CtrlK
BlogDocsLog inGet started
Tessl Logo

mflux-debugging

Debug MLX ports by comparing against a PyTorch/diffusers reference via exported tensors/images (export-then-compare).

62

Quality

72%

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 ./.cursor/skills/mflux-debugging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

This is a strong, actionable debugging runbook that supplies genuinely non-obvious domain knowledge with concrete code, commands, and a sequenced workflow including validation feedback loops. The main weakness is mild redundancy across the Ground Rules, Artifact Hygiene, and Isolate sections, and the absence of any bundle files means progressive disclosure rests entirely on in-section organization.

Suggestions

Consolidate the recurring artifact-hygiene and do-not-commit reminders into a single section to remove redundancy and tighten conciseness.

Add a small executable tensor-compare helper snippet (np/torch vs mx with atol/rtol and first-N-elements printout) so the compare step is fully copy-paste ready.

Consider extracting the detailed inject-initial-latents procedure into a references file and summarizing it in SKILL.md to improve progressive disclosure for this longer-than-50-line skill.

DimensionReasoningScore

Conciseness

The body is dense with novel domain knowledge (RNG parity gotchas, MPS NaN behavior, scheduler indexing, the inject-initial-latents trick) and avoids explaining basics Claude already knows, though artifact-hygiene reminders recur across several sections and could be tightened.

4 / 5

Actionability

Provides executable code (the randn_tensor export snippet), specific commands (uv run python, HF_HUB_OFFLINE=1, /usr/bin/time -p), concrete file layout, and tolerance values, with only minor gaps (e.g., no full copy-paste compare script and some placeholder names).

4 / 5

Workflow Clarity

The default workflow is clearly sequenced (pick repro, decide checkpoints, export, compare) with a binary-search feedback loop and pass/fail validation, but validation is not framed as a hard gate before proceeding, keeping it just below a 5.

4 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-organized into clearly headed sections with only one-level references to sibling skills (mflux-model-porting, mflux-testing) and no nested reference chains, though the long Isolate procedure could conceivably be split into a reference file.

4 / 5

Total

16

/

20

Passed

Description

70%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 specific and highly distinctive for a narrow technical niche, but it lacks an explicit "Use when..." trigger clause, which limits its completeness score. Adding a natural-language trigger phrase would raise the completeness and trigger_term_quality dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when porting a model to MLX and you need to prove numerical parity against a PyTorch/diffusers reference."

Add common natural synonyms users might say (e.g. "MLX port", "parity check", "tensor comparison") to broaden trigger coverage.

Keep the existing concise action list; avoid padding it with generic debugging language.

DimensionReasoningScore

Specificity

Names the domain ("MLX ports", "PyTorch/diffusers reference") and several concrete actions ("comparing", "exported tensors/images", "export-then-compare"), with only minor coverage gaps.

4 / 5

Completeness

The "what" is clear (debug MLX ports via export-then-compare) but there is no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural technical terms users would say ("MLX", "PyTorch", "diffusers", "debug", "port") with good niche coverage, though a few natural variations are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (numerical parity debugging of MLX ports against a PyTorch/diffusers reference) with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
filipstrand/mflux
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.