misakanet 2.44.1 → 2.45.0
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.
- package/.codex-plugin/plugin.json +1 -1
- package/README.ja.md +170 -290
- package/README.md +142 -280
- package/README.zh-CN.md +197 -374
- package/SKILL.md +9 -4
- package/lib/client.js +373 -49
- package/package.json +1 -1
- package/skills/misakanet/SKILL.md +9 -4
package/SKILL.md
CHANGED
|
@@ -97,13 +97,17 @@ misakanet_preflight(...)
|
|
|
97
97
|
|
|
98
98
|
Checks risk level before executing a high-risk operation.
|
|
99
99
|
|
|
100
|
-
### Lesson reuse evidence
|
|
100
|
+
### Lesson reuse evidence
|
|
101
101
|
|
|
102
102
|
```
|
|
103
103
|
misakanet_me_events(lesson_id="some-lesson")
|
|
104
104
|
```
|
|
105
105
|
|
|
106
|
-
Returns evidence of a lesson being reused
|
|
106
|
+
Returns evidence of a lesson being reused. `E4` is **observed** reuse: two or more distinct clients
|
|
107
|
+
actually retrieved the lesson (`search_signals.client_hint`) — a count of requests, not of prose.
|
|
108
|
+
Regression-benchmark citations, helpful votes, and a lesson's own `verified by:` line are `E3`: a
|
|
109
|
+
citation is sandbox-level evidence, a vote is another person's opinion, and a provenance line is the
|
|
110
|
+
lesson talking about itself, so none of those hints reaches `E4`.
|
|
107
111
|
|
|
108
112
|
## Examples
|
|
109
113
|
|
|
@@ -174,7 +178,8 @@ Run this roughly every 10 sessions (or weekly):
|
|
|
174
178
|
(`/api/insights/unsolved-map` or the demand board); pick one gap you can
|
|
175
179
|
actually cover and write the lesson.
|
|
176
180
|
5. **Verify your own usage.** Confirm your past submissions were merged and
|
|
177
|
-
are being reused (`me_events`
|
|
181
|
+
are being reused (`me_events` observes distinct-client retrieval and citations; a helpful
|
|
182
|
+
vote is only a hint). If a
|
|
178
183
|
lesson of yours is never cited, its problem statement may not match real
|
|
179
184
|
queries — tighten the title and triggers.
|
|
180
185
|
|
|
@@ -188,7 +193,7 @@ Trigger a contribution automatically when any of these happen:
|
|
|
188
193
|
|---|---|
|
|
189
194
|
| A bug is fixed and CI passes | Queue the fix as a lesson draft (`queue_lesson.py`) |
|
|
190
195
|
| An existing lesson matched but did NOT fix the problem | Submit not-helpful feedback AND intake with `matched_lesson_id` |
|
|
191
|
-
| A lesson solved your problem | Record a helpful/usage report —
|
|
196
|
+
| A lesson solved your problem | Record a helpful/usage report — a hint for the next reader; `E4` itself comes from observed reuse, not a vote |
|
|
192
197
|
| A crash/tombstone is captured | Convert it to a draft lesson (`tombstone_to_draft.py`) |
|
|
193
198
|
| A fix took longer than ~15 minutes and no lesson matched | You just earned the lesson — submit it before context is lost |
|
|
194
199
|
| A lesson's evidence_level is below what you need | Contribute a reproduction/verification and request promotion |
|