forked from jason/echo
Jason Stedwell
be3fd36ebf
1. capture-update keeps the whole body (was truncating to first line) 2. frontmatter completeness: kind-default status + kind-seeded tags at capture, fm create-or-replace, incomplete-frontmatter lint, sweep backfill (one data source: KIND_STATUS/KIND_REQUIRED_FM) 3. pre-write duplicate gate (exit 76, --merge-into/--force) 4. recall corpus + ranking: sessions/journal indexed (down-weighted), BM25 x freshness x status fusion, recall --json, index schema 2 5. session hooks: SessionStart auto-load, Stop reflection nudge 6. one-tap triage verb with processing-log audit; --json on read verbs +22 mock end-to-end tests; all suites green. Docs current (README, CHANGELOG, SKILL.md, commands, references, MAINTENANCE, eval README). Drops tracked .DS_Store (gitignored); retires README-gretchen.md (moved to gitignored dist/); adds the field report that drove item 2. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
22 lines
1.3 KiB
Markdown
22 lines
1.3 KiB
Markdown
---
|
||
description: Recall a topic from ECHO memory — matching notes plus their linked neighbourhood
|
||
argument-hint: "[topic, person, or project]"
|
||
---
|
||
|
||
Use the **echo-memory** skill to recall context for:
|
||
|
||
> $ARGUMENTS
|
||
|
||
Run the one-call recall — it resolves the term against the entity index, searches, and expands one hop along `## Related` links and `source_notes`, so you get the connected web (linked decisions, people, prior sessions), not an isolated note:
|
||
|
||
```bash
|
||
ECHO="${CLAUDE_PLUGIN_ROOT}/skills/echo-memory/scripts/echo.py"
|
||
[ -f "$ECHO" ] || ECHO=$(ls /sessions/*/mnt/.remote-plugins/*/skills/echo-memory/scripts/echo.py 2>/dev/null | head -1) # CoWork sandbox fallback
|
||
python3 "$ECHO" recall "$ARGUMENTS"
|
||
# Windows: use `python` or `py -3` if `python3` is not on PATH.
|
||
```
|
||
|
||
The corpus spans the entity graph **plus session logs and journal notes**, ranked by relevance × freshness × status — each hit shows its `updated:`/`status:`, so prefer fresh/active hits and treat stale ones as history. Add `--json` for structured hits (`path/score/type/updated/status/excerpt`) when you need to act on the results programmatically.
|
||
|
||
Then answer from the assembled context. If you only need the canonical path for one entity, use `echo.py resolve "<title>"` instead. Don't narrate the retrieval.
|