skillhone-optimization

A workflow for improving an agent skill through repeated planning, testing, diagnosis, and code changes. It also guides exploration of available tools and reference approaches before implementation.

In plain words
What is it for?
Starting and managing skill-improvement iterations, exploring alternative approaches, diagnosing failures, and implementing fixes through pull requests.
Why use it?
It gives an optimization effort a structured way to find weak points and turn them into targeted fixes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tencent/skillhone/skillhone-optimization
Any agent
npx skills add Tencent/SkillHone --skill skillhone-optimization
Clone the repo
git clone --depth 1 https://github.com/Tencent/SkillHone

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.02500
Opus 5 $0.00026 $0.01250
Sonnet 5 $0.00010 $0.00500
Haiku 4.5 $0.00005 $0.00250

Measured 3d ago against content hash ae7005144a2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillhone-optimization scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze_probe.py, scripts/write_observation.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

REST APIs directly with `curl` or handcrafted HTTP.
skills/skillhone-optimization/SKILL.md · 202 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 202 lines · 52 tokens per session scan A ae7005144a2d

Subscribe to this mod's changes

skillhone-optimization is a skill published in the GitHub repository Tencent/SkillHone (140 stars, last pushed 24d ago), with no licence file. It adds 52 tokens to every session and 2,500 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

a-evolve

Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…

aiming-lab/AutoResearchClaw · 100 tokens

flux-analyzer

Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.

aiming-lab/AutoResearchClaw · 44 tokens

statistical-method-design

Design statistical methods, baselines, diagnostics, variants, and ablations that directly address a formal problem formulation.

aiming-lab/AutoResearchClaw · 27 tokens

statistical-theory-analysis

Analyze theoretical properties of statistical methods under the formal formulation: identifiability, bias, variance, consistency, asymptotics, coverage, error bounds, robustness, and limitations.

aiming-lab/AutoResearchClaw · 41 tokens

literature-search

Systematic literature review methodology including search strategy, screening, and synthesis. Use when conducting literature reviews or writing background sections.

aiming-lab/AutoResearchClaw · 28 tokens

experimental-design

Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.

aiming-lab/AutoResearchClaw · 25 tokens