Skills

Skills are the unit of reusable agent knowledge in DecimalAI. The SDK has two flows: sync (push your local SKILL.md files to the platform during install()) and pull (download platform skills to disk). At runtime, the Skill Router is what your agent talks to — it picks which skills to load on every query and emits the telemetry that powers per-skill effectiveness. This page covers the SDK surface; the Router page covers strategies, response shape, and the routing-id → trace join.

Sync skills from code to platform

from decimalai.openai_agents import install

install(
    agent=agent,
    skill_dirs=["./skills/"],  # scans for SKILL.md files
)
# Skills are auto-synced to platform on install()

The skill_dirs argument is supported by all framework install() calls — OpenAI Agents, LangChain, LlamaIndex, etc.

Pull skills from platform to disk

from decimalai import SkillRouter

router = SkillRouter(api_key="dai_sk_...", base_url="https://api.decimal.ai")
result = router.pull_missing(
    local_skill_names={"existing_skill"},
    agents=["my-agent"],
)
print(f"Pulled {result['pulled']} new skills")

For consumers who just want to read a published skill without forking it into an org, the CLI’s pull command works against the public registry endpoint with no auth:

# Writes ./code-review-security/SKILL.md
decimalai skills pull code-review-security

# Or print to stdout for piping into another tool
decimalai skills pull pdf --stdout > pdf.md

pull is read-only — no fork is created, no activation telemetry is recorded. Use install() (Python) once you sign up to get the full lifecycle. In the SDK, install() = fork + write SKILL.md to disk (plus per-trace activation tracking); use fork() for the workspace copy without the disk write.

`SkillRouter` — full CRUD

For programmatic skill management, instantiate SkillRouter directly:

from decimalai import SkillRouter

router = SkillRouter(api_key="dai_sk_...", base_url="https://api.decimal.ai")

# Registry browsing
menu = router.get_menu(agent_name="support-agent")

# Smart routing — let the router pick the best skill for a query
chosen = router.smart_route(query="How do I cancel my subscription?",
                            agent_name="support-agent")

# CRUD
router.create_skill(name="refund_policy", description="Refund policy", body_markdown="...")
router.list_skills()
router.get_skill("refund_policy")
router.update_skill("skill_abc", body_markdown="...")
router.delete_skill("skill_abc")

# Bulk — sync_skills takes a list of skill dicts
router.sync_skills([{"name": "refund_policy", "body_markdown": "..."}])
router.export_to_disk(agents=["claude-code"])  # writes into the project's agent skill dirs
router.pull_missing(local_skill_names={"foo"}, agents=["support-agent"])

See the Skills API reference for the underlying REST surface.

On-demand bodies: the `load_skill` tool

The routed menu carries names + descriptions; bodies load on demand. On the openai_agents and pydantic_ai adapters, install(enable_skill_loader=True) also registers a native load_skill(name) tool on every agent — the model reads the menu, calls the tool with a skill’s exact name, and the full instructions arrive as the tool result mid-turn. Nothing to wire manually:

import decimalai
from decimalai.openai_agents import install

decimalai.init()
install(enable_skill_loader=True)   # menu injection + load_skill tool

# ... the model can now call load_skill("refund-policy") on its own

Body loads are budgeted per turn so they can’t blow the context window:

`SkillRouter` knob	Default	Effect
`max_loaded_bodies`	3	Max distinct bodies per turn; further loads get a refusal message
`body_token_budget`	6000	Estimated-token cap across all loaded bodies
`per_body_char_limit`	8192	Each body is trimmed to this (server- and client-side)
`body_load_deadline_s`	20	Wall-clock cap on body round-trips within a turn

Re-loading an already-loaded skill is free. Each load is recorded on the trace (skills_loaded_by_agent), closing the offered-vs-loaded join server-side. The anthropic and langchain adapters have no tool loop to route a result through, so they stay on prompt injection — their inject_skill_body=True path applies the same trim and budget. Disable the tool everywhere with decimalai.init(load_skill_tool=False) or DECIMALAI_LOAD_SKILL_TOOL=0. You can also call the primitive directly:

router.load_skill("refund-policy")        # budgeted, returns "## Skill: ..." block
router.get_skill_body("refund-policy", max_chars=8192)  # raw fetch, server-side trim

Sync skills from code to platform

Pull skills from platform to disk

`SkillRouter` — full CRUD

On-demand bodies: the `load_skill` tool

What’s next

Skills guide

Skills Observability tutorial

​Sync skills from code to platform

​Pull skills from platform to disk

​Pull a public skill — no signup required

​SkillRouter — full CRUD

​On-demand bodies: the load_skill tool

​What’s next

Skills guide

Skills Observability tutorial

Sync skills from code to platform

Pull skills from platform to disk

Pull a public skill — no signup required

`SkillRouter` — full CRUD

On-demand bodies: the `load_skill` tool

What’s next