[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASE4YCPF85PMB8YJ4AP2YY":3,"skill-same:01M7ASE4YCPF85PMB8YJ4AP2YY":51},{"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":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ASE4YCPF85PMB8YJ4AP2YY","codex-history-ingest",null,"Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Codex sessions for knowledge, import their ~\u002F.codex folder, extract insights from previous coding sessions, or says things like \"process my Codex history\", \"add my Codex conversations to the wiki\", or \"what have I discussed in Codex before\". Also triggers when the user mentions .codex sessions, rollout files, session_index.jsonl, or Codex transcript logs.","saski\u002Farnesto","saski","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140356?v=4","01M7ASBDSNXTRYDYB4K1PEA1RV","01M7ASBDTAKBDAAV99S1GE7HK6",6,"Unlicense","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodex-history-ingest\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codex-history-ingest\ndescription: >\n  Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine\n  their past Codex sessions for knowledge, import their ~\u002F.codex folder, extract insights from previous coding\n  sessions, or says things like \"process my Codex history\", \"add my Codex conversations to the wiki\", or\n  \"what have I discussed in Codex before\". Also triggers when the user mentions .codex sessions, rollout files,\n  session_index.jsonl, or Codex transcript logs.\n---\n\n# Codex History Ingest — Conversation Mining\n\nYou are extracting knowledge from the user's past Codex sessions and distilling it into the Obsidian wiki. Session logs are rich but noisy: focus on durable knowledge, not operational telemetry.\n\nThis skill can be invoked directly or via the `wiki-history-ingest` router (`\u002Fwiki-history-ingest codex`).\n\n## Before You Start\n\n1. Read `.env` to get `OBSIDIAN_VAULT_PATH` and `CODEX_HISTORY_PATH` (default to `~\u002F.codex` if unset)\n2. Read `.manifest.json` at the vault root to check what has already been ingested\n3. Read `index.md` at the vault root to understand what the wiki already contains\n\n## Ingest Modes\n\n### Append Mode (default)\n\nCheck `.manifest.json` for each source file. Only process:\n\n- Files not in the manifest (new session rollouts, new index files)\n- Files whose modification time is newer than `ingested_at` in the manifest\n\nUse this mode for regular syncs.\n\n### Full Mode\n\nProcess everything regardless of manifest. Use after `wiki-rebuild` or if the user explicitly asks for a full re-ingest.\n\n## Codex Data Layout\n\nCodex stores local artifacts under `~\u002F.codex\u002F`.\n\n```\n~\u002F.codex\u002F\n├── sessions\u002F                          # Session rollout logs by date\n│   └── YYYY\u002FMM\u002FDD\u002F\n│       └── rollout-\u003Ctimestamp>-\u003Cid>.jsonl\n├── archived_sessions\u002F                 # Archived rollout logs\n├── session_index.jsonl                # Lightweight index of thread id\u002Fname\u002Fupdated_at\n├── history.jsonl                      # Local transcript history (if persistence enabled)\n├── config.toml                        # User config (contains history settings)\n└── state_*.sqlite \u002F logs_*.sqlite     # Runtime DBs (usually skip)\n```\n\n### Key data sources ranked by value\n\n1. `session_index.jsonl` — best inventory source for IDs, titles, and freshness\n2. `sessions\u002F**\u002Frollout-*.jsonl` — rich structured transcript events\n3. `history.jsonl` — useful fallback\u002Ftimeline aid if enabled\n\nAvoid ingesting SQLite internals unless the user explicitly asks.\n\n## Step 1: Survey and Compute Delta\n\nScan `CODEX_HISTORY_PATH` and compare against `.manifest.json`:\n\n- `~\u002F.codex\u002Fsession_index.jsonl`\n- `~\u002F.codex\u002Fsessions\u002F**\u002Frollout-*.jsonl`\n- `~\u002F.codex\u002Farchived_sessions\u002F**` (optional; only if user asks for archived history)\n- `~\u002F.codex\u002Fhistory.jsonl` (optional fallback)\n\nClassify each file:\n\n- **New** — not in manifest\n- **Modified** — in manifest but file is newer than `ingested_at`\n- **Unchanged** — already ingested and unchanged\n\nReport a concise delta summary before deep parsing.\n\n## Step 2: Parse Session Index First\n\n`session_index.jsonl` typically has entries like:\n\n```json\n{\"id\":\"...\",\"thread_name\":\"...\",\"updated_at\":\"...\"}\n```\n\nUse it to:\n\n- Build a canonical session inventory\n- Prioritize recent\u002Fhigh-signal sessions\n- Map rollout IDs to human-readable thread names\n\n## Step 3: Parse Rollout JSONL Safely\n\nEach `rollout-*.jsonl` line is an event envelope with:\n\n```json\n{\n  \"timestamp\": \"...\",\n  \"type\": \"session_meta|turn_context|event_msg|response_item\",\n  \"payload\": { ... }\n}\n```\n\n### Extraction rules\n\n- Prioritize user intent and assistant-visible outputs\n- Favor `response_item` records with user\u002Fassistant message content\n- Use `event_msg` selectively for meaningful milestones; ignore pure telemetry\n- Treat `session_meta` as metadata (cwd, model, ids), not user knowledge\n\n### Skip\u002Fnoise filters\n\n- Token accounting events\n- Tool plumbing with no semantic content\n- Raw command output unless it contains reusable decisions\u002Fpatterns\n- Repeated plan snapshots unless they add novel decisions\n\n### Critical privacy filter\n\nRollout logs can include injected instructions, tool payloads, and sensitive text. Do not ingest verbatim system\u002Fdeveloper prompts or secrets.\n\n- Remove API keys, tokens, passwords, credentials\n- Redact private identifiers unless relevant and approved\n- Summarize instead of quoting raw transcripts\n\n## Step 4: Cluster by Topic\n\nDo not create one wiki page per session.\n\n- Group by stable topics across many sessions\n- Split mixed sessions into separate themes\n- Merge recurring concepts across dates\u002Fprojects\n- Use `cwd` from metadata to infer project scope\n\n## Step 5: Distill into Wiki Pages\n\nRoute extracted knowledge using existing wiki conventions:\n\n- Project-specific architecture\u002Fprocess -> `projects\u002F\u003Cname>\u002F...`\n- General concepts -> `concepts\u002F`\n- Recurring techniques\u002Fdebug playbooks -> `skills\u002F`\n- Tools\u002Fservices -> `entities\u002F`\n- Cross-session patterns -> `synthesis\u002F`\n\nFor each impacted project, create\u002Fupdate `projects\u002F\u003Cname>\u002F\u003Cname>.md` (project name as filename, never `_project.md`).\n\n### Writing rules\n\n- Distill knowledge, not chronology\n- Avoid \"on date X we discussed...\" unless date context is essential\n- Add `summary:` frontmatter on each new\u002Fupdated page (1-2 sentences, \u003C= 200 chars)\n- Add provenance markers:\n  - `^[extracted]` when directly grounded in explicit session content\n  - `^[inferred]` when synthesizing patterns across events\u002Fsessions\n  - `^[ambiguous]` when sessions conflict\n- Add\u002Fupdate `provenance:` frontmatter mix for each changed page\n\n## Step 6: Update Manifest, Log, and Index\n\n### Update `.manifest.json`\n\nFor each processed source file:\n\n- `ingested_at`, `size_bytes`, `modified_at`\n- `source_type`: `codex_rollout` | `codex_index` | `codex_history`\n- `project`: inferred project name (when applicable)\n- `pages_created`, `pages_updated`\n\nAdd\u002Fupdate a top-level project\u002Fsession summary block:\n\n```json\n{\n  \"project-name\": {\n    \"source_path\": \"~\u002F.codex\u002Fsessions\u002F...\",\n    \"last_ingested\": \"TIMESTAMP\",\n    \"sessions_ingested\": 12,\n    \"sessions_total\": 40,\n    \"index_updated_at\": \"TIMESTAMP\"\n  }\n}\n```\n\n### Update special files\n\nUpdate `index.md` and `log.md`:\n\n```\n- [TIMESTAMP] CODEX_HISTORY_INGEST sessions=N pages_updated=X pages_created=Y mode=append|full\n```\n\n**`hot.md`** — Read `$OBSIDIAN_VAULT_PATH\u002Fhot.md` (create from the template in `wiki-ingest` if missing). Update **Recent Activity** with a one-line summary — e.g. \"Ingested 12 Codex sessions; surfaced recurring patterns in CLI tooling and shell scripting.\" Keep the last 3 operations. Update `updated` timestamp.\n\n## Privacy and Compliance\n\n- Distill and synthesize; avoid raw transcript dumps\n- Default to redaction for anything that looks sensitive\n- Ask the user before storing personal\u002Fsensitive details\n- Keep references to other people minimal and purpose-bound\n\n## Reference\n\nSee `references\u002Fcodex-data-format.md` for field-level parsing notes and extraction guidance.\n","# Codex History Ingest — Conversation Mining\n\nYou are extracting knowledge from the user's past Codex sessions and distilling it into the Obsidian wiki. Session logs are rich but noisy: focus on durable knowledge, not operational telemetry.\n\nThis skill can be invoked directly or via the `wiki-history-ingest` router (`\u002Fwiki-history-ingest codex`).\n\n## Before You Start\n\n1. Read `.env` to get `OBSIDIAN_VAULT_PATH` and `CODEX_HISTORY_PATH` (default to `~\u002F.codex` if unset)\n2. Read `.manifest.json` at the vault root to check what has already been ingested\n3. Read `index.md` at the vault root to understand what the wiki already contains\n\n## Ingest Modes\n\n### Append Mode (default)\n\nCheck `.manifest.json` for each source file. Only process:\n\n- Files not in the manifest (new session rollouts, new index files)\n- Files whose modification time is newer than `ingested_at` in the manifest\n\nUse this mode for regular syncs.\n\n### Full Mode\n\nProcess everything regardless of manifest. Use after `wiki-rebuild` or if the user explicitly asks for a full re-ingest.\n\n## Codex Data Layout\n\nCodex stores local artifacts under `~\u002F.codex\u002F`.\n\n```\n~\u002F.codex\u002F\n├── sessions\u002F                          # Session rollout logs by date\n│   └── YYYY\u002FMM\u002FDD\u002F\n│       └── rollout-\u003Ctimestamp>-\u003Cid>.jsonl\n├── archived_sessions\u002F                 # Archived rollout logs\n├── session_index.jsonl                # Lightweight index of thread id\u002Fname\u002Fupdated_at\n├── history.jsonl                      # Local transcript history (if persistence enabled)\n├── config.toml                        # User config (contains history settings)\n└── state_*.sqlite \u002F logs_*.sqlite     # Runtime DBs (usually skip)\n```\n\n### Key data sources ranked by value\n\n1. `session_index.jsonl` — best inventory source for IDs, titles, and freshness\n2. `sessions\u002F**\u002Frollout-*.jsonl` — rich structured transcript events\n3. `history.jsonl` — useful fallback\u002Ftimeline aid if enabled\n\nAvoid ingesting SQLite internals unless the user explicitly asks.\n\n## Step 1: Survey and Compute Delta\n\nScan `CODEX_HISTORY_PATH` and compare against `.manifest.json`:\n\n- `~\u002F.codex\u002Fsession_index.jsonl`\n- `~\u002F.codex\u002Fsessions\u002F**\u002Frollout-*.jsonl`\n- `~\u002F.codex\u002Farchived_sessions\u002F**` (optional; only if user asks for archived history)\n- `~\u002F.codex\u002Fhistory.jsonl` (optional fallback)\n\nClassify each file:\n\n- **New** — not in manifest\n- **Modified** — in manifest but file is newer than `ingested_at`\n- **Unchanged** — already ingested and unchanged\n\nReport a concise delta summary before deep parsing.\n\n## Step 2: Parse Session Index First\n\n`session_index.jsonl` typically has entries like:\n\n```json\n{\"id\":\"...\",\"thread_name\":\"...\",\"updated_at\":\"...\"}\n```\n\nUse it to:\n\n- Build a canonical session inventory\n- Prioritize recent\u002Fhigh-signal sessions\n- Map rollout IDs to human-readable thread names\n\n## Step 3: Parse Rollout JSONL Safely\n\nEach `rollout-*.jsonl` line is an event envelope with:\n\n```json\n{\n  \"timestamp\": \"...\",\n  \"type\": \"session_meta|turn_context|event_msg|response_item\",\n  \"payload\": { ... }\n}\n```\n\n### Extraction rules\n\n- Prioritize user intent and assistant-visible outputs\n- Favor `response_item` records with user\u002Fassistant message content\n- Use `event_msg` selectively for meaningful milestones; ignore pure telemetry\n- Treat `session_meta` as metadata (cwd, model, ids), not user knowledge\n\n### Skip\u002Fnoise filters\n\n- Token accounting events\n- Tool plumbing with no semantic content\n- Raw command output unless it contains reusable decisions\u002Fpatterns\n- Repeated plan snapshots unless they add novel decisions\n\n### Critical privacy filter\n\nRollout logs can include injected instructions, tool payloads, and sensitive text. Do not ingest verbatim system\u002Fdeveloper prompts or secrets.\n\n- Remove API keys, tokens, passwords, credentials\n- Redact private identifiers unless relevant and approved\n- Summarize instead of quoting raw transcripts\n\n## Step 4: Cluster by Topic\n\nDo not create one wiki page per session.\n\n- Group by stable topics across many sessions\n- Split mixed sessions into separate themes\n- Merge recurring concepts across dates\u002Fprojects\n- Use `cwd` from metadata to infer project scope\n\n## Step 5: Distill into Wiki Pages\n\nRoute extracted knowledge using existing wiki conventions:\n\n- Project-specific architecture\u002Fprocess -> `projects\u002F\u003Cname>\u002F...`\n- General concepts -> `concepts\u002F`\n- Recurring techniques\u002Fdebug playbooks -> `skills\u002F`\n- Tools\u002Fservices -> `entities\u002F`\n- Cross-session patterns -> `synthesis\u002F`\n\nFor each impacted project, create\u002Fupdate `projects\u002F\u003Cname>\u002F\u003Cname>.md` (project name as filename, never `_project.md`).\n\n### Writing rules\n\n- Distill knowledge, not chronology\n- Avoid \"on date X we discussed...\" unless date context is essential\n- Add `summary:` frontmatter on each new\u002Fupdated page (1-2 sentences, \u003C= 200 chars)\n- Add provenance markers:\n  - `^[extracted]` when directly grounded in explicit session content\n  - `^[inferred]` when synthesizing patterns across events\u002Fsessions\n  - `^[ambiguous]` when sessions conflict\n- Add\u002Fupdate `provenance:` frontmatter mix for each changed page\n\n## Step 6: Update Manifest, Log, and Index\n\n### Update `.manifest.json`\n\nFor each processed source file:\n\n- `ingested_at`, `size_bytes`, `modified_at`\n- `source_type`: `codex_rollout` | `codex_index` | `codex_history`\n- `project`: inferred project name (when applicable)\n- `pages_created`, `pages_updated`\n\nAdd\u002Fupdate a top-level project\u002Fsession summary block:\n\n```json\n{\n  \"project-name\": {\n    \"source_path\": \"~\u002F.codex\u002Fsessions\u002F...\",\n    \"last_ingested\": \"TIMESTAMP\",\n    \"sessions_ingested\": 12,\n    \"sessions_total\": 40,\n    \"index_updated_at\": \"TIMESTAMP\"\n  }\n}\n```\n\n### Update special files\n\nUpdate `index.md` and `log.md`:\n\n```\n- [TIMESTAMP] CODEX_HISTORY_INGEST sessions=N pages_updated=X pages_created=Y mode=append|full\n```\n\n**`hot.md`** — Read `$OBSIDIAN_VAULT_PATH\u002Fhot.md` (create from the template in `wiki-ingest` if missing). Update **Recent Activity** with a one-line summary — e.g. \"Ingested 12 Codex sessions; surfaced recurring patterns in CLI tooling and shell scripting.\" Keep the last 3 operations. Update `updated` timestamp.\n\n## Privacy and Compliance\n\n- Distill and synthesize; avoid raw transcript dumps\n- Default to redaction for anything that looks sensitive\n- Ask the user before storing personal\u002Fsensitive details\n- Keep references to other people minimal and purpose-bound\n\n## Reference\n\nSee `references\u002Fcodex-data-format.md` for field-level parsing notes and extraction guidance.\n",{"name":5,"description":7},"main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Fcodex-history-ingest",0,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto","https:\u002F\u002Fgithub.com\u002Fsaski","http:\u002F\u002Fsaski.com","2026-11-12 20:09:16",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add saski\u002Farnesto --skill codex-history-ingest",{"tool":37,"command":38},"bunx","bunx skills add saski\u002Farnesto --skill codex-history-ingest",{"tool":40,"command":41},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill codex-history-ingest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodex-history-ingest\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fcodex-data-format.md","REFERENCE","参考文档",2425,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodex-history-ingest\u002Freferences\u002Fcodex-data-format.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7AT7F5FSHNAMFMF01N0QA1X","visualize","Use \u002Fvisualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fvisualize\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7AT79MHSAR3JDDMP7DGERM9","update-cursor-settings","Modify Cursor\u002FVSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cursor-settings\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7AT73WF3Y22E0FKYAMCCJES","update-cli-config","View and modify Cursor CLI configuration settings in ~\u002F.cursor\u002Fcli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cli-config\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7AT6F3FBP85AJJ5BJNR8B5W","statusline","Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fstatusline\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7AT6D24QFS5XRAFN8S5XJ7W","split-to-prs","Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fsplit-to-prs\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7AT69FYFN84XZKW452JV5DF","shell","Runs the rest of a \u002Fshell request as a literal shell command. Use only when the user explicitly invokes \u002Fshell and wants the following text executed directly in the terminal.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fshell\u002FSKILL.md",[],[]]