From memory-toolkit
Collect DOC: notes from session, generalize, and propose repo documentation (.claude/rules/, docs/).
How this skill is triggered — by the user, by Claude, or both
Slash command
/memory-toolkit:docs-reflect [optional focus area][optional focus area]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Collect DOC: notes accumulated during the session, generalize them into rules, and propose documentation for the repository.
Collect DOC: notes accumulated during the session, generalize them into rules, and propose documentation for the repository.
Two sources: DOC: notes from the current session, and recurring feedback from memory.
node "$MEM" --dir="$MEM_DIR" docs
node "$MEM" --dir="$MEM_DIR" recurring
This scans feedback/ files for clusters — similar corrections that appeared 2+ times across sessions. Recurring patterns are strong candidates for promotion to .claude/rules/.
If both sources are empty — tell user "No documentation findings." and stop.
If recurring patterns found (3+ occurrences) — these are project conventions, not personal preferences. Treat them as DOC automatically:
node "$MEM" --dir="$MEM_DIR" note "DOC: <domain> — <generalized rule from recurring feedback>"Patterns with 2 occurrences — mention as candidates but don't auto-promote.
For each DOC: note, extract a generalized rule.
Bad (too specific):
"The PaymentService bug was on line 42 in processRefund()"
Good (pattern):
"Refund operations must check transaction state before mutating — stale state causes double-refunds"
Bad (class-level):
"UserService.getProfile() returns null when user is not found"
Good (convention):
"Services return null for missing entities instead of throwing — callers must handle null"
If a note can't be generalized — skip it.
ls .claude/rules/ 2>/dev/null
cat CLAUDE.md 2>/dev/null | head -50
ls docs/ 2>/dev/null
Check memory for saved preference:
node "$MEM" --dir="$MEM_DIR" search "docs_target"
If no saved preference and no .claude/rules/ directory — ask:
Where should project rules go?
1. .claude/rules/ (Claude Code loads these per-directory)
2. docs/
3. CLAUDE.md (single file, always loaded — use sparingly)
4. Other — specify path
Choice? (default: 1)
Save preference:
node "$MEM" --dir="$MEM_DIR" note "CONFIG: docs_target=<chosen path>"
Route using the chosen target directory (default: .claude/rules/):
| Domain | Target |
|---|---|
| testing | <target>/testing.md |
| api | <target>/api.md |
| architecture | <target>/architecture.md |
| state | <target>/state.md |
| workflow | <target>/workflow.md |
| Other domain | <target>/<domain>.md |
| Truly universal (rare) | CLAUDE.md |
If a matching file exists — add to it. If not — create one.
## Docs-reflect: <date>
Found N DOC: notes, grouped into M domains:
### <target>/testing.md
- <rule 1>
- <rule 2>
### <target>/api.md
- <rule 3>
### Skipped
- <notes too specific to generalize>
Apply? (all / pick numbers / skip)
Wait for user confirmation.
For each approved rule:
For rule files (.claude/rules/, docs/, or custom target):
## <Section>
- <Rule>
.claude/rules/ file.npx claudepluginhub aivandelindt/claude_memory-toolkit --plugin memory-toolkitGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.