{"slug":"minutes-graph-5","title":"minutes-graph","summary":"Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-08-27T16:57:59.991311Z","repo":{"url":"https://github.com/silverstein/minutes","stars":1501,"forks":165,"license":"MIT","updatedAt":"2026-09-25T06:14:41Z"},"bodyHtml":"<hr>\n<h2>name: minutes-graph\ndescription: Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.\nuser_invocable: true</h2>\n<h1>/minutes-graph</h1>\n<p>Minutes builds relationship rankings, exact person profiles, and commitments from one supervised, process-private SQLite projection of stable policy-authorized Markdown plus confirmed identity corrections. One ordered snapshot authority spans corpus and corrections, and the worker is hard-limited for memory, output, and wall time. Topic research uses the separately bounded live-source search boundary. Both paths re-attest policy before returning facts. Do not fall back to a retired durable index or read meeting files directly.</p>\n<h2>Privacy boundary</h2>\n<ul>\n<li>Never walk meeting files, parse frontmatter yourself, or read raw transcripts for this skill.</li>\n<li>Never run <code>graph_build.py</code> or read <code>~/.minutes/graph/index.json</code>; those are retired legacy surfaces.</li>\n<li>Never create a replacement graph cache, spreadsheet, JSON file, or database.</li>\n<li>Never pass <code>--include-restricted</code>. Restricted meetings are intentionally absent from this agent-facing skill.</li>\n<li>Treat any authorization, resource-budget, correction-race, or projection error as a hard stop. Do not fall back to filesystem reads.</li>\n</ul>\n<h2>Available commands</h2>\n<ul>\n<li><code>minutes people --json</code> — bounded relationship rankings and losing-touch signals.</li>\n<li><code>minutes commitments --json</code> — bounded graph commitments.</li>\n<li><code>minutes people merge &lt;canonical&gt; &lt;alias...&gt;</code> — confirm an identity correction in the local vocabulary; uncertain names are never merged automatically.</li>\n<li><code>minutes person \"&lt;name&gt;\"</code> — bounded person profile.</li>\n<li><code>minutes research \"&lt;topic&gt;\"</code> — bounded topic research.</li>\n</ul>\n<h2>Workflow</h2>\n<ol>\n<li>Classify the request and use the narrowest command above.</li>\n<li>Require exit status 0. Use only the bounded native result and never substitute filesystem reads.</li>\n<li>For a proposed alias, show the suggestion and ask for confirmation before running <code>minutes people merge</code>; a wrong merge is worse than no merge.</li>\n<li>Do not imply that restricted history or a relationship fact is absent when any command fails.</li>\n</ol>\n<h2>Output</h2>\n<p>Return only the bounded native result. Never invent rankings, commitments, or relationship signals from raw files.</p>\n<h2>Gotchas</h2>\n<ul>\n<li>A failed person profile cannot be interpreted as “never met.” Report the source unavailable.</li>\n<li>Do not imply that a later sensitivity change proves a historical fact absent; report only the current authorized projection.</li>\n<li>Alias suggestions are evidence, not permission to rewrite identity. Require explicit confirmation before merging.</li>\n<li>Use <code>minutes research \"&lt;topic&gt;\"</code> for bounded company, product, or topic research. If it fails, report the source unavailable; never fall back to raw corpus reads.</li>\n</ul>\n","files":[{"path":"SKILL.md","sizeBytes":2857,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-08-27T17:02:40.015114Z","sha256":"217131D50137F357E47545E8595C0B9304AAF7F9B66AD2F67A2B56E1540DCBE1","sizeBytes":1394},"review":null,"source":{"repositoryUrl":"https://github.com/silverstein/minutes","path":"tooling/skills/goldens/claude/minutes-graph","license":"MIT","commit":"37d3440d4f132e2f3864fbe537e375fd546159ba","subtreeSha":"6693D5151808E201ACA2359B5EFEC162F9AD7275F6F5E367E23BA5CBD614BCC8","lastSyncedAt":"2026-09-25T07:37:08.19899Z"},"reviewedAt":"2026-08-27T17:13:41.823164Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/silverstein/minutes/tree/main/tooling/skills/goldens/claude/minutes-graph"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install silverstein-minutes@llmmart"},{"target":"git","command":"git clone https://github.com/silverstein/minutes.git"}]}