Continue
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi.
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install affaan-m/ECC continuous-learning-v2 --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .claude/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .claude/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install affaan-m/ECC continuous-learning-v2 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .agents/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .agents/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install affaan-m/ECC continuous-learning-v2 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .cursor/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .cursor/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/affaan-m/ECC.git --path docs/tr/skills/continuous-learning-v2--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install affaan-m/ECC continuous-learning-v2 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .gemini/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .gemini/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install affaan-m/ECC continuous-learning-v2Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .github/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .github/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add affaan-m/ECC --skill continuous-learning-v2 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install affaan-m/ECC continuous-learning-v2 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/tr/skills/continuous-learning-v2 .opencode/skills/continuous-learning-v2 && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "continuous-learning-v2" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/tr/skills/continuous-learning-v2 into .opencode/skills/continuous-learning-v2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "continuous-learning-v2", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
continuous-learning-v2Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi.
Continuous Learning V2 is an agent skill from affaan-m/ECC. Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ef648e0. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
python3gitFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
github.comx.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Continuous Learning V2 loads about 3.3k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 832 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from affaan-m/ECC at commit ef648e0, republished under its MIT licence (© affaan-m). 832 words, ~3,259 tokens.
.claude/skills/continuous-learning-v2/SKILL.md (or your agent's skills folder).Claude Code oturumlarınızı güven skorlaması ile atomik "instinct'ler" - küçük öğrenilmiş davranışlar - aracılığıyla yeniden kullanılabilir bilgiye dönüştüren gelişmiş bir öğrenme sistemi.
v2.1 proje kapsamlı instinct'ler ekler — React kalıpları React projenizde kalır, Python kuralları Python projenizde kalır ve evrensel kalıplar (örneğin "her zaman input'u doğrula") global olarak paylaşılır.
| Özellik | v2.0 | v2.1 |
|---|---|---|
| Depolama | Global (~/.claude/homunculus/) | Proje kapsamlı (projects/<hash>/) |
| Kapsam | Tüm instinct'ler her yerde geçerli | Proje kapsamlı + global |
| Tespit | Yok | git remote URL / repo path |
| Yükseltme | Yok | Proje → 2+ projede görülünce global |
| Komutlar | 4 (status/evolve/export/import) | 6 (+promote/projects) |
| Çapraz proje | Kontaminasyon riski | Varsayılan olarak izole |
| Özellik | v1 | v2 |
|---|---|---|
| Gözlem | Stop hook (oturum sonu) | PreToolUse/PostToolUse (%100 güvenilir) |
| Analiz | Ana bağlam | Arka plan agent'ı (Haiku) |
| Granülerlik | Tam skill'ler | Atomik "instinct'ler" |
| Güven | Yok | 0.3-0.9 ağırlıklı |
| Evrim | Doğrudan skill'e | Instinct'ler -> kümeleme -> skill/command/agent |
| Paylaşım | Yok | Instinct'leri dışa/içe aktar |
Instinct küçük öğrenilmiş bir davranıştır:
---
id: prefer-functional-style
trigger: "yeni fonksiyonlar yazarken"
confidence: 0.7
domain: "code-style"
source: "session-observation"
scope: project
project_id: "a1b2c3d4e5f6"
project_name: "my-react-app"
---
# Fonksiyonel Stili Tercih Et
## Aksiyon
Uygun olduğunda sınıflar yerine fonksiyonel kalıpları kullan.
## Kanıt
- 5 fonksiyonel kalıp tercihinin gözlemlenmesi
- Kullanıcı 2025-01-15'te sınıf tabanlı yaklaşımı fonksiyonele düzelttiÖzellikler:
project (varsayılan) veya globalOturum Aktivitesi (bir git repo'sunda)
|
| Hook'lar prompt'ları + tool kullanımını yakalar (%100 güvenilir)
| + proje bağlamını tespit eder (git remote / repo path)
v
+---------------------------------------------+
| projects/<project-hash>/observations.jsonl |
| (prompt'lar, tool çağrıları, sonuçlar, proje) |
+---------------------------------------------+
|
| Gözlemci agent okur (arka plan, Haiku)
v
+---------------------------------------------+
| KALIP TESPİTİ |
| * Kullanıcı düzeltmeleri -> instinct |
| * Hata çözümleri -> instinct |
| * Tekrarlanan iş akışları -> instinct |
| * Kapsam kararı: project mi global mi? |
+---------------------------------------------+
|
| Oluşturur/günceller
v
+---------------------------------------------+
| projects/<project-hash>/instincts/personal/ |
| * prefer-functional.yaml (0.7) [project] |
| * use-react-hooks.yaml (0.9) [project] |
+---------------------------------------------+
| instincts/personal/ (GLOBAL) |
| * always-validate-input.yaml (0.85) [global]|
| * grep-before-edit.yaml (0.6) [global] |
+---------------------------------------------+
|
| /evolve kümeleme + /promote
v
+---------------------------------------------+
| projects/<hash>/evolved/ (proje kapsamlı) |
| evolved/ (global) |
| * commands/new-feature.md |
| * skills/testing-workflow.md |
| * agents/refactor-specialist.md |
+---------------------------------------------+Sistem mevcut projenizi otomatik olarak tespit eder:
CLAUDE_PROJECT_DIR env var (en yüksek öncelik)git remote get-url origin -- taşınabilir proje ID'si oluşturmak için hash'lenir (farklı makinelerde aynı repo aynı ID'yi alır)git rev-parse --show-toplevel -- repo path kullanan yedek (makineye özgü)Her proje 12 karakterlik bir hash ID alır (örn. a1b2c3d4e5f6). ~/.claude/homunculus/projects.json dosyasındaki kayıt dosyası ID'leri insanların okuyabileceği isimlerle eşler.
~/.claude/settings.json dosyanıza ekleyin.
Plugin olarak kuruluysa (önerilen):
~/.claude/settings.json içine ek hook bloğu eklemeyin. Claude Code v2.1+ eklentinin hooks/hooks.json dosyasını otomatik yükler; observe.sh zaten orada kayıtlıdır.
Daha önce observe.sh satırlarını ~/.claude/settings.json içine kopyaladıysanız, yinelenen PreToolUse / PostToolUse bloğunu kaldırın. Yinelenen kayıt hem çift çalıştırmaya yol açar hem de ${CLAUDE_PLUGIN_ROOT} çözümleme hatası üretir; bu değişken yalnızca eklentiye ait hooks/hooks.json girdilerinde genişletilir.
~/.claude/skills dizinine manuel kuruluysa, aşağıdakini ~/.claude/settings.json içine ekleyin:
{
"hooks": {
"PreToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh"
}]
}],
"PostToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh"
}]
}]
}
}Sistem ilk kullanımda dizinleri otomatik oluşturur, ancak manuel olarak da oluşturabilirsiniz:
# Global dizinler
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands},projects}
# Proje dizinleri hook bir git repo'sunda ilk çalıştığında otomatik oluşturulur/instinct-status # Öğrenilmiş instinct'leri göster (proje + global)
/evolve # İlgili instinct'leri skill/command'lara kümele
/instinct-export # Instinct'leri dosyaya aktar
/instinct-import # Başkalarından instinct'leri içe aktar
/promote # Proje instinct'lerini global kapsamına yükselt
/projects # Tüm bilinen projeleri ve instinct sayılarını listele| Komut | Açıklama |
|---|---|
/instinct-status | Tüm instinct'leri göster (proje kapsamlı + global) güvenle |
/evolve | İlgili instinct'leri skill/command'lara kümele, yükseltme öner |
/instinct-export | Instinct'leri dışa aktar (kapsam/alana göre filtrelenebilir) |
/instinct-import <file> | Kapsam kontrolü ile instinct'leri içe aktar |
/promote [id] | Proje instinct'lerini global kapsamına yükselt |
/projects | Tüm bilinen projeleri ve instinct sayılarını listele |
Arka plan gözlemcisini kontrol etmek için config.json dosyasını düzenleyin:
{
"version": "2.1",
"observer": {
"enabled": false,
"run_interval_minutes": 5,
"min_observations_to_analyze": 20
}
}| Anahtar | Varsayılan | Açıklama |
|---|---|---|
observer.enabled | false | Arka plan gözlemci agent'ını aktifleştir |
observer.run_interval_minutes | 5 | Gözlemcinin gözlemleri ne sıklıkla analiz ettiği |
observer.min_observations_to_analyze | 20 | Analiz çalışmadan önce minimum gözlem |
Diğer davranışlar (gözlem yakalama, instinct eşikleri, proje kapsamı, yükseltme kriterleri) instinct-cli.py ve observe.sh içindeki kod varsayılanları aracılığıyla yapılandırılır.
