Hyperloom Setup
AMD-AGI/Hyperloom
Configures Hyperloom after pip install --target . An agent skill from AMD-AGI/Hyperloom.
Naming conventions for SGLang speculative decoding identifiers.
Install Speculative Naming
$ npx skills add sgl-project/sglang --skill speculative-naming -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sgl-project/sglang speculative-naming --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/speculative-naming .claude/skills/speculative-naming && rm -rf skills-srcUse ~/.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/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .claude/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-namingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sgl-project/sglang --skill speculative-naming -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sgl-project/sglang speculative-naming --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/speculative-naming .agents/skills/speculative-naming && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .agents/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sgl-project/sglang --skill speculative-naming -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sgl-project/sglang speculative-naming --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/speculative-naming .cursor/skills/speculative-naming && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .cursor/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sgl-project/sglang.git --path .agents/skills/speculative-naming--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sgl-project/sglang --skill speculative-naming -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sgl-project/sglang speculative-naming --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/speculative-naming .gemini/skills/speculative-naming && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .gemini/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sgl-project/sglang speculative-namingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sgl-project/sglang --skill speculative-naming -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/speculative-naming .github/skills/speculative-naming && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .github/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sgl-project/sglang --skill speculative-naming -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sgl-project/sglang speculative-naming --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/speculative-naming .opencode/skills/speculative-naming && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "speculative-naming" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/speculative-naming into .opencode/skills/speculative-naming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speculative-naming", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
speculative-naming- GitHub stars
- 37k
- Used in
- 2 other repos
- Token cost
- ~1.6k tokens
- SKILL.md length
- 599 words
- Files
- 1
- Skills in repo
- 32
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Naming conventions for SGLang speculative decoding identifiers.
- Reviewing identifiers in speculative decoding code — anything under python/sglang/srt/speculative/
- SKILL.md covers Rule 1 — Verb form, drop -ed, Rule 2 — The extra/bonus token…, Rule 3 — accept includes… and Rule 4 — num_ for counts; _ct…, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Related attention backends
What it does
Speculative Naming is an agent skill from sgl-project/sglang. Naming conventions for SGLang speculative decoding identifiers. Use when adding, renaming, or reviewing identifiers in speculative decoding code — anything under python/sglang/srt/speculative/, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering LLM inference and serving and Observability. It works with SGLang and Python. The repository describes itself as: SGLang is a high-performance serving framework for large language models and multimodal models. The licence is Apache-2.0.
When your agent uses it
- Reviewing identifiers in speculative decoding code — anything under python/sglang/srt/speculative/
- Related attention backends
- Scheduler accumulators
- Observability metrics
Example prompts
- “/speculative-naming”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit f620d73. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Speculative Naming loads about 1.6k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 599 words of instructions outside code blocks.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from sgl-project/sglang at commit f620d73, republished under its Apache-2.0 licence (© sgl-project). 599 words, ~1,569 tokens.
Download SKILL.mdSave it as
.claude/skills/speculative-naming/SKILL.md (or your agent's skills folder).- name
- speculative-naming
- description
- Naming conventions for SGLang speculative decoding identifiers. Use when adding, renaming, or reviewing identifiers in speculative decoding code — anything under `python/sglang/srt/speculative/`, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags.
Speculative Decoding — Naming Conventions
Apply this skill when adding, renaming, or reviewing identifiers in speculative decoding code (anything under python/sglang/srt/speculative/, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags).
Rule 1 — Verb form, drop -ed
Use the verb form accept everywhere. Don't use the past-participle form accepted.
| Don't | Do |
|---|---|
num_accepted_tokens | num_accept_tokens |
accepted_indices | accept_indices |
accepted_token_ids | accept_tokens (also see Rule 3) |
Rule 2 — The extra/bonus token is bonus_token / bonus_tokens
The "+1" token that the target model always emits in addition to verifying drafts is the bonus token. Use bonus_token / bonus_tokens per Rule 7.
| Don't | Do |
|---|---|
verified_id / verified_ids | bonus_token / bonus_tokens |
output_id / output_ids (when referring to the bonus) | bonus_token / bonus_tokens |
req.output_ids (the full output history of a request) is unrelated and stays as is.
Rule 3 — accept includes bonus; correct excludes bonus
The semantic distinction lives in the verb, not the noun. Don't enumerate noun pairs.
| Verb | Meaning |
|---|---|
accept_* | Includes the bonus token |
correct_* | Drafts only, no bonus |
Pair with whatever noun fits the data (tokens, drafts, indices, …). No required pairing, but preferred default nouns: accept_tokens and correct_drafts — correct semantically describes drafts (what got verified), accept describes the resulting token sequence (incl. bonus).
| Form | Meaning |
|---|---|
accept_tokens / accept_indices | Include bonus |
correct_drafts | Drafts only, no bonus |
num_accept_tokens | Count incl. bonus |
num_correct_drafts | Count excl. bonus |
Exception: accept_rate / accept_length follow paper convention
These two metric names are entrenched in the spec-decoding literature and in external-facing fields (meta_info, Prometheus). Their semantics are paper-defined, not Rule-3-defined:
| Name | Paper term | Bonus? | Definition |
|---|---|---|---|
accept_rate | $\alpha$ (Leviathan 2023) | No | per-draft-token acceptance probability = correct_drafts / proposed_drafts |
accept_length | $\tau$ (EAGLE) | Yes | avg tokens per verify step = completion_tokens / verify_ct |
Internal counters still follow Rule 3 strict semantics: num_correct_drafts (no bonus), num_accept_tokens (with bonus).
Rule 4 — num_ for counts; _ct for counters; _rate for rates; no prefix for IDs
Each form has its own marker. Never mix (no num_X_ct, no num_accept_rate).
| Form | Pattern | Meaning | Examples |
|---|---|---|---|
| Count | num_X | Snapshot quantity at one point in time (often a tensor or scalar) | num_accept_tokens, num_correct_drafts, num_proposed_drafts |
| Counter | X_ct | Monotonically incrementing accumulator over time | spec_verify_ct, forward_ct |
| Rate / ratio | X_rate | Fractional value in [0, 1] | accept_rate |
| Tokens / content array | no prefix | The actual token data, not a count | accept_tokens, correct_drafts, bonus_token |
Show full SKILL.md (239 more words)Show less
Rule 5 — Drop redundant _token_id / _token_ids suffix in spec scope
_id / _ids and _token / _tokens are both fine. But don't combine — _token_id / _token_ids is redundant inside spec decoding, because spec code only ever deals with vocab integers.
The semantic differs by scope:
| Scope | Example | What _token_id means |
|---|---|---|
| Framework / multimodal / tokenizer | image_token_id, pad_token_id, eos_token_id, mask_token_id, bos_token_id | A specific named/role token's vocab ID. The prefix names the role; _token_id says it's the integer ID for that role. Both halves carry information. |
| Spec decoding | accepted_token_ids, curr_token_id, out_token_ids | Redundant. Spec only deals with vocab integers; _id adds nothing beyond _token. |
Renames
| Don't | Do |
|---|---|
accepted_token_ids | accept_tokens (Rule 1 + 3) |
curr_token_id | current_token |
out_token_ids | out_tokens |
_resolve_spec_overlap_token_ids | _resolve_spec_overlap_tokens |
Rule 6 — Singular vs plural
Plural for any non-scalar tensor ([bs]-shaped, flat, or multi-dim); singular only for scalars (kernel tl.load results, single-int locals). Applies to all spec-decoding tensors (tokens, indices, etc.).
accept_tokens: torch.Tensor # [total_accepted] flat - plural
accept_indices: torch.Tensor # [bs, num_draft_tokens] - plural
draft_tokens: torch.Tensor # [bs * num_draft_tokens] flat - plural
bonus_tokens: torch.Tensor # [bs] - plural
accept_token = tl.load(...) # int32 scalar in a kernel iteration - singular
bonus_token = tl.load(...) # int32 scalar inside a kernel - singularOut of scope (these names stay as is)
These rules apply to spec-decoding-specific identifiers. Pre-existing or framework-level names are kept.
- PyTorch / ecosystem:
seq_lens,extend_seq_lens,cu_seqlens_q - Framework / multimodal vocab:
image_token_id,pad_token_id,eos_token_id,mask_token_id,hot_token_id,bos_token_id,topk_id - Request-level state:
req.input_ids,req.output_ids,req.origin_input_ids,next_token_ids(model_runner.sampleoutput) - Frozen C++ kwargs:
accept_token_num(sgl-kernel) - Non-token IDs:
req_id,gpu_id,layer_id,program_id _len/_lensnames:num_Xis preferred for counts (Rule 4), but_len/_lensnames are acceptable. Triton kernel params in particular often use_lens/_lento align with the PyTorch ecosystem (seq_lens,cu_seqlens_q). Rule 1 still requires the-ed-less form (accept_lengthOK,accepted_lengthnot).
© sgl-project, 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
Just SKILL.md in .agents/skills/speculative-naming of sgl-project/sglang.
Open the folder on GitHubat commit f620d73
Used in 2 other repositories
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in sgl-project/sglang, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Speculative Naming 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Speculative Naming this skillsgl-project/sglang | 37k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Hyperloom SetupAMD-AGI/Hyperloom | 218 | — | ~7.2k | Automated safety check: Notes | Custom licence | |
| Dstack Prototypingdstackai/dstack | 2.3k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 | |
| One EvalOpenDCAI/One-Eval | 165 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Agent Kill Switchvivekchand/clawmetry | 426 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Clawmetry Selfcheckvivekchand/clawmetry | 426 | — | ~515 | Automated safety check: Pass | MIT |
Similar skills
Dstack Prototyping
dstackai/dstack
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.
One Eval
OpenDCAI/One-Eval
驱动 One-Eval 对 API 或本地模型做端到端评测，覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric，或生成图文评测报告时使用本 skill。
Agent Kill Switch
vivekchand/clawmetry
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.
Clawmetry Selfcheck
vivekchand/clawmetry
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.
Dstack Presets
dstackai/dstack
Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format.
More from sgl-project/sglang
All 32 skills in this repoSglang Prod Incident Triage
sgl-project/sglang
Replay-first debug flow for SGLang serving problems. An agent skill from sgl-project/sglang.
LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Babysit PR To Pass CI
sgl-project/sglang
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.
Compute Mamba Ratio
sgl-project/sglang
Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and…
Debug Distributed Hang
sgl-project/sglang
Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).
Env Var Conventions
sgl-project/sglang
Conventions for SGLang environment variables — where to define, how to access, how to name, and how to deprecate.
Related
Categories
Questions about Speculative Naming
What does Speculative Naming do?
Naming conventions for SGLang speculative decoding identifiers. Speculative Naming is an agent skill from sgl-project/sglang. Naming conventions for SGLang speculative decoding identifiers.
When should I use Speculative Naming?
Speculative Naming fits situations like: reviewing identifiers in speculative decoding code — anything under python/sglang/srt/speculative/; related attention backends; scheduler accumulators; observability metrics.
How do I install Speculative Naming in Claude Code?
Run `npx skills add sgl-project/sglang --skill speculative-naming -a claude-code`. Or copy the skill folder (.agents/skills/speculative-naming in sgl-project/sglang) into .claude/skills/speculative-naming in your project. Claude Code loads it when a task matches its description.
How do I install Speculative Naming in Codex?
Run `npx skills add sgl-project/sglang --skill speculative-naming -a codex`. Or copy the skill folder (.agents/skills/speculative-naming in sgl-project/sglang) into .agents/skills/speculative-naming in your project. Codex loads it when a task matches its description.
Can I use Speculative Naming 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 sgl-project/sglang --skill speculative-naming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speculative-naming, .gemini/skills/speculative-naming, .github/skills/speculative-naming and .opencode/skills/speculative-naming in your project.
What does Speculative Naming need to run?
SKILL.md names no scripts, command-line tools or credentials: Speculative Naming is instructions for the agent only. Our summary lists: Python 3.
Does Speculative Naming access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Speculative Naming 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. Review the folder before installing.
What licence does Speculative Naming use?
Speculative Naming 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 Speculative Naming use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Speculative Naming?
Skills that share tags, products or a category with Speculative Naming: Hyperloom Setup (AMD-AGI/Hyperloom, 218 stars), Dstack Prototyping (dstackai/dstack, 2.3k stars), One Eval (OpenDCAI/One-Eval, 165 stars) and Agent Kill Switch (vivekchand/clawmetry, 426 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Speculative Naming?
sgl-project (a GitHub organization) maintains it in sgl-project/sglang, which has 36,907 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 9, 2026.
Source: sgl-project/sglang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.