agent toolingby ellmos-ai
Metacognitive Injectors
ellmos-ai/metacognitive-injectors
Metakognitive Injektoren und Selbstgesprächs-Strategien (Self-Talk, Metacognitive Auditing, Evaluator Hooks, Pre-Flight Checklists, State Persistence & Personas). Integriert Aktive Informationssuche (Systemgedächtnis Gardener & USMC), Rehearsal (Aktives Abrufen & Wiedergeben), Baddeleys Arbeitsgedächtnis (State + Hooks), Miyake Exekutivfunktionen sowie CBT/ACT therapeutische Strategien.
Code scan CleanIntent PassedContent Clean
Benchmark snapshot
Same tasks, with and without this skill.
Model gemini-3.6-flashMeasured 8/6/2026v1
- Pass-rate lift
- +55 pp
percentage-point change- Pass rate with skill
- 82%
27% without skill- Tokens
- +55%
vs. without skill- Agent turns
- 0%
vs. without skill
Usage
All-time distinct users and times used, across every version.
Read the skill
SKILL.md · instructions and conventions
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedellmos-ai / skills
skills/infrastructure/metacognitive-injectors/SKILL.md
View on GitHub ↗License MITImported 8/24/2026Version v1