Pith Number

pith:LRAFZOQ3

pith:2026:LRAFZOQ3XVEAFU4ICVSRUH7GAC

not attested not anchored not stored refs resolved

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces

Bangzheng Pu, Dong Dong, Duling Xu, Jialin Li, Jiawei Guan, Zaifeng Pan, Zheng Chen

SkillSmith compiles agent skills offline into minimal boundary-guided interfaces to cut redundant context and reasoning in LLM systems.

arxiv:2605.15215 v1 · 2026-05-12 · cs.AI · cs.SE

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LRAFZOQ3XVEAFU4ICVSRUH7GAC}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On SkillsBench, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills; compiled artifacts from a stronger model can be reused by a smaller runtime model to improve accuracy where raw skill interpretation fails.

C2weakest assumption

The extraction of fine-grained operational boundaries from skill descriptions is both feasible and lossless enough that the resulting minimal interfaces preserve all task-relevant behavior without requiring the agent to fall back to full skill text.

C3one line summary

SkillSmith is a boundary-first compiler-runtime system that turns skill packages into minimal executable interfaces, cutting token usage 57%, thinking iterations 43%, and solve time 51% versus raw skill injection on SkillsBench.

References

30 extracted · 30 resolved · 7 Pith anchors

[1] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances 2022 · arXiv:2204.01691

[2] Equipping agents for the real world with agent skills

[3] Agent skills 2026

[4] Introducing Claude Opus 4.7 2026

[5] Prompting is programming: A query language for large language models.Proceedings of the ACM on Programming Languages, 7(PLDI):1946–1969, 2023 1946

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:46.682544Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c

Aliases

arxiv: 2605.15215 · arxiv_version: 2605.15215v1 · doi: 10.48550/arxiv.2605.15215 · pith_short_12: LRAFZOQ3XVEA · pith_short_16: LRAFZOQ3XVEAFU4I · pith_short_8: LRAFZOQ3

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/LRAFZOQ3XVEAFU4ICVSRUH7GAC \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 5c405cba1bbd4802d38815651a1fe6008c28210b2ed35182e057bc2e3ac2a38c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a77aced08f6a82e033946ac1a51cbcdfdbcca0b2542e5663e3304a00369b48af",
    "cross_cats_sorted": [
      "cs.SE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-12T09:25:25Z",
    "title_canon_sha256": "aed4f347a90ff71451c9203a3f07c72dd0d9d726d995daa7603beca7db96f8c0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15215",
    "kind": "arxiv",
    "version": 1
  }
}