Ready to supercharge your AI agents?

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

Get Started Free →

Self-Improving Agent - Autonomous Learning Patterns · borghei | DecimalAI

agent toolingby borghei

Self-Improving Agent - Autonomous Learning Patterns

borghei/self-improving-agent

Source borghei/claude-skills ↗License NOASSERTION

Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously.

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/21/2026

What it changes

Passed 17 of 21 test cases with the skill, and 8 of 21 without it.

Without skill36%

With skill82%

Checks it passed that the model alone missed

The response lists `CLAUDE.md` as the top-level enforced rules layer.
The response passes `--rules` to specify the target rules directory location.
The response uses the `analyze` subcommand to process the feedback log entries.

and 8 more in the full report

10 fixed8 passed either way4 still failing0 broke

Pass-rate lift: +45 pp
Tokens: +43%
Agent turns: 0%
Response time: -33%

Model gemini-3.6-flashMeasured 8/21/2026v118 of 22 cases passed with skill · 21 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/borghei-self-improving-agent/SKILL.md https://app.decimal.ai/s/borghei-self-improving-agent/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add borghei-self-improving-agent, 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/borghei-self-improving-agent/ and pins it in .decimal/skills.lock

decimalai skills add borghei-self-improving-agent

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

curl -fsSL --create-dirs -o .claude/skills/borghei-self-improving-agent/SKILL.md https://app.decimal.ai/s/borghei-self-improving-agent/SKILL.md

Raw file: /s/borghei-self-improving-agent/SKILL.md ↗ · machine-readable summary at /s/borghei-self-improving-agent.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We need to check which entries in our local MEMORY.md file meet the bar to become permanent system rules. We have CLI tools configured under scripts/. Provide the exact shell command to check promotion candidate entries without applying changes.

What was checked, without and with the skill
Checked	Without skill	With skill
The response includes `--list-candidates` to preview promotion candidates without making changes.	Missed	Passed

case-04 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md88 lines11 filesincludes scripts

Self-Improving Agent - Autonomous Learning Patterns

Architectural patterns for AI agents that get better with use. Most agents are stateless -- they repeat mistakes because they cannot learn from their own execution. This skill closes that gap with patterns for feedback capture, memory curation, skill extraction, and regression detection. Key insight: auto-memory captures everything, but curation turns noise into knowledge.

Core Capabilities

Memory curation — a layered memory stack (CLAUDE.md → MEMORY.md → session), review protocol, and promotion criteria for graduating learnings into enforced rules.
Feedback loops — outcome classification, signal extraction, and a capture template that turn every task result into a structured learning.
Regression detection — metrics, thresholds, and a response protocol that flags performance degradation within a few sessions.
Skill extraction — criteria and a 4-step process to graduate proven patterns into standalone skill packages.
Meta-learning — adaptive capture strategy and anti-pattern detection so the agent learns what is worth learning.
Continuous calibration — confidence scoring and belief revision for resolving contradictions across learned knowledge.

When to Use

Building agents intended to improve over time rather than stay stateless.
Managing auto-memory (MEMORY.md) and deciding what to keep, promote, or retire.
Designing self-correcting feedback loops and regression alarms for agent behavior.
Graduating recurring solutions into reusable skill packages.

Clarify First

Before capturing or promoting learnings, confirm these inputs. If any is unknown or vague, ASK — do not assume:

Loop stage — remember / extract / promote / review (routes the sub-skill and the whole workflow)
Source data — which session logs, MEMORY.md, and rules dir to operate on (the subject the tools read and write)
Promotion bar — min occurrences / confidence threshold for graduating a learning into an enforced rule (--min-occurrences; decides what is kept vs discarded)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Sub-Skills

Compound sub-skill architecture — each file in skills/ handles one step of the improvement loop:

Sub-Skill	File	Purpose
Remember	`skills/remember.md`	Capture errors and learnings from current session
Extract	`skills/extract.md`	Extract reusable patterns from completed work
Promote	`skills/promote.md`	Graduate proven patterns to permanent rules
Review	`skills/review.md`	Audit memory health, prune stale entries

Track record

Benchmark

17 / 21

test cases passed, vs 8 / 21 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 — 8/3/2026

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

borghei / claude-skills

engineering/self-improving-agent/SKILL.md

View on GitHub ↗

License MIT + Commons ClauseImported 8/3/2026Version v1Bundled 10 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

self-improving-agentA universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.Close match+38 pp pass-rate lift

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

Self-Improving Agent - Autonomous Learning Patterns

Core Capabilities

When to Use

Clarify First

Sub-Skills

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills