Ready to supercharge your AI agents?

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

Get Started Free →

Team Admin — measured AI agent skill | DecimalAI

kdlbs/kandev-team-admin

NewSkillScoreMaintained

Manage the Office roster when delegating work, hiring agents, changing budgets or concurrency, retiring agents, or checking spend before approvals.

agent-toolingby kdlbs

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/kdlbs-kandev-team-admin/SKILL.md

decimalai skills pull kdlbs-kandev-team-admin --out .claude/skills/

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

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

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

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—+151% tokens0% turns9% of whole cases pass with skill (2/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-16	✗→✓	▲ Improved	78%	0%
case-04	✓→✗	▼ Worse	-60%	0%
case-06	✓→✗	▼ Worse	-63%	0%
case-05	✓→✓	＝ Same ✓	259%	0%
case-01	✗→✗	＝ Same ✗	-70%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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/kandev-team-admin/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version v1Bundled 4 files

Skill contents

references/

SKILL.md

Team Admin

Use this skill when you need fresh organization state or need to change the agent roster.

First checks

bash
$KANDEV_CLI kandev agents list
$KANDEV_CLI kandev budget get

Before hiring, confirm no existing idle specialist or worker already fits. Before approving budget grants, check workspace and per-agent spend.

Common actions

List and inspect agents: read references/team.md.
Hire a new worker, specialist, assistant, or reviewer: read references/hiring.md.
Rename, cap, or retire an agent: read references/agent-edit.md.
Review workspace or per-agent spend: read references/budget.md.

Guardrails

Do not hire for one-off work that an existing agent can handle.
Do not assign work to agents in pending_approval.
Do not silently pause or cap an over-budget agent. Leave a task comment explaining the reason first.

Want to see if kdlbs/kandev-team-admin would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.