CtrlK
BlogDocsLog inGet started
Tessl Logo

trae-native-debug

Maintain, debug, and recover MTGA's Trae native custom-model route. Use when Trae native integration fails, Trae updates shift ai_agent.dll hook offsets, errors such as 4028/4054/429 appear, native rewriter or SseOpenPayload URL rewriting needs diagnosis, or Codex needs to avoid repeating prior renderer-JS/private-protocol dead ends.

79

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a tight, actionable debugging runbook with concrete commands, a sequenced diagnostic workflow, and well-signaled one-level references that both exist. It assumes Claude's competence and adds only non-obvious domain knowledge, though explicit fix-validation loops live in the referenced recovery doc rather than the main flow.

DimensionReasoningScore

Conciseness

The body is lean — Operating Rules, a short Workflow, Known Stable Facts, and a Resources pointer — with no explanation of concepts Claude already knows; every section carries non-obvious domain detail (error-code meanings, byte patterns, file paths). Matches the score-3 'every token earns its place' anchor; not score 2 because there is no padded or unnecessary explanation to tighten.

3 / 3

Actionability

Quotes executable commands such as "uv run python -m modules.trae_patch.trae_native_sse_open_url_rewriter --help" and concrete scripts like "scripts/trae_patch/trae_native_byte_pattern.py", plus the literal byte pattern "48 8b 52 08 4d 8b 46 10 48 8d 8d 20 01 00 00" and call offset "0x0F". Matches the score-3 'fully executable commands; specific examples' anchor; not score 2 because guidance is concrete rather than pseudocode.

3 / 3

Workflow Clarity

Quotes a sequenced diagnostic flow: "1. Classify the failure before changing code" with an error-code table, then confirm path, then reproduce with smallest surface, then route to references on Trae-update or prior-approach uncertainty. The 'classify before changing code' gate and reproduce commands act as checkpoints; not score 2 because the sequence is explicit and gated rather than a bare step list.

3 / 3

Progressive Disclosure

The body is an overview that signals two one-level-deep references inline ("read references/update-recovery.md", "read references/native-route-map.md") and again in a Resources section; both files exist in ./references/ and are not nested further. Matches the score-3 'well-signaled one-level-deep references' anchor; not score 2 because content is appropriately split rather than inlined.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 uses third-person voice, names a precise niche, and pairs a clear what-statement with an explicit multi-scenario 'Use when' trigger clause. It is concise and free of vague fluff, though some terms (e.g. 'SseOpenPayload URL rewriting') are domain-jargon heavy.

DimensionReasoningScore

Specificity

Quotes "Maintain, debug, and recover MTGA's Trae native custom-model route" plus "needs diagnosis" — multiple concrete actions (maintain, debug, recover, diagnose) tied to a specific named route, matching the score-3 anchor that lists several specific concrete actions; not score 2 because it goes beyond naming only a domain and a couple of actions.

3 / 3

Completeness

Quotes the explicit "Use when ..." trigger clause plus the what-statement "Maintain, debug, and recover ... route", so both what it does and when to use it are explicit; not score 2 because the when is stated explicitly rather than merely implied.

3 / 3

Trigger Term Quality

Quotes "Use when Trae native integration fails, Trae updates shift ai_agent.dll hook offsets, errors such as 4028/4054/429 appear" — these are the exact terms a user of this domain would say (error codes, "Trae native", "ai_agent.dll"); not score 2 because coverage spans several natural trigger scenarios rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Quotes "MTGA's Trae native custom-model route" with narrow triggers (specific error codes, ai_agent.dll offsets) — a clear niche unlikely to fire for unrelated skills; not score 2 because the scope is highly specific rather than broadly overlapping.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing, 3 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
BiFangKNT/mtga
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.