loom-mentor — the store's advice, and where each plane lives
Loom has a few hundred operations; your tool list shows the ones a coding
session uses most. The mentor reads what your agent called this week and
names the plane it is not using: a hint on a tool result, a Loom mentor
line in the session primer. Read a hint once, act on it once; the same code
is not shown again this session.
This skill routes. The destination skill owns the detail: the shape of a
write is loom-memory, code questions are loom-code, reworking stored
rows is loom-optimize.
Calling an op your tool list does not show
A listed op is the tool loom_<op with dots as underscores>
(tracker.similar → loom_tracker_similar). An op that is not in your
tool list runs through loom_op {op: "tracker.similar", arguments: {…}};
loom_op {op: "help", query: "<words>"} lists matching ops and their
arguments. Your host can only call tools it was shown, so never call an
unlisted loom_* name directly. The tracker tools are listed when the MCP
entry mounts /mcp?toolset=coding+tracker (the plugin's toolset option),
or a second entry mounts /mcp?toolset=tracker.
The planes a hint points at
| Situation |
Op |
| "has this crash / test failure / report been seen before" |
loom_tracker_duplicate_check (listed: draft title + body → duplicate_of / related / none); loom_tracker_similar, tracker.flaky, tracker.test_signal (listed on coding+tracker, else through loom_op) |
| which PR broke a behaviour between two versions |
loom_code_bisect_candidates (symbols or paths, good_version, bad_version) |
| about to open a PR |
loom_code_pr_check (title, body, paths, symbols, issues) |
| is it safe to change X |
loom_code_impact |
| a document, runbook or report over ~2 KB |
knowledge.upsert + one pointer row (loom-memory) |
| a table of facts with identity (PRs, alerts, services) |
memory_schema.register once, then memory.record.write |
| your plan, a lease, "where was I" |
loom_working_memory_set |
| a 3,000-line log or diff to park |
context.offload, then context.fetch |
Tracker ops take the tracker namespace, or the repository's code namespace
when it is bound to one (tracker.binding says which).
The hints you will see most
| code |
do |
tracker_unused |
run the tracker check above before filing or grepping |
code_index_unused |
loom_code_symbol / loom_code_search for identifier questions |
bisect_available |
loom_code_bisect_candidates first, blame second |
get_miss |
loom_search by meaning; memory.list prefix=; follow: true |
set_duplicate / duplicates_written |
revise the named row, never a third copy |
documents_as_memories / set_large_value |
a knowledge document plus a pointer row |
Every other code, the full situation table and mentor.brief (the counts
behind a hint) are in reference.md beside this file. A code that is in
neither table is newer than this skill: follow the hint's own sentence and
the ops it names, or ask mentor.brief for its evidence.
1---2name: loom-mentor3description: >4 Use when a loom hint (a tool result's `hint`, an `X-Loom-Hint` header or5 a "Loom mentor" line) names a plane or op you do not know how to use, or6 when the user asks "what can loom do", "how should I be using loom", "am I7 using loom well", "loom mentor". A hint that already names the op to call8 needs no skill: call it or carry on with the task. Maps a situation to the9 loom plane and op that fits — code index, tracker record, documents,10 records, working memory, offload, the entity graph, runs, decisions,11 procedures, duplicates, conflicts, bisect — and says what to do about each12 hint code. NOT for deciding the shape of one write (loom-memory), NOT for13 grep-vs-code.* in an indexed repo (loom-code), NOT for reworking a14 namespace that already holds the wrong shape (loom-optimize).15disable-model-invocation: true16metadata:17 source: https://skillmd.com/skills/clickhouse/loom-mentor18---1920# loom-mentor — the store's advice, and where each plane lives2122Loom has a few hundred operations; your tool list shows the ones a coding23session uses most. The mentor reads what your agent called this week and24names the plane it is not using: a `hint` on a tool result, a `Loom mentor`25line in the session primer. Read a hint once, act on it once; the same code26is not shown again this session.2728This skill routes. The destination skill owns the detail: the shape of a29write is `loom-memory`, code questions are `loom-code`, reworking stored30rows is `loom-optimize`.3132## Calling an op your tool list does not show3334A listed op is the tool `loom_<op with dots as underscores>`35(`tracker.similar` → `loom_tracker_similar`). An op that is not in your36tool list runs through `loom_op {op: "tracker.similar", arguments: {…}}`;37`loom_op {op: "help", query: "<words>"}` lists matching ops and their38arguments. Your host can only call tools it was shown, so never call an39unlisted `loom_*` name directly. The tracker tools are listed when the MCP40entry mounts `/mcp?toolset=coding+tracker` (the plugin's `toolset` option),41or a second entry mounts `/mcp?toolset=tracker`.4243## The planes a hint points at4445| Situation | Op |46|---|---|47| "has this crash / test failure / report been seen before" | `loom_tracker_duplicate_check` (listed: draft title + body → `duplicate_of` / `related` / `none`); `loom_tracker_similar`, `tracker.flaky`, `tracker.test_signal` (listed on `coding+tracker`, else through `loom_op`) |48| which PR broke a behaviour between two versions | `loom_code_bisect_candidates` (symbols or paths, `good_version`, `bad_version`) |49| about to open a PR | `loom_code_pr_check` (title, body, paths, symbols, issues) |50| is it safe to change X | `loom_code_impact` |51| a document, runbook or report over ~2 KB | `knowledge.upsert` + one pointer row (`loom-memory`) |52| a table of facts with identity (PRs, alerts, services) | `memory_schema.register` once, then `memory.record.write` |53| your plan, a lease, "where was I" | `loom_working_memory_set` |54| a 3,000-line log or diff to park | `context.offload`, then `context.fetch` |5556Tracker ops take the tracker namespace, or the repository's code namespace57when it is bound to one (`tracker.binding` says which).5859## The hints you will see most6061| code | do |62|---|---|63| `tracker_unused` | run the tracker check above before filing or grepping |64| `code_index_unused` | `loom_code_symbol` / `loom_code_search` for identifier questions |65| `bisect_available` | `loom_code_bisect_candidates` first, blame second |66| `get_miss` | `loom_search` by meaning; `memory.list prefix=`; `follow: true` |67| `set_duplicate` / `duplicates_written` | revise the named row, never a third copy |68| `documents_as_memories` / `set_large_value` | a knowledge document plus a pointer row |6970Every other code, the full situation table and `mentor.brief` (the counts71behind a hint) are in `reference.md` beside this file. A code that is in72neither table is newer than this skill: follow the hint's own sentence and73the ops it names, or ask `mentor.brief` for its evidence.