@fro.bot/systematic 1.22.6 → 1.22.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -1,7 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: learnings-researcher
|
|
3
|
-
description: Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes.
|
|
4
|
-
model: anthropic/haiku
|
|
3
|
+
description: "Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes."
|
|
5
4
|
mode: subagent
|
|
6
5
|
temperature: 0.2
|
|
7
6
|
---
|
|
@@ -57,7 +56,7 @@ If the feature type is clear, narrow the search to relevant category directories
|
|
|
57
56
|
|
|
58
57
|
### Step 3: Grep Pre-Filter (Critical for Efficiency)
|
|
59
58
|
|
|
60
|
-
**Use
|
|
59
|
+
**Use Grep to find candidate files BEFORE reading any content.** Run multiple Grep calls in parallel:
|
|
61
60
|
|
|
62
61
|
```bash
|
|
63
62
|
# Search for keyword matches in frontmatter fields (run in PARALLEL, case-insensitive)
|
|
@@ -230,7 +229,7 @@ Structure your findings as:
|
|
|
230
229
|
## Efficiency Guidelines
|
|
231
230
|
|
|
232
231
|
**DO:**
|
|
233
|
-
- Use
|
|
232
|
+
- Use Grep to pre-filter files BEFORE reading any content (critical for 100+ files)
|
|
234
233
|
- Run multiple Grep calls in PARALLEL for different keywords
|
|
235
234
|
- Include `title:` in Grep patterns - often the most descriptive field
|
|
236
235
|
- Use OR patterns for synonyms: `tags:.*(payment|billing|stripe)`
|
|
@@ -246,7 +245,7 @@ Structure your findings as:
|
|
|
246
245
|
- Note when no relevant learnings exist (this is valuable information too)
|
|
247
246
|
|
|
248
247
|
**DON'T:**
|
|
249
|
-
- Read frontmatter of ALL files (use
|
|
248
|
+
- Read frontmatter of ALL files (use Grep to pre-filter first)
|
|
250
249
|
- Run Grep calls sequentially when they can be parallel
|
|
251
250
|
- Use only exact keyword matches (include synonyms)
|
|
252
251
|
- Skip the `title:` field in Grep patterns
|
|
@@ -259,8 +258,8 @@ Structure your findings as:
|
|
|
259
258
|
## Integration Points
|
|
260
259
|
|
|
261
260
|
This agent is designed to be invoked by:
|
|
262
|
-
- `/
|
|
263
|
-
- `/deepen-plan`
|
|
261
|
+
- `/ce:plan` — To inform planning with institutional knowledge
|
|
262
|
+
- `/deepen-plan` — To add depth with relevant learnings
|
|
264
263
|
- Manual invocation before starting work on a feature
|
|
265
264
|
|
|
266
|
-
The goal is to surface relevant learnings in under 30 seconds for a typical solutions directory, enabling fast knowledge retrieval during planning phases.
|
|
265
|
+
The goal is to surface relevant learnings in under 30 seconds for a typical solutions directory, enabling fast knowledge retrieval during planning phases.
|