search SKILL.md skillB
search from tonydzi/second-brain-starter-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tonydzi/second-brain-starter-kit/search@git:20261007.cd6c208Pins git:20261007.cd6c208 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tonydzi/second-brain-starter-kit
- Path
skills/search/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261007.cd6c208, committed Oct 7, 2026
- First version recorded
- Aug 14, 2026
- Size
- 4,017 bytes
- Repository stars
- 13
- License
- MIT
Full-text keyword search across every conversation at once (Telegram, Facebook, ChatGPT, Claude, notes, transcripts) over a local BM25/FTS5 catalog: instant, zero tokens, with snippets and chat-title hits. The exact-words lane, complementary to semantic search. Triggers: "/search <words>", "where did I write about <X>".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
OBJECTIVE: Find specific words/phrases inside Anton's entire conversation corpus (~99k notes in `01-Conversations/**`) instantly and token-free, returning ranked snippets + which chats match by title. The lexical (BM25) lane of the unified search layer; the semantic (sqlite-vec + RRF) lane is added per the decision memo. CONTEXT: - Engine: `$IMPORTS_ROOT/search/search_catalog.db` (SQLite FTS5 over title+body of every conversation .md). Rebuilt by `build_catalog_fts.py` (derived, rebuildable artifact; ~3 min over 99k files). - CLI: `python $IMPORTS_ROOT/search/search.py [--k N] [--chats] <query>` (UTF-8 output, real Cyrillic). - Visual UI: `python $IMPORTS_ROOT/search/search_server.py` -> http://127.0.0.1:8771 (stdlib, no deps; autostart task keeps it alive). - Title index reused: `..\dialogs\dialogs.db` (chat lookup by name). - Canon: vault `02-Decisions\decision-unified-search-layer.md`; memory `unified-search-layer`. Token law: exact/SQL before BM25, BM25 before embeddings, retrieval before LLM. STEPS: 1. Take Anton's query words. If he wants the visual interface, point him to http://127.0.0.1:8771 (start `search_server.py` if down). …
Read the whole file at its exact version.
How to install
mdr add tonydzi/second-brain-starter-kit/search@sha256:735cbb0226b948baThe line at the top of this page pins the label git:20261007.cd6c208, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ccakpi5ifntgr455)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 14, 2026 and Oct 7, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.cd6c208 latest | 2026-10-07 | cd6c208 | 4,017 B | B | view · diff |
| git:20261003.a2d662f | 2026-10-03 | a2d662f | 4,018 B | B | view · diff |
| v1.0.0 | 2026-09-24 | 2784cb2 | 3,280 B | B | view · diff |
| git:20260908.2ec1bf8 | 2026-09-08 | 2ec1bf8 | 4,023 B | B | view · diff |
| git:20260814.d899e4a | 2026-08-14 | d899e4a | 3,627 B | B | view · diff |
| git:20260814.06fa906 | 2026-08-14 | 06fa906 | 3,644 B | B | view · diff |
| git:20260814.5023d8c | 2026-08-14 | 5023d8c | 2,949 B | B | view · diff |
| git:20260814.44e61cf | 2026-08-14 | 44e61cf | 3,492 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:8771)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4017 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
tonydzi/second-brain-starter-kit · 13 stars · license MIT · pushed 2026-11-02 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_ccakpi5ifntgr455 GET https://markdownregistry.com/api/v1/resolve?ref=tonydzi/second-brain-starter-kit/search GET https://markdownregistry.com/api/v1/blob/735cbb0226b948ba050ef63b0c6661344cd9111caf0249245bc9d56e78872519
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from tonydzi/second-brain-starter-kit
Every file in tonydzi/second-brain-starter-kit