Borrowing it
Nothing to install: this file belongs to tile-ai/tilelang-ascend. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tile-ai/tilelang-ascend/ascendc_pto/.agents/skills/tilelang-skill-review/SKILL.mdgit clone --depth 1 https://github.com/tile-ai/tilelang-ascendWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-skill-review)<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-skill-review"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-skill-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-skill-review"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-skill-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.02195 |
| Opus 5 | $0.00049 | $0.01097 |
| Sonnet 5 | $0.00020 | $0.00439 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
tilelang-skill-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Review — TileLang-Ascend Skill 改进评审
聚合算子开发过程中产生的反馈，生成可勾选的改进建议表，让开发者控制哪些落到 SKILL.md。
1. 适用场景
| 场景 | 输入 | 输出 |
|---|---|---|
| 周期性评审 | .agents/skill-journal/*.md 中所有 status: pending 的 entry |
分组表格 + 评审快照 |
| 应用改动 | apply 1,3,5 |
修改对应 SKILL.md，更新 entry 状态 |
| 拒绝改动 | reject 2,4 |
仅更新 entry 状态为 rejected |
| 状态查询 | status |
各 skill 的 pending / applied / rejected 计数 |
2. 核心约束
- 永远不直接修改 SKILL.md，除非用户用
apply明确勾选 - 评审范围覆盖全部 skill：
glob .agents/skills/**/SKILL.md自动发现，不硬编码 - rejected 的 entry 不删除：保留供后续频次累计判断（"反复被拒但反复出现"是改 skill 的强信号）
- 所有更改最终落在文本文件：可
git diff/git checkout回退，不需要数据库
3. 输入参数解析
skill 调用时若带 args，按以下规则解析：
| args 形式 | 含义 |
|---|---|
| 空 / 无参数 | 进入评审模式：扫描、聚合、输出表格、写快照 |
apply N[,N...] |
应用模式：对评审表中编号 N 的行应用改动 |
apply all |
应用全部 pending 改动（高风险，需二次确认） |
reject N[,N...] |
拒绝模式：仅标记为 rejected，不改 SKILL.md |
add |
添加模式（交互式）：开发者主动反馈，逐个问 7 个字段后写入 manual-{date}.md |
add <text> |
添加模式（快速式）：吃自由文本，自动补全字段后让开发者确认 |
status |
列出每个 skill 的 pending/applied/rejected 计数 |
若 args 含义不明，进入评审模式并提示可用命令。
4. 评审模式工作流
步骤 1：发现所有 skill
glob .agents/skills/**/SKILL.md
建立 skill_path -> SKILL.md 绝对路径 映射，备后续 apply 用。
步骤 2：扫描 journal
glob .agents/skill-journal/*.md # 排除 README.md 和 reviews/ 目录
读取每个 journal 文件，提取：
- frontmatter（
op / created / skills_consulted） - 所有 entry 块（按
## Entry eN切分） - 每个 entry 的字段（target_skill / target_artifact / target_section / type / severity / status / observation / evidence / proposed_change）。
target_artifact缺省视为skill
只处理 status: pending 的 entry，其余跳过。
entry 解析细节（字段正则、source 字段处理、容错规则）查 references/entry-schema.md。
步骤 3：聚合 & 排序
按 (target_skill, target_artifact, target_section, type) 四元组分桶。target_artifact 必须参与分桶——同一 target_skill 下，改 SKILL.md 和改 troubleshooting.md 是不同的改动单位，不可合并。同一桶内的 entry 合并：
- 频次 = entry 数量
- 严重度 = 取最高（high > medium > low）
- 来源 = 同桶内含 developer 来源就标
👤+🤖（混合）；纯 developer 标👤；纯 agent 标🤖 - 证据 = 合并所有 evidence（用
;分隔，仅保留前 3 条） - 提案 = 取频次最高的 proposed_change，其它列为补充
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 183 lines · 98 tokens per session scan A 445635cac58d
tilelang-skill-review is a skill published in the GitHub repository tile-ai/tilelang-ascend (363 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,195 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…