CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mamba-architecture

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace. Also covers RWKV (guides in references/).

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/model-architecture/mamba/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers strong, executable coverage of installation, model usage, pretrained loading, Mamba-1 vs Mamba-2 differences, and benchmarking, with a useful troubleshooting section. Its two real defects are broken progressive disclosure — most reference links are dead while real bundle files sit orphaned — and repetitive performance claims that inflate the token budget without adding information.

Suggestions

Fix the reference links to match the actual bundle: point Advanced topics at `references/architecture-details.md` (selective SSM math), `references/benchmarks.md` (performance), and a Mamba-2 section within the existing files, and add a link to `references/training-guide.md` so it is discoverable.

Deduplicate the "5× faster / no KV cache / linear scaling" claims into a single Performance section and remove the star count and paper dates or move them to a clearly dated Resources note.

Quote the version pin (`pip install "causal-conv1d>=1.4.0"`) so the install command is actually copy-paste executable, and either include the benchmark script in the bundle or note it must be run from the mamba GitHub repo.

DimensionReasoningScore

Conciseness

The body is mostly efficient code-first content, but the "5× faster inference" / "No KV cache" / "linear vs quadratic" claims are repeated across Quick start, Workflow 4 expected results, Advantages, Hardware requirements, and Performance sections, and time-sensitive details (paper dates, "⭐ 13,000+" stars) pad the Resources section — anchor 3, could be tightened but not severely verbose.

3 / 5

Actionability

Mostly executable, copy-paste-ready guidance: install commands, Mamba block usage, full LM config with generation, pretrained-model loading, and troubleshooting fixes. It falls short of anchor 5 because `pip install causal-conv1d>=1.4.0` is unquoted (bash treats `>=` as a redirect, so the command fails as written) and the benchmark workflow invokes `benchmarks/benchmark_generation_mamba_simple.py`, a path that does not exist in the skill bundle.

4 / 5

Workflow Clarity

Workflows 1–4 are clearly sequenced (install → basic block → LM → pretrained models → comparison → benchmarking) and the Common issues section provides error-recovery guidance (OOM → gradient checkpointing, load failure → use `MambaLMHeadModel.from_pretrained`). No explicit validation checkpoints exist, but the operations are non-destructive inference tasks, so this is a minor gap — anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Three of the four Advanced-topics links point to files that do not exist (`references/selective-ssm.md`, `references/mamba2-details.md`, `references/performance.md`), while the actual bundle files (`architecture-details.md`, `benchmarks.md`, `training-guide.md`) are never referenced from SKILL.md, and `rwkv/overview.md` chains into a further nested `references/rwkv/references/` level. Navigation to the bundle is factually broken, which is worse than the "not clearly signaled" state of anchor 3 and fits anchor 2's minimal effective structure.

2 / 5

Total

13

/

20

Passed

Description

65%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is informationally rich and highly distinctive, packing precise technical facts (complexity, d_state values, model sizes) into a short space. Its main weaknesses are the complete absence of "when to use" trigger guidance and the lack of any stated actions or capabilities, leaving a reader to infer what the skill does with the content.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with Mamba, state-space models (SSMs), RWKV, or when comparing linear-complexity architectures to Transformers for long-context work."

State at least one concrete action the skill supports (e.g. "Set up and run Mamba models, generate text with pretrained weights, and benchmark against Transformers") rather than only listing architecture facts.

Fold in natural synonyms such as "S4", "linear RNN", and "sequence modeling" so users phrasing the need differently still hit the skill.

DimensionReasoningScore

Specificity

The description is dense with concrete facts ("O(n) complexity vs Transformers' O(n²)", "Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head)", "Models 130M-2.8B on HuggingFace") but contains no verbs or actions describing what the skill actually does, matching anchor 3 (clear domain, not comprehensive on capabilities) rather than anchor 4 which requires several specific actions.

3 / 5

Completeness

The "what" is clear (a reference on Mamba's architecture and properties), but there is no "Use when..." clause or equivalent trigger guidance anywhere, capping completeness at 3 per the judging guidelines. It is not 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

Natural user terms are well covered: "Mamba", "state-space model", "SSM", "KV cache", "RWKV", "Transformers", "HuggingFace". It falls short of anchor 5 because common synonyms a user might say — "S4", "linear RNN", "sequence modeling", "long context" — are absent from the description itself.

4 / 5

Distinctiveness Conflict Risk

"Mamba-1... Mamba-2... Also covers RWKV" carves out a clear niche with distinct triggers (Mamba, SSM, state-space, RWKV) that virtually no other skill would claim, matching the anchor-5 example of a clear niche with minimal conflict risk.

5 / 5

Total

15

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 missing, 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 6 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

OpenLAIR/dr-claw

Path

skills/model-architecture/mamba/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.