llm-wiki/.automation/discord-link-ingest/interest-profile.md

Discord Link Ingest Interest Profile

Updated: 2026-06-30 Source: discrawl read-only analysis of Yuta/toymaker Discord messages.

Author IDs considered

• 890593691440398456 — yuta, historical messages through 2025-03-24
• 890908900520505354 — toymaker, current identity through 2026-06-28

Evidence snapshot

• Total messages by these identities in archive: 42,677
• URL-containing messages: 13,169
• Top channels by message volume: 💭｜yuta, chat, notes
• Recent URL domains are heavily technical/source-oriented: github.com, x.com, github.blog, zenn.dev, openai.com, blog.cloudflare.com, docs.litellm.ai, scrapbox.io, obsidian.md, hermes-agent.nousresearch.com, alphaxiv.org.
• Keyword signals: AI/LLM, X/Twitter, development/code, workflow automation, wiki/knowledge management, agents/Hermes.

Current scoring bias

Start strict. The wiki should remain curated; raw sources are acceptable, but wiki-page upgrades should require durable reuse value.

Score 4 — create/update substantial wiki pages

Use for sources that are central to one of these durable themes:

• LLM Wiki / compiled knowledge bases / Obsidian / knowledge management systems
• AI agents, Hermes Agent, Codex/Claude/OpenCode-style automation, multi-agent workflows
• Developer tooling that changes Yuta's automation/dev workflow materially
• Quality engineering, security, supply-chain, infra reliability for AI/software systems
• Technical writeups with implementation details likely to be referenced later
• Loop-engineering style agent operations: discovery, handoff, independent verification, persistence, scheduling, evaluator separation, and state/log design for autonomous jobs
• Framework-level workflow orchestration for agents: typed graph execution, reusable node/tool/agent primitives, durable pause/resume, human-in-the-loop interrupts, retry/concurrency controls, branch/session isolation, and telemetry that makes loops observable and replayable
• AI-agent operator observability and control surfaces: monitoring multiple coding agents, local process/port/session visibility, rate-limit/context tracking, approval flows, and mobile/terminal dashboards for agent operations
• Minimal, observable agent harnesses that expose context/session/tool/process state clearly, especially when they document trade-offs around provider abstraction, terminal/tmux workflows, sub-agents, MCP, permissions, or worktree-based isolation
• Agent-oriented CLI/tool design that reduces model guesswork with CLI-owned usage guides, JSON-first output, actionable errors, search/read separation, stale-state metadata, safe defaults, few flags, discoverable command trees, job controls, and bundled agent skills
• Implementation-derived quality metrics that turn test traces, routes, APIs/RPCs, coverage denominators, evaluator outputs, or runtime evidence into durable feedback loops for development and release decisions
• Code-to-knowledge and code-to-documentation systems that generate repo Wikis, C4 architecture views, diagrams, or durable onboarding material from source code, especially when they address documentation drift, agent instruction-file integration, scheduled diff-based updates, traceability, and review workflows
• Agent identity/security standards and operational controls, especially MCP authorization, Cross App Access/XAA, least privilege, audit logs, command-execution guards, sandbox/approval boundaries, and supply-chain risks around agents
• Package supply-chain incidents that explicitly affect AI coding tools, developer credential stores, CI/CD secrets, or agent configuration files; score high when the incident links package execution to agent persistence, credential theft, or cross-ecosystem self-propagation
• Browser-agent harnesses with concrete tool surfaces: DOM/network/console/screenshot/page-interaction access, local browser MCP servers, tab/session boundaries, performance checks, and accessibility checks that make UI debugging verifiable by agents
• Human-gated AI security workflows that reduce maintainer burden: vulnerability discovery, verification, patch drafting, responsible disclosure, release monitoring, and false-positive suppression before any report leaves the operator's workspace
• Niche, exciting design/hack/Hacker News-like material, especially when it exposes an unusual technique, tool, interface, or way of thinking
• Public-interest/public-sector technology, civic infrastructure, accessibility (a11y), inclusive design, and systems that make services more usable or equitable
• Papers or research with clear relevance to LLMs, agents, evaluation, knowledge systems, automation, accessibility, or public-interest technology

Score 3 — update existing page only

Use when the source adds a concrete fact, method, comparison, or implementation note to an existing page, but does not deserve a new page.

Score 2 — raw/articles only

Use for interesting but not-yet-connected sources:

• good one-off articles
• news with possible future relevance
• tools/repos worth remembering but not yet central
• X/Twitter links only when they point to durable technical content or a thread with reusable insight

Score 1 — state/link-only

Use for URLs whose title/context is notable but body extraction fails or value is unclear.

Score 0 — skip

• ads/campaigns
• memes/ephemeral posts
• shallow news with no later reuse value
• duplicate URLs
• login-only pages where no useful content is extractable
• media-only links unless explicitly tied to a technical/knowledge workflow

Per-domain handling hints

• github.com: prioritize repos, READMEs, issues/PRs, commits related to automation, agents, LLMs, dev infra, security, QE. Skip personal one-off commits unless message context says they matter.
• x.com: do not auto-upgrade by default. Use only for high-signal technical threads or links to durable sources.
• zenn.dev, github.blog, openai.com, blog.cloudflare.com, technical docs/blogs: usually score 2+, score 3/4 if aligned with above themes.
• newspapers/general news: usually score 0-2 unless strongly connected to cyber/security/AI policy or a durable thesis.
• YouTube: usually link-only unless transcript/title/context indicates durable technical value.

Style notes

• Prefer natural Japanese prose. Avoid unnecessary katakana and English jargon when a clear Japanese term works.
• Do not force every source into an LLM Wiki framing. Public-interest, design, accessibility, information integrity, and hack/design topics can stand on their own when that is the natural framing.

Learning rule

After each run, if repeated keep/skip decisions reveal a stable preference, append one compact note here or to state.md. Prefer explicit evidence from Discord messages over assumptions from short Hermes conversations.