Dev & Engineering claude-code-hooksmemory-managementclaude-mdagents-mdsession-historyskill-discoverycorrection-detectionpython

Claude Reflect Self-Learning Memory

Captures your corrections and preferences automatically via Claude Code hooks, then syncs them to CLAUDE.md after human review — permanent memory plus repeatable skill discovery.

FollowSkills review · FSRS-2.0
Use with care
57/ 100 5-point scale 2.9 / 5
1 2 3 4 5 6
1Trust13 / 25 · 2.6/5

Data flow is well disclosed (hooks capture → queue → human review before writing to CLAUDE.md/AGENTS.md), writes are gated by [y/n] confirmation and --dry-run preview, MIT license; deducted because hooks automatically capture prompt/session content and persist it across multiple ~/.claude locations with broad scope, no explicit rollback mechanism, and limited sensitive-data handling disclosure.

2Reliability13 / 20 · 3.3/5

Repo includes CI workflows (3 OSes, 2 Python versions) and committed pytest suites (test_memory_hierarchy.py etc.) covering key paths like rule parsing, file discovery and routing, plus abnormal-input tests (invalid JSON, missing files); but this is a static review — pass status unverified — and CLAUDE.md's example queue path (~/.claude/learnings-queue.) contradicts the per-project queue path described in changelog 3.1.0.

3Adaptability9 / 15 · 3.0/5

SKILL.md trigger conditions are explicit (user corrections, 'remember', pre-compaction reminders) and scenarios are clear; changelog claims CJK correction patterns added in v3.1.0; deducted for missing declared non-fit boundaries (non-Claude-Code environments, missing Python) and unverified real-world CJK detection accuracy.

4Convention10 / 15 · 3.3/5

MIT license, Keep-a-Changelog format, semantic versioning, and RELEASING.md release process are all present; deducted because the README version badge (2.6.0) is out of sync with changelog 3.1.0, SKILL.md itself is thin beyond examples, publisher identity is unverified, and maintenance responsibility rests on a single personal repository.

5Effectiveness7 / 15 · 2.3/5

The two-stage design (automatic capture + manual review) addresses a real pain point and produces standard CLAUDE.md entries, with --dry-run and --dedupe reducing cost; deducted because static review cannot verify output quality, and false positive/negative rates of the regex+semantic hybrid detection are unknown.

6Verifiability5 / 10 · 2.5/5

Auditable primary material exists: CI config, 160 tests (including bash/Python equivalence integration tests), and reproducible CLI test commands; but all evidence is self-reported, test passage could not be independently reproduced in this static review, and there is no third-party corroboration, so capped at 5.

Evidence confidence:Low Reviewed Sep 18, 2026 Reviewed revision 8dc9db43c9bf
Before you use it
  • Static review only; no code was executed. Test badges (160 passing) and CI status are self-reported and independently unverified.
  • Hooks analyze and persist prompt content automatically on every submission to multiple files under ~/.claude; sensitive prompt content may be written to disk queues — evaluate privacy implications before installing.
  • Documentation inconsistencies exist (README badge 2.6.0 vs CHANGELOG 3.1.0, conflicting queue path descriptions); rely on actual behavior rather than docs.
  • CJK detection (including Chinese correction patterns) is claimed only in the changelog with no pattern list or test evidence in the reviewed material; Chinese users should trial with a small scope first.
  • CLAUDE.md is shared by multiple tools; automatic writes may affect Codex/Cursor and others — review changes with --dry-run first.
See the full review method →

What does this skill do, and when should you use it?

claude-reflect is a self-learning plugin for Claude Code (v2.6.0, MIT licensed). Automatically-running hooks capture corrections, positive feedback, and preferences during your sessions and queue them; you then run /reflect to review each learning and sync it to global or project CLAUDE.md and AGENTS.md files. Version 2 adds skill discovery: it analyzes past sessions to find repeating workflows and turns them into reusable slash commands. Every learning carries a confidence score, gets human review before landing, supports corrections in any language via AI semantic validation, and includes semantic deduplication.

Runs four hooks automatically: one reminds of pending learnings at session start; capture_learning.py detects correction patterns on every prompt (regex matches like "no, use X", "actually...", "remember:") and queues them to ~/.claude/learnings-queue.; one backs up the queue before context compaction; one reminds after git commits. When you run /reflect, an AI semantic filter validates the queue (understanding any language), filters false positives, and assigns confidence scores (0.60–0.95); approved learnings sync to ~/.claude/CLAUDE.md, ./CLAUDE.md, subdirectory CLAUDE.md files, AGENTS.md, .claude/rules/*.md, or the relevant skill file. Running /reflect-skills uses AI semantic analysis over session history to distill repeated intents into skill candidates (e.g., generating /daily-review from 15 similar requests), creating draft skill files in .claude/commands/ for your approval. Supporting flags include --dry-run, --dedupe for semantic deduplication, and --scan-history.

  1. Developers who repeatedly correct Claude about wrong models or tools and want those mistakes to stop recurring
  2. Engineers on large projects who want conventions (naming, build commands, structure) remembered across sessions
  3. Users who type similar instructions repeatedly (daily productivity reviews, deploy routines) and want them codified into one command
  4. Teams using multiple AI coding tools (Codex, Cursor, Aider, etc.) who want learnings synced to AGENTS.md
  5. Custom skill authors who want corrections made during skill execution routed back into the skill file itself
  6. Users on a new machine who want to recover learnings by scanning up to 90 days of past sessions

What are this skill's strengths and limitations?

Pros
  • Human review gate before anything is written, preventing bad learnings from polluting memory files
  • Multi-target sync covers CLAUDE.md, AGENTS.md, rules directories, and skill files — works across several AI tools
  • Hybrid regex + AI semantic detection understands corrections in any language, with visible confidence scores
  • Safety options like --dry-run, --dedupe, and --targets; 160 tests passing
  • Skill improvement routing makes custom skills smarter over time
Limitations
  • Deeply tied to Claude Code-specific mechanisms (plugin hooks, slash commands, CLAUDE.md) — not portable as-is
  • Stage 2 is manual; if you forget to run /reflect, learnings pile up unprocessed
  • Historical scan and skill discovery depend on local session files, which Claude Code purges after 30 days by default
  • README screenshots and example outputs cannot be independently verified; contributing guidelines are referenced but not included in the source
  • Upgrading older versions hits known Claude Code plugin cache bugs (upstream issues #14061, #15369) requiring manual cache clearing

How do you install this skill?

Prerequisites: Claude Code CLI and Python 3.6+ (macOS, Linux, and Windows natively supported; no WSL needed). Install with:

claude plugin marketplace add bayramannakov/claude-reflect
claude plugin install claude-reflect@claude-reflect-marketplace

You must fully exit and restart Claude Code afterward so hooks auto-configure. When upgrading from older versions, known Claude Code cache issues ("Duplicate hooks file detected") require manually clearing the two cache directories under ~/.claude/plugins/ before reinstalling — see the README steps.

How do you use this skill?

Daily flow: correct Claude naturally (e.g., "no, use gpt-5.1 not gpt-5") — hooks queue it automatically; after finishing work, run /reflect (or say "remember: ..." for high-confidence capture), then apply, edit, or skip each learning. Skill discovery: run /reflect-skills --days 30 to analyze recent sessions, use --dry-run to preview and --all-projects for cross-project patterns. First-time users should run /reflect --scan-history. Note: Claude Code deletes local sessions after 30 days by default; set { "cleanupPeriodDays": 99999 } in ~/.claude/settings. to preserve history.

How does this skill compare with similar options?

The source names no direct competitors, but the README notes AGENTS.md sync targets Codex, Cursor, Aider, Jules, Zed, and Factory — positioning it as a complementary memory layer across those tools' native mechanisms.

FAQ

Are learnings written automatically? Could they pollute my config files?
No. Hooks only queue learnings; nothing is synced until you run /reflect and explicitly apply, edit, or skip each one. A --dry-run mode lets you preview changes first.
Does it need network access or cost money?
The plugin itself is a free, MIT-licensed local tool with no stated network requirement; semantic validation and skill discovery use Claude Code's built-in AI, billed as part of your existing Claude Code usage.
Does it work with corrections in languages other than English?
Yes. Regex handles real-time fast capture, while the AI semantic filter during /reflect understands corrections in any language — e.g., the Spanish "no, usa Python" is detected correctly.
Will I lose my learnings when switching machines?
The local queue would be lost, but /reflect --scan-history (e.g., --days 90) can recover corrections from past sessions — provided those sessions weren't purged by Claude Code's default 30-day cleanup, so raising cleanupPeriodDays is recommended.

Related skills