Ready to supercharge your AI agents?

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

Memory · kdlbs | DecimalAI

agent toolingby kdlbs

Memory

kdlbs/memory

Source kdlbs/kandev ↗License AGPL-3.0

Read, write, and summarize persistent Office memory when durable behavioral guidance or project knowledge should survive across agent sessions.

SkillScore61Maintained

Automatic

Knowledge Management pack

Last verified 8/19/2026

What it changes

Passed 9 of 14 test cases with the skill, and 4 of 14 without it.

Without skill30%

With skill61%

Checks it passed that the model alone missed

The command uses the --layer flag.
The command uses kandev memory get.
The command uses --layer operating.

and 6 more in the full report

7 fixed7 passed either way9 still failing0 broke

Pass-rate lift: +30 pp
Tokens: -15%
Agent turns: 0%
Response time: -34%

Model gemini-3.6-flashMeasured 8/19/2026v114 of 23 cases passed with skill · 14 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/kdlbs-memory/SKILL.md https://app.decimal.ai/s/kdlbs-memory/SKILL.md

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

decimalai skills add kdlbs-memory

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

curl -fsSL --create-dirs -o .claude/skills/kdlbs-memory/SKILL.md https://app.decimal.ai/s/kdlbs-memory/SKILL.md

Raw file: /s/kdlbs-memory/SKILL.md ↗ · machine-readable summary at /s/kdlbs-memory.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I want to filter and inspect only the knowledge layer entries in my CLI context. Is the flag `--type knowledge` or `--category knowledge`? Write the exact CLI command.

What was checked, without and with the skill
Checked	Without skill	With skill
The command uses the --layer flag.	Missed	Passed
The command specifies knowledge as the layer.	Passed	Passed

case-08 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md38 linessingle file

Memory

Read and write persistent memory entries via the CLI. Memory is organized by layer:

operating -- behavioral guidelines, preferences, communication style
knowledge -- facts about people, projects, systems, decisions

Write Memory

$KANDEV_CLI kandev memory set --layer knowledge --key "people-alice" \
  --content "Alice is the frontend lead. Prefers TypeScript, reviews PRs quickly."

Read Memory

# List all memory entries
$KANDEV_CLI kandev memory get

# List by layer
$KANDEV_CLI kandev memory get --layer knowledge

# Get specific entry
$KANDEV_CLI kandev memory get --layer knowledge --key "people-alice"

Memory Summary

$KANDEV_CLI kandev memory summary

Guidelines

Use operating for persistent behavioral instructions (communication style, workflow preferences).
Use knowledge for learned facts that should persist across sessions.
Keep keys descriptive and hyphenated (e.g., people-alice, project-api-migration).
Memory entries are markdown files on disk and can be edited by the user directly.

Track record

Benchmark

9 / 14

test cases passed, vs 4 / 14 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

kdlbs / kandev

apps/backend/internal/office/configloader/skills/memory/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version 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

Memory

Write Memory

Read Memory

Memory Summary

Guidelines

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills