CtrlK
BlogDocsLog inGet started
Tessl Logo

akg-agents

代理执行 AKG 算子任务。先检查固定仓库与分支;若 `~/.akg/check_env.md` 不存在则强制 `FULL_SETUP=true`;忽略所有 `akg_cli` 检查和使用;后端代码生成直接执行 `run_workflow.py --workflow kernelgen`。

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/akg-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is highly actionable with executable commands, a well-sequenced workflow, and clean one-level references; its main weakness is redundancy where the same hard rules are restated across multiple sections.

Suggestions

State the akg_cli-ignore and foreground-execution rules once in 硬规则 and reference them from 执行顺序/输出要求 rather than repeating them verbatim, to tighten token efficiency.

Consider extracting the lengthy 输出要求 checklist into a short checklist reference if the restated rules are kept, preserving the overview's leanness.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but the akg_cli-ignore and foreground-execution rules are restated across 硬规则, 代码生成, 执行顺序, and 输出要求, so not every token earns its place.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands — git clone, git rev-parse/branch checks, and the complete run_workflow.py --workflow kernelgen invocation with all flags.

3 / 3

Workflow Clarity

A clear 12-step execution order with explicit validation checkpoints (check_env.md existence, settings.json configuration gate) and a feedback loop requiring honest failure reporting before any fallback.

3 / 3

Progressive Disclosure

A single well-sectioned file with clearly signaled, one-level-deep references to akg-env-setup and op-task-extractor SKILL.md; no nested or deeply chained references.

3 / 3

Total

11

/

12

Passed

Description

67%

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 distinctive with concrete actions and a clear AKG niche, but it omits an explicit 'Use when...' trigger clause and leans on internal config jargon rather than natural user terms.

Suggestions

Add an explicit 'Use when...' (使用时机) clause naming natural user phrasings such as writing, modifying, or tuning AKG operators.

Replace or supplement internal flags (FULL_SETUP, akg_cli, check_env.md) in the description with user-facing trigger terms so the trigger_term_quality reaches 3.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — checking repo/branch, forcing FULL_SETUP=true, ignoring akg_cli checks, and executing run_workflow.py --workflow kernelgen — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

The 'what' is explicit, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

'AKG 算子任务' is a natural domain trigger, but the remainder (FULL_SETUP=true, akg_cli, check_env.md) is internal flag jargon rather than terms a user would naturally say, missing common variations.

2 / 3

Distinctiveness Conflict Risk

It targets a clear, narrow niche (AKG kernelgen operator tasks) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

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
XiaoLuoLYG/GOD
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.