~/.claude/homunculus/
+-- identity.json # Profiliniz, teknik seviye
+-- projects.json # Kayıt: proje hash -> isim/path/remote
+-- observations.jsonl # Global gözlemler (yedek)
+-- instincts/
| +-- personal/ # Global otomatik öğrenilmiş instinct'ler
| +-- inherited/ # Global içe aktarılan instinct'ler
+-- evolved/
| +-- agents/ # Global oluşturulan agent'lar
| +-- skills/ # Global oluşturulan skill'ler
| +-- commands/ # Global oluşturulan komutlar
+-- projects/
+-- a1b2c3d4e5f6/ # Proje hash (git remote URL'den)
| +-- project.json # Proje başına metadata yansıması (id/name/root/remote)
| +-- observations.jsonl
| +-- observations.archive/
| +-- instincts/
| | +-- personal/ # Projeye özgü otomatik öğrenilmiş
| | +-- inherited/ # Projeye özgü içe aktarılan
| +-- evolved/
| +-- skills/
| +-- commands/
| +-- agents/
+-- f6e5d4c3b2a1/ # Başka bir proje
+-- ...| Kalıp Tipi | Kapsam | Örnekler |
|---|---|---|
| Dil/framework kuralları | project | "React hook'ları kullan", "Django REST kalıplarını takip et" |
| Dosya yapısı tercihleri | project | "Testler __tests__/ içinde", "Bileşenler src/components/ içinde" |
| Kod stili | project | "Fonksiyonel stil kullan", "Dataclass'ları tercih et" |
| Hata işleme stratejileri | project | "Hatalar için Result tipi kullan" |
| Güvenlik uygulamaları | global | "Kullanıcı input'unu doğrula", "SQL'i sanitize et" |
| Genel en iyi uygulamalar | global | "Önce testleri yaz", "Her zaman hataları işle" |
| Tool iş akışı tercihleri | global | "Edit'ten önce Grep", "Write'tan önce Read" |
| Git uygulamaları | global | "Conventional commit'ler", "Küçük odaklı commit'ler" |
Aynı instinct birden fazla projede yüksek güvenle göründüğünde, global kapsamına yükseltme adayıdır.
Otomatik yükseltme kriterleri:
Nasıl yükseltilir:
# Belirli bir instinct'i yükselt
python3 instinct-cli.py promote prefer-explicit-errors
# Tüm uygun instinct'leri otomatik yükselt
python3 instinct-cli.py promote
# Değişiklik yapmadan önizle
python3 instinct-cli.py promote --dry-run/evolve komutu ayrıca yükseltme adaylarını önerir.
Güven zamanla evrimleşir:
| Skor | Anlamı | Davranış |
|---|---|---|
| 0.3 | Geçici | Önerilir ama zorunlu değil |
| 0.5 | Orta | İlgili olduğunda uygulanır |
| 0.7 | Güçlü | Uygulama için otomatik onaylanır |
| 0.9 | Neredeyse kesin | Temel davranış |
Güven artar şu durumlarda:
Güven azalır şu durumlarda:
"v1 gözlem için skill'lere güveniyordu. Skill'ler olasılıksaldır -- Claude'un yargısına göre zamanın ~%50-80'inde tetiklenirler."
Hook'lar %100 deterministik olarak tetiklenir. Bu şu anlama gelir:
v2.1, v2.0 ve v1 ile tamamen uyumludur:
~/.claude/homunculus/instincts/ içindeki mevcut global instinct'ler hala global instinct olarak çalışır~/.claude/skills/learned/ skill'leri hala çalışırInstinct tabanlı öğrenme: Claude'a kalıplarınızı öğretmek, her seferinde bir proje.
© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in docs/tr/skills/continuous-learning-v2 of affaan-m/ECC.
Open the folder on GitHubat commit ef648e0
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in affaan-m/ECC, which our catalogue first saw on October 7, 2026.
Continuous Learning V2 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Continuous Learning V2 this skillaffaan-m/ECC | 276k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Continuetelegramdesktop/tdesktop | 33k | 2 repos | ~9.4k | Automated safety check: Pass | GPL-3.0 | |
| Agent Runtime Lifecycle Hookslobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Continuityparcadei/Continuous-Claude-v3 | 3.9k | 1 repos | ~292 | Automated safety check: Notes | MIT | |
| Agentmemory Capture Hooksrohitg00/agentmemory | 29k | — | ~444 | Automated safety check: Pass | Apache-2.0 | |
| Crush Hook Writercharmbracelet/crush | 29k | — | ~1.8k | Automated safety check: Pass | Custom licence |
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
lobehub/lobehub
Registers lifecycle hooks on an agent run to observe, mock or intervene at each step, dispatching them in the order they were registered.
parcadei/Continuous-Claude-v3
Problem-solving strategies for continuity in real analysis. An agent skill from parcadei/Continuous-Claude-v3.
rohitg00/agentmemory
Describes the lifecycle hooks in the agentmemory Claude Code plugin that record observations automatically, and what to check when observations go missing.
charmbracelet/crush
Helps write, debug and configure Crush hooks in crush.json that block, approve or rewrite tool calls before they run.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
affaan-m/ECC
Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.
affaan-m/ECC
Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.
affaan-m/ECC
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
affaan-m/ECC
Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.
affaan-m/ECC
Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces.
affaan-m/ECC
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. Continuous Learning V2 is an agent skill from affaan-m/ECC. Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi.
Run `npx skills add affaan-m/ECC --skill continuous-learning-v2 -a claude-code`. Or copy the skill folder (docs/tr/skills/continuous-learning-v2 in affaan-m/ECC) into .claude/skills/continuous-learning-v2 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add affaan-m/ECC --skill continuous-learning-v2 -a codex`. Or copy the skill folder (docs/tr/skills/continuous-learning-v2 in affaan-m/ECC) into .agents/skills/continuous-learning-v2 in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill continuous-learning-v2 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/continuous-learning-v2, .gemini/skills/continuous-learning-v2, .github/skills/continuous-learning-v2 and .opencode/skills/continuous-learning-v2 in your project.
Going by SKILL.md and its folder, Continuous Learning V2 needs the command-line tools its instructions call (python3 and git). Our summary lists: Python 3.
SKILL.md names 2 domains. As links in the text: github.com and x.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Continuous Learning V2 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Continuous Learning V2: Continue (telegramdesktop/tdesktop, 33k stars), Agent Runtime Lifecycle Hooks (lobehub/lobehub, 83k stars), Continuity (parcadei/Continuous-Claude-v3, 3.9k stars) and Agentmemory Capture Hooks (rohitg00/agentmemory, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 275,546 GitHub stars. The repository holds 673 skills in this directory. The repository was last updated on October 5, 2026.
Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.