Use this skill when the user asks to update CLAUDE.md, save a lesson, or persist something from the current session: phrases like "update claude.md", "what should we remember", "save this lesson", or "add to context". Scans the conversation for hard-won lessons, new file paths, infrastructure changes, and new workflows, then proposes scoped edits to the project's CLAUDE.md for approval before writing.
SkillScore87Maintained
Automatic
◆Knowledge Management pack
Last verified 8/21/2026
What it changes
Passed 20 of 23 test cases with the skill, and 7 of 23 without it.
Without skill30%
With skill87%
Checks it passed that the model alone missed
Recommends keeping correction history out of CLAUDE.md.
Categorizes the gRPC ALB timeout finding as a hard-won lesson.
Proposes no duplicate additions for the existing database URL.
and 15 more in the full report
13 fixed7 passed either way3 still failing0 broke
Pass-rate lift
+57 pp
Tokens
+49%
Agent turns
0%
Response time
-13%
Model gemini-3.6-flashMeasured 8/21/2026v120 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
Today we refactored three React components, fixed two CSS padding glitches, and discovered that Redis 7 requires `TLS_RESTART=true` on our staging cluster to avoid broken socket connections. Draft a memory update for our project setup, but omit the temporary bug fixes and daily progress details.
What was checked, without and with the skill
Checked
Without skill
With skill
Includes the Redis TLS flag workaround under the hard-won lessons category.
Missed
Passed
Excludes component refactoring and CSS padding fixes from the proposed diff.
Passed
Passed
case-07 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md86 linessingle file
CLAUDE.md auto-updater
Analyze the current conversation to identify information worth persisting in CLAUDE.md for future sessions, then propose the edits for approval before writing anything.
What to look for
1. Hard-won lessons
Debugging sessions that revealed non-obvious causes
Workarounds for platform or tool limitations
Anti-patterns discovered through failure
"The real problem was..." moments
2. New infrastructure
New services deployed
New endpoints or URLs
New file paths or directories
New credentials or tokens (reference only, never the values)
3. New workflows
Commands that solve recurring problems
Multi-step processes that work well
Integration patterns between systems
4. Updated information
Changed ports, IPs, or URLs
New capabilities added to existing systems
Deprecated or removed features
Analysis process
Scan the conversation for keywords:
"fixed", "solved", "the issue was", "turns out"
"deployed", "set up", "configured", "installed"
"new endpoint", "new service", "new path"
"doesn't work", "limitation", "workaround"
Categorize findings. Only durable facts belong in CLAUDE.md:
Hard-won lessons go to the "Hard-won lessons" section
Infrastructure changes update the relevant section