New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Adapt Server Config

by ai-dynamo in ai-dynamo/aiconfigurator

Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests.

Apache-2.0Auto-check passed

Install Adapt Server Config

skills CLI
$ npx skills add ai-dynamo/aiconfigurator --skill adapt-server-config -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ai-dynamo/aiconfigurator adapt-server-config --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ai-dynamo/aiconfigurator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/adapt-server-config .claude/skills/adapt-server-config && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
adapt-server-config
GitHub stars
455
Token cost
~828 tokens
SKILL.md length
284 words
Files
4 (incl. scripts, references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests.

  • Works in 4 steps: Explicit source fields. → Inferred canonical fields and the… → Missing fields and assumptions. → …
  • Adapting server configuration
  • SKILL.md covers Choose the workflow, Adapt a known format, Handle unknown formats and Run estimates only on explicit…
  • Runs Python scripts from its folder; calls uv

What it does

Adapt Server Config is an agent skill from ai-dynamo/aiconfigurator. Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests. Use when adapting server configuration, checking whether a recipe can be estimated, generating canonical request JSON, or explicitly running estimates from adapted requests.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/custom-mapping.md` and `scripts/adapt_config.py`).

The repository describes itself as: Offline optimization of your disaggregated Dynamo graph. The licence is Apache-2.0.

When your agent uses it

  • Adapting server configuration
  • Checking whether a recipe can be estimated
  • Generating canonical request JSON
  • Explicitly running estimates from adapted requests

Example prompts

  • “/adapt-server-config”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Explicit source fields.
  2. Inferred canonical fields and the evidence for each inference.
  3. Missing fields and assumptions.
  4. Every discovered operating point in source order.

What it can do on your machine

Read from SKILL.md and the folder at commit f254959. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Adapt Server Config loads about 828 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 284 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~828
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ai-dynamo/aiconfigurator at commit f254959, republished under its Apache-2.0 licence (© ai-dynamo). 284 words, ~828 tokens.

Download SKILL.mdSave it as .claude/skills/adapt-server-config/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
adapt-server-config
description
Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests. Use when adapting server configuration, checking whether a recipe can be estimated, generating canonical request JSON, or explicitly running estimates from adapted requests.

Adapt Server Config

Create versioned AIC estimate requests without silently dropping operating points. Keep adaptation separate from estimate execution.

Choose the workflow

  • InferenceX DB record plus benchmark row: use the helper with --format inferencex.
  • DynamoGraphDeployment with optional perf.yaml, or a concrete dynamo-ci SGLang benchmark recipe: use the helper with --format dynamo.
  • Existing canonical request: use the helper with --format request to validate it.
  • Any other format: follow custom-mapping.md. Do not pass it to a known-format adapter.

Adapt a known format

Run from the aiconfigurator repository root:

bash
uv run python .agents/skills/adapt-server-config/scripts/adapt_config.py \
  --format inferencex --config configs-record.json --benchmark benchmark-row.json \
  --overrides '{"backend_version":"0.19.0"}'
bash
uv run python .agents/skills/adapt-server-config/scripts/adapt_config.py \
  --format dynamo --deploy deploy.yaml --perf perf.yaml \
  --overrides '{"system_name":"h200_sxm"}'

The helper prints an ordered adaptation report. Preserve every outcome, including rejected points and warnings. Treat any rejection as unresolved; do not repair it with guesses.

For benchmark cookbooks or Slurm command templates, require a rendered concrete recipe or DynamoGraphDeployment. For Helm inputs, require a rendered DynamoGraphDeployment; the matching unrendered benchmark-values.yaml can supply literal toolPipeline workload points through --perf. Do not evaluate templates or infer runtime parameters.

The helper validates adapted requests against both the Python model and packaged JSON Schema. Use --output PATH to save the report.

Handle unknown formats

Read custom-mapping.md. Inspect the source, then show the user:

  1. Explicit source fields.
  2. Inferred canonical fields and the evidence for each inference.
  3. Missing fields and assumptions.
  4. Every discovered operating point in source order.

Obtain confirmation before creating canonical request JSON. After confirmation, create aic-estimate-request/1.0.0 JSON and validate it:

bash
uv run python .agents/skills/adapt-server-config/scripts/adapt_config.py \
  --format request --request request.json

Do not add heuristic behavior to the SDK. Do not infer missing model identity, system, workload, concurrency, or speculative-token acceptance without confirmation.

Run estimates only on explicit request

Adaptation never runs an estimate. Add --run-estimate only when the user explicitly asks to execute estimates:

bash
uv run python .agents/skills/adapt-server-config/scripts/adapt_config.py \
  --format dynamo --deploy deploy.yaml --perf perf.yaml \
  --overrides '{"system_name":"h200_sxm"}' --run-estimate

Never execute recipe shell commands. The SDK only parses literal configuration values.

© ai-dynamo, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in .agents/skills/adapt-server-config of ai-dynamo/aiconfigurator.

  • SKILL.md
  • agents/openai.yaml
  • references/custom-mapping.md
  • scripts/adapt_config.py

Open the folder on GitHubat commit f254959

Compare with similar skills

Adapt Server Config next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Adapt Server Config compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adapt Server Config this skillai-dynamo/aiconfigurator455—~828Automated safety check: PassApache-2.0
Dynamo Frontend Benchmarkai-dynamo/dynamo8.2k—~3.5kAutomated safety check: NotesApache-2.0
Benchmarkaffaan-m/ECC275k3 repos~654Automated safety check: PassMIT
Benchmarkaffaan-m/ECC275k—~412Automated safety check: PassMIT
Benchmarkaffaan-m/ECC275k—~330Automated safety check: PassMIT
Convertremotion-dev/remotion62k—~247Automated safety check: PassCustom licence

Similar skills

  • Dynamo Frontend Benchmark

    ai-dynamo/dynamo

    Benchmark and profile the Dynamo frontend (dynamo.frontend HTTP + tokenizer + KV router) against mock workers (dynamo.mocker).

    8.2k GitHub stars~3.5k tokensUpdated today
    Frontend & DesignAuto-check: notes

  • Benchmark

    affaan-m/ECC

    Measure performance baselines and detect regressions across browser Core Web Vitals (LCP, INP, CLS, page weight), API endpoint latency percentiles, and build/test feedback times, with before/after…

    275k GitHub starsUsed in 3 repos~654 tokens
    Frontend & DesignAuto-check passed

  • Benchmark

    affaan-m/ECC

    このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します. An agent skill from affaan-m/ECC.

    275k GitHub stars~412 tokensUpdated 3 days ago
    Auto-check passed

  • Benchmark

    affaan-m/ECC

    使用此技能测量性能基线，检测PR前后的回归，并比较堆栈替代方案。

    275k GitHub stars~330 tokensUpdated 3 days ago
    Auto-check passed

  • Convert

    remotion-dev/remotion

    Official

    Start the local @remotion/convert app and open it in the Codex browser.

    62k GitHub stars~247 tokensUpdated today
    Media & CreativeAuto-check passed

  • Dynamo Recipe Runner

    NVIDIA/skills

    Official

    Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes.

    3.5k GitHub stars~1.8k tokensUpdated today
    DevOps & CloudAuto-check passed

More from ai-dynamo/aiconfigurator

  • Aic Collector Op Development

    ai-dynamo/aiconfigurator

    Design, add, review, or modify AIC Collector operations and their case population.

    455 GitHub stars~3k tokensUpdated 20 days ago
    Auto-check passed

  • Aic Auto Collect

    ai-dynamo/aiconfigurator

    A skill your agent uses when running long AIC/aiconfigurator GPU perf auto-collection for a specific GPU/framework/frameworkversion, including draft-PR checkpoints, resumable collectxx.py runs…

    455 GitHub stars~6.9k tokensUpdated 20 days ago
    Auto-check passed

  • Aic Silicon Align

    ai-dynamo/aiconfigurator

    A skill your agent uses when validating AIC predictions against real GPU serving measurements and root-causing fidelity gaps (prediction-vs-measured issues, memory/concurrency mismatches, per-op…

    455 GitHub stars~1.2k tokensUpdated 20 days ago
    Auto-check passed

  • Aic Version Slots

    ai-dynamo/aiconfigurator

    A skill your agent uses when adding perf data for a new framework version, deciding which backendversion to query or pin in tests, bumping the maintained (current/previous) versions, retiring old…

    455 GitHub stars~878 tokensUpdated 20 days ago
    Auto-check passed

Questions about Adapt Server Config

What does Adapt Server Config do?

Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests. Adapt Server Config is an agent skill from ai-dynamo/aiconfigurator. Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests.

When should I use Adapt Server Config?

Adapt Server Config fits situations like: adapting server configuration; checking whether a recipe can be estimated; generating canonical request JSON; explicitly running estimates from adapted requests.

How do I install Adapt Server Config in Claude Code?

Run `npx skills add ai-dynamo/aiconfigurator --skill adapt-server-config -a claude-code`. Or copy the skill folder (.agents/skills/adapt-server-config in ai-dynamo/aiconfigurator) into .claude/skills/adapt-server-config in your project. Claude Code loads it when a task matches its description.

How do I install Adapt Server Config in Codex?

Run `npx skills add ai-dynamo/aiconfigurator --skill adapt-server-config -a codex`. Or copy the skill folder (.agents/skills/adapt-server-config in ai-dynamo/aiconfigurator) into .agents/skills/adapt-server-config in your project. Codex loads it when a task matches its description.

Can I use Adapt Server Config in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ai-dynamo/aiconfigurator --skill adapt-server-config -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adapt-server-config, .gemini/skills/adapt-server-config, .github/skills/adapt-server-config and .opencode/skills/adapt-server-config in your project.

What does Adapt Server Config need to run?

Going by SKILL.md and its folder, Adapt Server Config needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Adapt Server Config access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Adapt Server Config safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Adapt Server Config use?

Adapt Server Config is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adapt Server Config use?

About 828 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 461 tokens, read only when the agent opens those files.

What are the alternatives to Adapt Server Config?

Skills that share tags, products or a category with Adapt Server Config: Dynamo Frontend Benchmark (ai-dynamo/dynamo, 8.2k stars), Benchmark (affaan-m/ECC, 275k stars), Benchmark (affaan-m/ECC, 275k stars) and Benchmark (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adapt Server Config?

ai-dynamo (a GitHub organization) maintains it in ai-dynamo/aiconfigurator, which has 455 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 18, 2026.

Source: ai-dynamo/aiconfigurator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.