\nObsidian vault. Never\nput Obsidian-only syntax (wikilinks, callouts, `%%` comment lines) into\nanything this skill produces.\n\u003C!-- \u002Fgate -->\n\nAlso out of scope: diagram rules for commit messages, pull requests and\nrepository documents. Those follow the rules of the skill that owns the\nartifact (`loom-workflow:git-memory`, `loom-code:ship`,\n`loom-design:write-spec`).\n\nDocumented reasoning turned into a standalone page is page mode, below.\n\n## Plain language and conversation tables\n\nThese references sit beside the data-shape templates; the templates in\nStep 1 stay as they are.\n\n| Need | Read |\n|---|---|\n| A plainer explanation, a decision question, or a table for a conversation situation (decision, before and after, progress, checklist, confirmed and unconfirmed, findings, risks, support matrix) | `references\u002Fplain-language.md` |\n| A software document: incident postmortem or incident report, test plan, traceability or compatibility matrix, migration guide, API parameters, runbook, RACI, ADR or RFC options, technology selection, feature-flag rollout, release notes, risk register, RAID log, threat model (STRIDE), decision table, state-transition table, truth table, morphological box, risk matrix, feature table, confusion matrix, correlation matrix | `references\u002Ftables-software.md` |\n| A design document: heuristic evaluation, usability test report, content audit, design critique, design tokens, component states, accessibility audit, journey map, personas or JTBD, design decision log | `references\u002Ftables-design.md` |\n| A business document: weighted or Pugh matrix, RICE, ICE, MoSCoW or WSJF, SWOT or TOWS, competitive analysis, Five Forces, stakeholder analysis, scenario planning, business case, OKR, assumption log, go\u002Fno-go, pricing tiers, Kano, decisional balance sheet, roadmap, 2×2 quadrants | `references\u002Ftables-business.md` |\n\nRead only the one file whose row matches; a conversation-situation reply never opens a domain file.\n\n## Step 1 — Classify the information shape\n\nName the one shape the information has. If it has two, draw the one the\nreader must act on, and state the other in a sentence.\n\n| Shape | Signals | Template | Generator |\n|---|---|---|---|\n| Option comparison | 2+ options, shared criteria | `templates\u002F01-option-comparison.md` | `table` |\n| Linear steps | 3+ steps, fixed order, no branch; before\u002Fafter flows in titled panels | `templates\u002F02-linear-steps.md` | `flow` |\n| Branching decision | a question sends work down different paths | `templates\u002F03-branching-decision.md` | none |\n| Reasoning chain | causes or inferences leading to a conclusion | `templates\u002F04-reasoning-chain.md` | none |\n| State lifecycle | named states changed by named events | `templates\u002F05-state-lifecycle.md` | none |\n| Actor sequence | actors exchanging messages in time order | `templates\u002F06-actor-sequence.md` | `seq` |\n| Task dependencies | parallel prerequisites feeding a required join | `templates\u002F12-task-dependencies.md` | none |\n| Cross-role workflow | steps with different work ownership and handoffs | `templates\u002F13-cross-role-workflow.md` | none |\n| Hierarchy | parent-child, no cross-links | `templates\u002F07-hierarchy.md` | `tree` |\n| System architecture | components in layers with dependencies | `templates\u002F08-system-architecture.md` | `arch` |\n| Data model | entities, fields, cardinality | `templates\u002F09-data-model.md` | none (table substitute) |\n| Timeline | events on dates or periods | `templates\u002F10-timeline.md` | none |\n| Quantity | a few labelled numbers to compare | `templates\u002F11-quantity.md` | `bar` |\n\n## Step 2 — Read only that template\n\nRead the one template file from Step 1, and no other. Each template gives the\nshape's table form, ASCII form, Mermaid form and common mistakes, with a\nworked example to adapt.\n\n## Step 3 — Choose the form\n\nRun `python3 \u003Cskill-dir>\u002Fscripts\u002Fdetect_client.py`. It prints\n`{client, mermaid, remote_viewer, obsidian_vault, reason}`. What each client\ndisplays, with sources and a verified date, is in\n`references\u002Fclient-matrix.md`.\n\n\u003C!-- gate: loom-visualization.mermaid-only-when-confirmed -->\nUse Mermaid only when you have no shell and your own host is claude.ai or the\nClaude Desktop chat, where Mermaid is reported to render. If you can run the\nclient check at all, you have a shell, so do not use Mermaid. Everywhere else\nthe reply gets a markdown table, which every client in the matrix renders.\nA drawn ASCII diagram goes in a fenced code block when the shape itself is\nthe information, or when the answer is bound for a plain-text destination.\nA wrong Mermaid choice shows the user raw source; a markdown table reads\neverywhere.\n\u003C!-- \u002Fgate -->\n\nWhich of the two forms to send:\n\n- Shaped content in a chat reply gets a markdown table by default; the drawn\n  form is for a destination that does not render markdown, such as a code\n  comment, a commit message or a plain-text file.\n- Option comparison always uses a GFM markdown table, in every client. Use the\n  ASCII table generator only when the answer goes into a code block or a\n  plain-text destination.\n- Data model and quantity need only the markdown table.\n- A flow, a branch, a reasoning chain, a state machine, a sequence, a\n  hierarchy, an architecture, a timeline, task dependencies or a cross-role\n  workflow may still be drawn in the reply\n  when a table would lose what the reader needs: there the shape is the\n  information. Draw it, verify it, and keep a table beside it when exact\n  values matter.\n- The client never decides between the two. `remote_viewer` and the client\n  name tell you whether Mermaid is safe, and nothing more.\n\n## Step 4 — Generate and verify the ASCII\n\nWhere the template names a generator, generate; do not hand-pad:\n\n```\nprintf '%s' '\u003Cjson input from the template>' | python3 \u003Cskill-dir>\u002Fscripts\u002Fgenerate.py \u003Cshape>\n```\n\nShapes: `table`, `flow`, `seq`, `tree`, `arch`, `bar`. Pass the JSON as the\n`printf '%s'` argument so a `\\n` inside a label reaches the script as a line\nbreak request rather than a raw newline. `seq` and `bar` labels must be\nsingle-line.\n\nWhere there is no generator (branching decision, reasoning chain, state\nlifecycle, timeline, task dependencies, cross-role workflow), adapt the\ntemplate's ASCII by hand. The data model has\nno ASCII form; use its table substitute.\n\nFor how a node's text is structured and verified, see\n`references\u002Fnode-structure.md`.\n\nAlways verify before sending:\n\n```\nprintf '%s' '\u003Cyour diagram>' | python3 \u003Cskill-dir>\u002Fscripts\u002Falign.py -\n```\n\nIt prints a per-line width report, then either `line N: col C: message` for\neach drift or `✓ no drift`, exiting 0 when clean and 1 on drift. Fix only the\nflagged lines and rerun until it is clean. The checks it runs are the vertical\nseam (`scripts\u002Fchecks_seam.py`), table equal width\n(`scripts\u002Fchecks_table.py`), kink plus arrowhead landing\n(`scripts\u002Fchecks_kink.py`) and node structure (`scripts\u002Fchecks_nodes.py`). The\none exception is `seq` output: it is correct\nby construction, its blank off-span lifelines sit outside the seam model, and\nit is sent unedited.\n\nWidth rules the checks depend on:\n\n- Chinese and Japanese characters take two cells; the scripts measure this,\n  so never count characters by eye.\n- Keep emoji and pictographic symbols out of box labels and table cells.\n  Their width differs between terminals, so no check can make them align.\n- Keep ambiguous-width symbols (`→`, `★`, `·`, `°`, Greek letters) out of\n  the column that sets a box's width. Use the generators' arrows (`▼ ▲ ► ◄`).\n\n## Page mode\n\nPage mode turns reasoning that already exists (in a document, a folder, or\nthis conversation) into one self-contained HTML page whose core is a\nchain-of-thought Mermaid diagram. It is for how a conclusion was reached, not\nfor what a function does, and not for doing the thinking itself. The page is\na file the user opens, so the chat client check does not apply to it.\n\nRead `references\u002Fpage-mode.md` in full before starting. It holds the whole\nprocedure: resolve the source, extract the chain before drawing, build the\ndiagram to `references\u002Fmermaid-cot-spec.md`, write the markdown from\n`assets\u002Fcot-report-template.md`, convert and verify, then run the fidelity\ncheck in `references\u002Ffidelity-check.md` before the page is shared.\n\nAsk once whether the user wants an Artifact; do not publish unprompted, and\nnever publish before the fidelity check passes.\n\n## Failure modes to refuse\n\n- **Prose for a shaped answer.** Three options described in paragraphs make\n  the reader build the table themselves.\n- **Mermaid \"because it looks better\".** Outside a confirmed client the user\n  sees raw source. The client check decides, not taste.\n- **Hand-padded CJK boxes sent without `scripts\u002Falign.py`.** Eyeballed widths\n  break on the first full-width character.\n- **Editing generator output by hand.** Change the JSON input and regenerate.\n- **A diagram for a trivial answer.** Two steps or one fact is a sentence.\n- **Reading every template \"to be safe\".** Read the one the shape names.\n- **Writing a vault note.** Decline and name\n  `obsidian:obsidian-mermaid-visualizer`.\n- **A page drawn without reading the source, or padded to reach five nodes.**\n  Page mode's extraction is the work; three reasoning states get prose.\n- **Unstructured multi-line box.** A box interior with multiple content lines\n  and no separator row — the node structure was skipped.\n- **Empty separator.** A separator row with no body line after it — the\n  container rule was violated.\n",{"name":5,"description":7},"main","3b1a9972644517911454530dc1876f88525b1f37","loom-workflow\u002Fskills\u002Floom-visualization","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins","https:\u002F\u002Fgithub.com\u002Fkouko","2026-11-15 00:45:02",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add kouko\u002Floom-plugins --skill loom-visualization",{"tool":35,"command":36},"bunx","bunx skills add kouko\u002Floom-plugins --skill loom-visualization",{"tool":38,"command":39},"pnpm","pnpm dlx skills add kouko\u002Floom-plugins --skill loom-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002FSKILL.md",true,[43,49,53,57,63,67,71,75,79,83,87,91,95,99,103,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217,221],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"assets\u002Fcot-report-template.md","ASSET","资产文件",4635,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fassets\u002Fcot-report-template.md",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"assets\u002Ftrigger-card-coexist.md",1283,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fassets\u002Ftrigger-card-coexist.md",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Ftrigger-card.md",1190,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fassets\u002Ftrigger-card.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"NOTICE.md","REFERENCE","参考文档",2359,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002FNOTICE.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"README.md",1825,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002FREADME.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fclient-matrix.md",3112,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Fclient-matrix.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Ffidelity-check.md",6142,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Ffidelity-check.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fmermaid-cot-spec.md",18650,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Fmermaid-cot-spec.md",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fnode-structure.md",2754,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Fnode-structure.md",{"path":84,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fpage-mode.md",19341,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Fpage-mode.md",{"path":88,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fplain-language.md",23418,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Fplain-language.md",{"path":92,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Ftables-business.md",17179,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Ftables-business.md",{"path":96,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Ftables-design.md",10744,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Ftables-design.md",{"path":100,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Ftables-software.md",23261,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Freferences\u002Ftables-software.md",{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Falign.py","SCRIPT","脚本",2915,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Falign.py",{"path":110,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fchecks_kink.py",6792,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fchecks_kink.py",{"path":114,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fchecks_nodes.py",7890,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fchecks_nodes.py",{"path":118,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Fchecks_seam.py",2427,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fchecks_seam.py",{"path":122,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":123,"sourceHtmlUrl":124},"scripts\u002Fchecks_table.py",4737,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fchecks_table.py",{"path":126,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":127,"sourceHtmlUrl":128},"scripts\u002Fdetect_client.py",2770,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fdetect_client.py",{"path":130,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":131,"sourceHtmlUrl":132},"scripts\u002Fgen_arch.py",11604,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_arch.py",{"path":134,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":135,"sourceHtmlUrl":136},"scripts\u002Fgen_bar.py",1598,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_bar.py",{"path":138,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":139,"sourceHtmlUrl":140},"scripts\u002Fgen_flow.py",7568,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_flow.py",{"path":142,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":143,"sourceHtmlUrl":144},"scripts\u002Fgen_seq.py",9898,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_seq.py",{"path":146,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":147,"sourceHtmlUrl":148},"scripts\u002Fgen_table.py",2573,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_table.py",{"path":150,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":151,"sourceHtmlUrl":152},"scripts\u002Fgen_tree.py",3302,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgen_tree.py",{"path":154,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":155,"sourceHtmlUrl":156},"scripts\u002Fgenerate.py",2875,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fgenerate.py",{"path":158,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":159,"sourceHtmlUrl":160},"scripts\u002Fglyphs.py",1065,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fglyphs.py",{"path":162,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":163,"sourceHtmlUrl":164},"scripts\u002Frender_cot_html.py",44961,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Frender_cot_html.py",{"path":166,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002Fverify_cot_html.py",42730,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fverify_cot_html.py",{"path":170,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Fwidth.py",8815,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Fscripts\u002Fwidth.py",{"path":174,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":175,"sourceHtmlUrl":176},"templates\u002F01-option-comparison.md",2509,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F01-option-comparison.md",{"path":178,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":179,"sourceHtmlUrl":180},"templates\u002F02-linear-steps.md",7680,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F02-linear-steps.md",{"path":182,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":183,"sourceHtmlUrl":184},"templates\u002F03-branching-decision.md",2411,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F03-branching-decision.md",{"path":186,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":187,"sourceHtmlUrl":188},"templates\u002F04-reasoning-chain.md",3946,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F04-reasoning-chain.md",{"path":190,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":191,"sourceHtmlUrl":192},"templates\u002F05-state-lifecycle.md",3092,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F05-state-lifecycle.md",{"path":194,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":195,"sourceHtmlUrl":196},"templates\u002F06-actor-sequence.md",2219,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F06-actor-sequence.md",{"path":198,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":199,"sourceHtmlUrl":200},"templates\u002F07-hierarchy.md",1607,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F07-hierarchy.md",{"path":202,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":203,"sourceHtmlUrl":204},"templates\u002F08-system-architecture.md",3311,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F08-system-architecture.md",{"path":206,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":207,"sourceHtmlUrl":208},"templates\u002F09-data-model.md",1635,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F09-data-model.md",{"path":210,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":211,"sourceHtmlUrl":212},"templates\u002F10-timeline.md",1393,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F10-timeline.md",{"path":214,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":215,"sourceHtmlUrl":216},"templates\u002F11-quantity.md",1233,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F11-quantity.md",{"path":218,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":219,"sourceHtmlUrl":220},"templates\u002F12-task-dependencies.md",1909,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F12-task-dependencies.md",{"path":222,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":223,"sourceHtmlUrl":224},"templates\u002F13-cross-role-workflow.md",1977,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002Ftemplates\u002F13-cross-role-workflow.md",[226,233,240,247,254,261],{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":232,"publishedAt":18},"01M7CQNVD2W5MP7PKX3MD0YSQE","using-loom-workflow","Route broad Loom workflow-tool requests to the right skill. Use when the request spans tools or the right workflow skill is unclear.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fusing-loom-workflow\u002FSKILL.md",[],[],{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":239,"publishedAt":18},"01M7CQNNTPVG52CS2C6Q9HJ2E2","skill-retro","Review selected past or current Claude Code or Codex sessions against readable target skill sources and related integration. Produce source-linked proposals without applying changes.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fskill-retro\u002FSKILL.md",[],[],{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":244,"categories":245,"keywords":246,"publishedAt":18},"01M7CQNHR1BDKJ63CC4R1RY9GE","recap-state","Give an in-session recap of current progress for 'where were we', '我們剛剛在幹嘛', '剛剛講到哪', '我跟丟了', 'ちょっと振り返って', '今どこだっけ', or '振り返り'. The built-in \u002Frecap is an away-summary.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Frecap-state\u002FSKILL.md",[],[],{"skillNo":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":251,"categories":252,"keywords":253,"publishedAt":18},"01M7CQNE1A9272WPRE1MM3JRFK","project-retro","Review one current or specified coding session for source-backed project\ndevelopment improvements. Use for a requested retrospective, including\n振り返り seeking improvements; not for current-progress recaps or recurring skill mining.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fproject-retro\u002FSKILL.md",[],[],{"skillNo":255,"name":256,"nameZh":6,"description":257,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":258,"categories":259,"keywords":260,"publishedAt":18},"01M7CQN7TVS0XF44JXQBWA32Z1","loom-memory","Record repo-wide lessons when saving to your own memory or asked to remember; recall, reconcile, or forget them when a task needs it.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-memory\u002FSKILL.md",[],[],{"skillNo":262,"name":263,"nameZh":6,"description":264,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":265,"categories":266,"keywords":267,"publishedAt":18},"01M7CQN2BA49P4WJY08DCX7BAH","loom-interactive-diagram","Create and check editable diagrams during standalone or Loom work. Use when the agent needs to create a diagram for the user to edit in an external editor or read back saved changes; draw.io is the default format.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-interactive-diagram\u002FSKILL.md",[],[]]