Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Permanent Learning Protocol · avizmarlon | DecimalAI

agent toolingby avizmarlon

Permanent Learning Protocol

avizmarlon/permanent-learning-protocol

Source avizmarlon/agent-skills ↗License MIT

Permanent learning — AI agent proposes learnings from sessions, user approves in chat, integrations saved to auto-loaded files.

SkillScore96Maintained

Automatic

AI Engineer pack

Last verified 8/3/2026

What it changes

Passed 23 of 24 test cases with the skill, and 12 of 24 without it.

Without skill48%

With skill96%

Checks it passed that the model alone missed

The response identifies /learn as the manual trigger command.
The response assigns the [feedback] category type to user corrections.
The response specifies a target file location for each proposed learning.

and 16 more in the full report

13 fixed11 passed either way0 still failing1 broke

Pass-rate lift: +48 pp
Tokens: +48%
Agent turns: 0%
Response time: -50%

Model gemini-3.6-flashMeasured 8/3/2026v124 of 25 cases passed with skill · 24 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/avizmarlon-permanent-learning-protocol/SKILL.md https://app.decimal.ai/s/avizmarlon-permanent-learning-protocol/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add avizmarlon-permanent-learning-protocol, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/avizmarlon-permanent-learning-protocol/ and pins it in .decimal/skills.lock

decimalai skills add avizmarlon-permanent-learning-protocol

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/avizmarlon-permanent-learning-protocol/SKILL.md https://app.decimal.ai/s/avizmarlon-permanent-learning-protocol/SKILL.md

Raw file: /s/avizmarlon-permanent-learning-protocol/SKILL.md ↗ · machine-readable summary at /s/avizmarlon-permanent-learning-protocol.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

What explicit short command can a user type in chat to manually initiate the learning reflection protocol?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies /learn as the manual trigger command.	Missed	Passed

case-22 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md89 linessingle file

Permanent Learning Protocol

AI agents evolve only if learnings become part of their permanent instruction layer — auto-loaded in every future session. Session-only memory does not persist; only auto-loaded files survive across sessions.

This protocol moves learnings from chat to durable instruction files, with explicit user approval at each step. It prevents silent integration and ensures transparency.

1. Triggers

Automatic (natural session end — inferred from tone/context):

Farewell signals (goodbye, thanks + session ending, "signing off")
Gratitude + user disappears
Clear pivot to unrelated topic after coherent work block
Request to open new session / create handoff / create worktree for next phase
Session approaching context limit

Manual: User invokes skill /learn, or says variations like "consolidate what you learned this session" / "what did you discover today?"

2. Agent Action — Reflection + Proposal in Chat

Quick scan across learning categories:

User Correction (explicit or implicit — user ignored approach and did differently) → feedback type
Validated Pattern (user approved non-obvious approach without technical criticism, or called it "exactly right" / "perfect") → feedback type (good-pattern)
Technical Discovery (tool gotcha, API behavior, effective workaround) → discovery type
New Project/Context Fact (new platform, credential, person, decision) → project type
External Resource Pointer (documentation, dashboard, repo, reference) → reference type

Present in chat as numbered proposal — DO NOT save yet:

📚 Proposed permanent learnings:

1. [feedback] User prefers X over Y
   Location: global-instructions.md (global scope)
   Why: incident from session / concrete reason
   How to apply: when/where to use this pattern

2. [discovery] Tool Z has gotcha W
   Location: project docs or global reference
   Type: behavioral / limitation / workaround

Track record

Benchmark

23 / 24

test cases passed, vs 12 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

Imported

avizmarlon / agent-skills

skills/permanent-learning-protocol/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Permanent Learning Protocol

1. Triggers

2. Agent Action — Reflection + Proposal in Chat

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills