Not in the top 1,000 by GitHub stars
GiaSip/giasip-skills
Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
locales/zh/skills/giasip-dispatch/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 7886a35b6e49
No earlier version was observed for comparison.
plugins/giasip/skills/research/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 7886a35b6e49
No earlier version was observed for comparison.
skills/giasip-dispatch/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 7886a35b6e49
No earlier version was observed for comparison.
skills/giasip-research/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 7886a35b6e49
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 7886a35b6e49168a5655fcc55ce6f1fc92a8895c
git clone --filter=blob:none --no-checkout https://github.com/GiaSip/giasip-skills.git .hotskills/giasip-giasip-skills && git -C .hotskills/giasip-giasip-skills checkout --detach 7886a35b6e49168a5655fcc55ce6f1fc92a8895c
# Copy each selected skill directory from .hotskills/giasip-giasip-skills into .claude/skills/<skill-name>/13GitHub stars
0stars in 7 days
4skills in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- giasip-dispatch
locales/zh/skills/giasip-dispatch - research
plugins/giasip/skills/research - giasip-dispatch
skills/giasip-dispatch - giasip-research
skills/giasip-research
How it works
giasip-dispatch
When your agent uses it
多模型调用器 — 把任务或 prompt 派发给其他 AI 模型（Codex / Gemini / Kimi / DeepSeek / 豆包 / Qwen / GLM / MiniMax）执行并取回结果。当你想用某个或某几个其他模型跑任务、需要多模型交叉对比验证、或想用更便宜的模型省钱时触发。提供两类调用通道：API 直调（只需 API key）和 CLI 调用（需本地装对应 CLI）。触发信号：「用 Kimi/Codex/Gemini 跑一下」「交给其他 AI」「换个模型试试」「让几个模型都看看」「这个不用最贵的模型」。
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
4,083 tokensWhen the skill is activated
Reference documents
6,404 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 脚本目录（Script Directory）
- 两类调用通道
- 通用纪律（所有 CLI 调用必读）
- 复杂度路由
- 调用方式
- 环境检查
- 多模型并行（交叉对比 / 多方验证）
- 执行参数
- Fallback 链
- 输出格式
- 回答持久化
- 脚本清单
Scripts executed separately
../../../../skills/giasip-dispatch/scripts/api-dispatch.sh../../../../skills/giasip-dispatch/scripts/codex-appserver.mjs../../../../skills/giasip-dispatch/scripts/dispatch-persist.mjs../../../../skills/giasip-dispatch/scripts/gemini-supervisor.sh../../../../skills/giasip-dispatch/scripts/kimi-dispatch.sh../../../../skills/giasip-dispatch/scripts/stop-review-gate.mjs
Files
../../../../.claude-plugin/marketplace.jsonasset521 bytes../../../../.claude-plugin/plugin.jsonasset398 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytesSKILL.mdcore13,986 bytes../../../../skills/giasip-dispatch/SKILL.mddoc17,605 bytes../../../../skills/giasip-dispatch/references/model-roster.mddoc5,643 bytes../../../../skills/giasip-dispatch/scripts/api-dispatch.shruns16,196 bytes../../../../skills/giasip-dispatch/scripts/codex-appserver.mjsruns15,103 bytes../../../../skills/giasip-dispatch/scripts/dispatch-persist.mjsruns4,724 bytes../../../../skills/giasip-dispatch/scripts/gemini-supervisor.shruns11,124 bytes../../../../skills/giasip-dispatch/scripts/kimi-dispatch.shruns10,866 bytes../../../../skills/giasip-dispatch/scripts/stop-review-gate.mjsruns5,129 bytes../../../../skills/giasip-research/FEEDBACK.mddoc168 bytes../../../../skills/giasip-research/SKILL.mddoc2,028 bytes
Read SKILL.md
> ✦ A **GiaSip** skill · part of the `giasip` toolkit · github.com/GiaSip
# /dispatch — 多模型调用器
把一个任务或 prompt 派发给其他 AI 模型执行，取回结果。这个 skill **只提供调用能力**——选哪个模型、单派还是多派，由你（或当前的 Claude）根据任务临场判断，本 skill 不内置选型偏好。
## 脚本目录（Script Directory）
**重要**：所有脚本都在**本 skill 目录**下的 `scripts/` 子目录里。
**Agent 准备 —— 跑下面任何命令前先做一次**：确定包含本 `SKILL.md` 的目录的绝对路径，export 为 `BASE_DIR`：
```bash
# 全局安装（最常见）；作为 plugin 安装时改用 plugin 缓存路径research
When your agent uses it
Use when the user asks to research, investigate, compare competitors, study a market or industry, check the current status of a regulation or policy, search literature, or simply look something up that needs external sources. Any question that requires fetching outside information triggers this skill. To verify specific claims in an existing report, use a dedicated verification pass instead.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
448 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,021 bytesSKILL.mdcore2,021 bytesSKILL.mdcore2,021 bytes
Read SKILL.md
> ✦ **GiaSip** · github.com/GiaSip/giasip-skills
# GiaSip Research
**Goal.** Get the user accurate information that answers *their* question. Accuracy is a hard constraint; breadth is a means (you must gather widely to hit the accurate parts).
**Method.** Split the question into 2–3 complementary facets and run one sub-agent per facet in parallel. Sub-agents only gather, they do not conclude. Each sub-agent stops after at most 15 searches/fetches and returns compact findings without writing files. The main agent then writes a single `report.md`: answer the user's questions one by one, list every entity found with its URL, keep the body under 200 lines, and end with a separate **"To verify"** section.
**Discipline (hard rules)**
- Every fact carries a source URL. Prefer official / owner primary sources; label source type (primary / third-party / media).
- If it cannot be found, write "not found" — never fill from memory. Dates are absolute. GitHub stars and timestamps come from `gh api` snapshots, not search-result pages.
- Read and write only inside the output directory. Never `rm -rf`.
- Before anything goes out under a real name, quotes a price, or states a legal/financial conclusion, run a verification pass on the claims.
giasip-dispatch
When your agent uses it
“Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific model, need multi-model cross-validation, or want to use a cheaper model.”
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
4,354 tokensWhen the skill is activated
Reference documents
1,558 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Script Directory
- Dispatch Channels
- General Discipline (must-read for all CLI calls)
- Complexity Routing
- Dispatch Methods
- Environment Check
- Multi-Model Parallel (cross-validation / multi-perspective)
- Execution Parameters
- Fallback Chain
- Output Format
- Response Logging
- Script Inventory
Scripts executed separately
scripts/api-dispatch.shscripts/codex-appserver.mjsscripts/dispatch-persist.mjsscripts/gemini-supervisor.shscripts/kimi-dispatch.shscripts/stop-review-gate.mjs
Files
SKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesSKILL.mdcore17,605 bytesreferences/model-roster.mddoc5,643 bytesscripts/api-dispatch.shruns16,196 bytesscripts/codex-appserver.mjsruns15,103 bytesscripts/dispatch-persist.mjsruns4,724 bytesscripts/gemini-supervisor.shruns11,124 bytesscripts/kimi-dispatch.shruns10,866 bytesscripts/stop-review-gate.mjsruns5,129 bytes
Read SKILL.md
> ✦ A **GiaSip** skill · part of the `giasip` toolkit · github.com/GiaSip
# /dispatch — Multi-Model Dispatcher
Sends a task or prompt to another AI model for execution and retrieves the result. This skill **only provides the dispatch capability** — which model to pick, whether to fan out to multiple models, is decided by you (or the current Claude) based on the task at hand. No built-in model preference.
## Script Directory
**Important**: All scripts live in the `scripts/` subdirectory of *this* skill folder.
**Agent setup — do this ONCE before running any command below**: determine the absolute path of the directory that contains this `SKILL.md`, and export it as `BASE_DIR`:
```bash
# Global install (most common); use the plugin cache path instead if installed as a plugingiasip-research
When your agent uses it
Use when the user asks to research, investigate, compare competitors, study a market or industry, check the current status of a regulation or policy, search literature, or simply look something up that needs external sources. Any question that requires fetching outside information triggers this skill. To verify specific claims in an existing report, use a dedicated verification pass instead.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
452 tokensWhen the skill is activated
Reference documents
40 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
FEEDBACK.mddoc168 bytesSKILL.mdcore2,028 bytesSKILL.mdcore2,028 bytesSKILL.mdcore2,028 bytes
Read SKILL.md
> ✦ **GiaSip** · github.com/GiaSip/giasip-skills
# GiaSip Research
**Goal.** Get the user accurate information that answers *their* question. Accuracy is a hard constraint; breadth is a means (you must gather widely to hit the accurate parts).
**Method.** Split the question into 2–3 complementary facets and run one sub-agent per facet in parallel. Sub-agents only gather, they do not conclude. Each sub-agent stops after at most 15 searches/fetches and returns compact findings without writing files. The main agent then writes a single `report.md`: answer the user's questions one by one, list every entity found with its URL, keep the body under 200 lines, and end with a separate **"To verify"** section.
**Discipline (hard rules)**
- Every fact carries a source URL. Prefer official / owner primary sources; label source type (primary / third-party / media).
- If it cannot be found, write "not found" — never fill from memory. Dates are absolute. GitHub stars and timestamps come from `gh api` snapshots, not search-result pages.
- Read and write only inside the output directory. Never `rm -rf`.
- Before anything goes out under a real name, quotes a price, or states a legal/financial conclusion, run a verification pass on the claims.
Skills included
- giasip-dispatch
- research
- giasip-dispatch
- giasip-research
Repository facts
- License
- MIT
- Created
- May 30, 2026
- Last pushed
- Oct 8, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 37 notes
locales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocales/zh/skills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/giasip/skills/research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/giasip/skills/research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/giasip-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 14 dangerous shell commandsin 3 files: skills/giasip-dispatch/scripts/gemini-supervisor.sh:242 skills/giasip-dispatch/scripts/kimi-dispatch.sh:208 skills/giasip-dispatch/scripts/api-dispatch.sh:300
- 172 network referencesin 7 files: skills/giasip-dispatch/scripts/api-dispatch.sh:33 skills/giasip-dispatch/scripts/kimi-dispatch.sh:104 skills/giasip-dispatch/SKILL.md:3 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- 12 executable scriptsin 6 files: skills/giasip-dispatch/scripts/api-dispatch.sh:1 skills/giasip-dispatch/scripts/codex-appserver.mjs:1 skills/giasip-dispatch/scripts/dispatch-persist.mjs:1 and 3 more
- 80 references to secretsin 4 files: skills/giasip-dispatch/scripts/api-dispatch.sh:4 skills/giasip-dispatch/scripts/kimi-dispatch.sh:91 skills/giasip-dispatch/SKILL.md:121 and 1 more
- No requests to vote in Hot
Show all 278 signals by file
.claude-plugin/marketplace.json
- Network accessline 6
"owner": { "name": "GiaSip", "url": "https://github.com/GiaSip" - Network accessline 7
"name": "GiaSip", "url": "https://github.com/GiaSip" }, - Network accessline 8
"url": "https://github.com/GiaSip" - Network accessline 9
}, "repository": "https://github.com/GiaSip/giasip-skills", "license": "MIT", - Network accessline 10
"repository": "https://github.com/GiaSip/giasip-skills",
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "GiaSip", "url": "https://github.com/GiaSip" - Network accessline 6
"name": "GiaSip", "url": "https://github.com/GiaSip" }, - Network accessline 7
"url": "https://github.com/GiaSip" - Network accessline 8
}, "repository": "https://github.com/GiaSip/giasip-skills", "license": "MIT", - Network accessline 9
"repository": "https://github.com/GiaSip/giasip-skills",
locales/zh/skills/giasip-dispatch/SKILL.md
- Network accessline 3
version: 1.2.0 description: 多模型调用器 — 把任务或 prompt 派发给其他 AI 模型（Codex / Gemini / Kimi / DeepSeek / 豆包 / Qwen / GLM / MiniMax）执行并取回结果。当你想用某个或某几个其他模型跑任务、需要多模型交叉对比验证、或想用更便宜的模型省钱时触发。提供两类调用通道：API 直调（只需 API key）和 CLI 调用（需本地装对应 CLI）。触发信号：「用 Kimi/Code - Network accessline 4
description: 多模型调用器 — 把任务或 prompt 派发给其他 AI 模型（Codex / Gemini / Kimi / DeepSeek / 豆包 / Qwen / GLM / MiniMax）执行并取回结果。当你想用某个或某几个其他模型跑任务、需要多模型交叉对比验证、或想用更便宜的模型省钱时触发。提供两类调用通道：API 直调（只需 API key）和 CLI 调用（需本地装对应 CLI）。触发信号：「用 Kimi/Codex/Gemini 跑一下」「交 - Network accessline 5
author: GiaSip <https://github.com/GiaSip> - Network accessline 60
├── 纯思考/分析（商业分析、战略、文本理解、翻译） │ → [API 直调] — 不需要 Agent 能力，直接 curl │ 快 10 倍；支持没有 CLI 的模型（DeepSeek/Qwen/GLM 等） - Network accessline 61
│ → [API 直调] — 不需要 Agent 能力，直接 curl │ 快 10 倍；支持没有 CLI 的模型（DeepSeek/Qwen/GLM 等） │ - Network accessline 196
> **Thinking 模型纪律**：Kimi K2.6 是 thinking 模型——复杂 prompt 推理可能耗时数分钟。**Bash timeout 必须 ≥600000**（10 分钟）。脚本内置 SSE streaming + idle guard（120s 无字节阈值）+ 900s hard cap。不要中途 kill 或用手写 curl 替代。快速模式：前缀 `KIMI_NO_THINK=1`（注入 `{"thinking":{"type":"disable - Access to secretsline 199
[Credential-related source omitted] - Access to secretsline 205
[Credential-related source omitted]
skills/giasip-dispatch/SKILL.md
- Network accessline 3
version: 1.3.0 description: “Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific mo - Network accessline 3
version: 1.3.0 description: “Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific mo - Network accessline 4
description: “Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific model, need multi - Network accessline 4
description: “Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific model, need multi - Network accessline 5
author: GiaSip <https://github.com/GiaSip> - Network accessline 5
author: GiaSip <https://github.com/GiaSip> - Network accessline 64
│ ├── Pure thinking/analysis (business analysis, strategy, text understanding, translation) │ → [API direct call] — no agent capability needed, curl the API directly - Network accessline 64
│ ├── Pure thinking/analysis (business analysis, strategy, text understanding, translation) │ → [API direct call] — no agent capability needed, curl the API directly - Network accessline 65
├── Pure thinking/analysis (business analysis, strategy, text understanding, translation) │ → [API direct call] — no agent capability needed, curl the API directly │ 10x faster; supports models without CLI (DeepSeek/Qwen/GLM etc.) - Network accessline 65
├── Pure thinking/analysis (business analysis, strategy, text understanding, translation) │ → [API direct call] — no agent capability needed, curl the API directly │ 10x faster; supports models without CLI (DeepSeek/Qwen/GLM etc.) - Network accessline 66
│ → [API direct call] — no agent capability needed, curl the API directly - Network accessline 66
│ → [API direct call] — no agent capability needed, curl the API directly - Access to secretsline 121
[Credential-related source omitted] - Access to secretsline 121
[Credential-related source omitted] - Network accessline 124
|----------|-------------------------------|---------|------| | `openrouter` | `openrouter.env` (`OPENROUTER_API_KEY`) | deepseek / qwen / glm / kimi / minimax / **claude / gpt / gemini** | Overseas; needs a VPN in mainland China | | `silic - Network accessline 124
|----------|-------------------------------|---------|------| | `openrouter` | `openrouter.env` (`OPENROUTER_API_KEY`) | deepseek / qwen / glm / kimi / minimax / **claude / gpt / gemini** | Overseas; needs a VPN in mainland China | | `silic - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Network accessline 126
[Credential-related source omitted] - Network accessline 126
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 233
[Credential-related source omitted] - Access to secretsline 233
[Credential-related source omitted] - Access to secretsline 239
[Credential-related source omitted] - Access to secretsline 239
[Credential-related source omitted]
skills/giasip-dispatch/references/model-roster.md
- Network accessline 11
### OpenRouter (overseas) — `https://openrouter.ai/api/v1` · [models page](https://openrouter.ai/models) - Network accessline 11
### OpenRouter (overseas) — `https://openrouter.ai/api/v1` · [models page](https://openrouter.ai/models) - Network accessline 26
### SiliconFlow 硅基流动 (China) — `https://api.siliconflow.cn/v1` · [models page](https://siliconflow.cn/models) - Network accessline 26
### SiliconFlow 硅基流动 (China) — `https://api.siliconflow.cn/v1` · [models page](https://siliconflow.cn/models) - Network accessline 38
> China direct-access, no VPN. Open-source / domestic models only — no Claude / GPT / Gemini. Some models rate-limit unverified accounts (e.g. ~100 requests/day on certain DeepSeek tiers) — ID-verify to lift it, and check SiliconFlow's curr - Network accessline 38
> China direct-access, no VPN. Open-source / domestic models only — no Claude / GPT / Gemini. Some models rate-limit unverified accounts (e.g. ~100 requests/day on certain DeepSeek tiers) — ID-verify to lift it, and check SiliconFlow's curr
skills/giasip-dispatch/scripts/api-dispatch.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 4
[Credential-related source omitted] - Access to secretsline 4
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Network accessline 33
# 安全说明： # - 每个 provider 只读取自己白名单内的 key 变量（KEY_ENV_VARS），不会误取环境里其它 provider 的 key。 # - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 - Network accessline 33
# 安全说明： # - 每个 provider 只读取自己白名单内的 key 变量（KEY_ENV_VARS），不会误取环境里其它 provider 的 key。 # - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 - Network accessline 34
# - 每个 provider 只读取自己白名单内的 key 变量（KEY_ENV_VARS），不会误取环境里其它 provider 的 key。 # - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 # - 注意：若 .env 用 `export` 导出 key，它仍在进程环境里，同用户可经 `ps e` / /pro - Network accessline 34
# - 每个 provider 只读取自己白名单内的 key 变量（KEY_ENV_VARS），不会误取环境里其它 provider 的 key。 # - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 # - 注意：若 .env 用 `export` 导出 key，它仍在进程环境里，同用户可经 `ps e` / /pro - Network accessline 35
# - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 - Network accessline 35
# - API key 通过 `curl -K -`（config 走 stdin）传入，不出现在进程 argv。config 里的值都经 cfg_escape 转义，避免注入额外 curl 选项。 - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Network accessline 122
KEY_FILE="$AI_KEYS_DIR/openrouter.env" KEY_ENV_VARS="OPENROUTER_API_KEY API_KEY" BASE_URL_DEFAULT="https://openrouter.ai/api/v1" - Network accessline 122
KEY_FILE="$AI_KEYS_DIR/openrouter.env" KEY_ENV_VARS="OPENROUTER_API_KEY API_KEY" BASE_URL_DEFAULT="https://openrouter.ai/api/v1" - Network accessline 123
[Credential-related source omitted] - Network accessline 123
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Network accessline 124
BASE_URL_DEFAULT="https://openrouter.ai/api/v1" - Network accessline 124
BASE_URL_DEFAULT="https://openrouter.ai/api/v1" - Network accessline 128
EXTRA_HEADER_LINES+=("HTTP-Referer: ${OPENROUTER_REFERER:-https://github.com/GiaSip/giasip-skills}") - Network accessline 128
EXTRA_HEADER_LINES+=("HTTP-Referer: ${OPENROUTER_REFERER:-https://github.com/GiaSip/giasip-skills}") - Network accessline 133
# alias → OpenRouter model ID (VOLATILE — slugs verified present 2026-07-19; check https://openrouter.ai/models) - Network accessline 133
# alias → OpenRouter model ID (VOLATILE — slugs verified present 2026-07-19; check https://openrouter.ai/models) - Network accessline 144
*) echo "[api-dispatch] OpenRouter 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 - Network accessline 144
*) echo "[api-dispatch] OpenRouter 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 - Network accessline 145
echo "[api-dispatch] OpenRouter 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 exit 1 - Network accessline 145
echo "[api-dispatch] OpenRouter 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 exit 1 - Network accessline 146
echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 - Network accessline 146
echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://openrouter.ai/models" >&2 - Network accessline 153
# ========================================================================= # AGGREGATOR: SiliconFlow 硅基流动 (China) — one key, DeepSeek/Qwen/GLM/Kimi/MiniMax # Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 - Network accessline 153
# ========================================================================= # AGGREGATOR: SiliconFlow 硅基流动 (China) — one key, DeepSeek/Qwen/GLM/Kimi/MiniMax # Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 - Network accessline 154
# AGGREGATOR: SiliconFlow 硅基流动 (China) — one key, DeepSeek/Qwen/GLM/Kimi/MiniMax # Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 # ========================================================================= - Network accessline 154
# AGGREGATOR: SiliconFlow 硅基流动 (China) — one key, DeepSeek/Qwen/GLM/Kimi/MiniMax # Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 # ========================================================================= - Network accessline 155
# Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 - Network accessline 155
# Intl users: export SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1 - Network accessline 158
KEY_FILE="$AI_KEYS_DIR/siliconflow.env" KEY_ENV_VARS="SILICONFLOW_API_KEY API_KEY" BASE_URL_DEFAULT="https://api.siliconflow.cn/v1" - Network accessline 158
KEY_FILE="$AI_KEYS_DIR/siliconflow.env" KEY_ENV_VARS="SILICONFLOW_API_KEY API_KEY" BASE_URL_DEFAULT="https://api.siliconflow.cn/v1" - Network accessline 159
[Credential-related source omitted] - Network accessline 159
[Credential-related source omitted] - Access to secretsline 159
[Credential-related source omitted] - Access to secretsline 159
[Credential-related source omitted] - Network accessline 160
BASE_URL_DEFAULT="https://api.siliconflow.cn/v1" - Network accessline 160
BASE_URL_DEFAULT="https://api.siliconflow.cn/v1" - Network accessline 166
# alias → SiliconFlow model ID (VOLATILE — live-tested 2026-07-19; check https://siliconflow.cn/models) - Network accessline 166
# alias → SiliconFlow model ID (VOLATILE — live-tested 2026-07-19; check https://siliconflow.cn/models) - Network accessline 174
*) echo "[api-dispatch] SiliconFlow 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 - Network accessline 174
*) echo "[api-dispatch] SiliconFlow 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 - Network accessline 175
echo "[api-dispatch] SiliconFlow 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 exit 1 - Network accessline 175
echo "[api-dispatch] SiliconFlow 别名表无 '$MODEL'。" >&2 echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 exit 1 - Network accessline 176
echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 - Network accessline 176
echo "[api-dispatch] 用 --model-id <raw> 透传，或查 https://siliconflow.cn/models" >&2 - Network accessline 193
KEY_FILE="$AI_KEYS_DIR/dashscope.env" KEY_ENV_VARS="DASHSCOPE_API_KEY API_KEY" API_URL="https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" - Network accessline 193
KEY_FILE="$AI_KEYS_DIR/dashscope.env" KEY_ENV_VARS="DASHSCOPE_API_KEY API_KEY" API_URL="https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" - Network accessline 194
[Credential-related source omitted] - Network accessline 194
[Credential-related source omitted] - Access to secretsline 194
[Credential-related source omitted] - Access to secretsline 194
[Credential-related source omitted] - Network accessline 195
API_URL="https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" - Network accessline 195
API_URL="https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" - Network accessline 200
KEY_FILE="$AI_KEYS_DIR/deepseek.env" KEY_ENV_VARS="DEEPSEEK_API_KEY API_KEY" API_URL="https://api.deepseek.com/chat/completions" - Network accessline 200
KEY_FILE="$AI_KEYS_DIR/deepseek.env" KEY_ENV_VARS="DEEPSEEK_API_KEY API_KEY" API_URL="https://api.deepseek.com/chat/completions" - Network accessline 201
[Credential-related source omitted] - Network accessline 201
[Credential-related source omitted] - Access to secretsline 201
[Credential-related source omitted] - Access to secretsline 201
[Credential-related source omitted] - Network accessline 202
API_URL="https://api.deepseek.com/chat/completions" - Network accessline 202
API_URL="https://api.deepseek.com/chat/completions" - Network accessline 207
KEY_FILE="$AI_KEYS_DIR/zai.env" KEY_ENV_VARS="ZAI_API_KEY ZHIPUAI_API_KEY BIGMODEL_API_KEY API_KEY" API_URL="https://open.bigmodel.cn/api/paas/v4/chat/completions" - Network accessline 207
KEY_FILE="$AI_KEYS_DIR/zai.env" KEY_ENV_VARS="ZAI_API_KEY ZHIPUAI_API_KEY BIGMODEL_API_KEY API_KEY" API_URL="https://open.bigmodel.cn/api/paas/v4/chat/completions" - Network accessline 208
[Credential-related source omitted] - Network accessline 208
[Credential-related source omitted] - Access to secretsline 208
[Credential-related source omitted] - Access to secretsline 208
[Credential-related source omitted] - Network accessline 209
API_URL="https://open.bigmodel.cn/api/paas/v4/chat/completions" - Network accessline 209
API_URL="https://open.bigmodel.cn/api/paas/v4/chat/completions" - Network accessline 214
KEY_FILE="$AI_KEYS_DIR/volcengine.env" KEY_ENV_VARS="VOLCENGINE_API_KEY VOLC_API_KEY ARK_API_KEY API_KEY" API_URL="https://ark.cn-beijing.volces.com/api/v3/chat/completions" - Network accessline 214
KEY_FILE="$AI_KEYS_DIR/volcengine.env" KEY_ENV_VARS="VOLCENGINE_API_KEY VOLC_API_KEY ARK_API_KEY API_KEY" API_URL="https://ark.cn-beijing.volces.com/api/v3/chat/completions" - Network accessline 215
[Credential-related source omitted] - Network accessline 215
[Credential-related source omitted] - Access to secretsline 215
[Credential-related source omitted] - Access to secretsline 215
[Credential-related source omitted] - Network accessline 216
API_URL="https://ark.cn-beijing.volces.com/api/v3/chat/completions" - Network accessline 216
API_URL="https://ark.cn-beijing.volces.com/api/v3/chat/completions" - Access to secretsline 222
[Credential-related source omitted] - Access to secretsline 222
[Credential-related source omitted] - Access to secretsline 224
[Credential-related source omitted] - Access to secretsline 224
[Credential-related source omitted] - Network accessline 226
BASE_URL_DEFAULT="https://api.minimaxi.com/v1" - Network accessline 226
BASE_URL_DEFAULT="https://api.minimaxi.com/v1" - Network accessline 248
[Credential-related source omitted] - Network accessline 248
[Credential-related source omitted] - Network accessline 249
[Credential-related source omitted] - Network accessline 249
[Credential-related source omitted] - Network accessline 250
[Credential-related source omitted] - Network accessline 250
[Credential-related source omitted] - Access to secretsline 250
[Credential-related source omitted] - Access to secretsline 250
[Credential-related source omitted] - Network accessline 251
[Credential-related source omitted] - Network accessline 251
[Credential-related source omitted] - Network accessline 252
[Credential-related source omitted] - Network accessline 252
[Credential-related source omitted] - Access to secretsline 252
[Credential-related source omitted] - Access to secretsline 252
[Credential-related source omitted] - Access to secretsline 261
[Credential-related source omitted] - Access to secretsline 261
[Credential-related source omitted] - Network accessline 262
if [[ -n "$BASE_URL_ENVVAR" ]]; then base_from_env="${!BASE_URL_ENVVAR:-}" API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" - Network accessline 262
if [[ -n "$BASE_URL_ENVVAR" ]]; then base_from_env="${!BASE_URL_ENVVAR:-}" API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" - Network accessline 263
base_from_env="${!BASE_URL_ENVVAR:-}" API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" fi - Network accessline 263
base_from_env="${!BASE_URL_ENVVAR:-}" API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" fi - Network accessline 264
API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" - Network accessline 264
API_URL="${base_from_env:-$BASE_URL_DEFAULT}/chat/completions" - Access to secretsline 268
[Credential-related source omitted] - Access to secretsline 268
[Credential-related source omitted] - Access to secretsline 271
[Credential-related source omitted] - Access to secretsline 271
[Credential-related source omitted] - Access to secretsline 276
[Credential-related source omitted] - Access to secretsline 276
[Credential-related source omitted] - Access to secretsline 286
[Credential-related source omitted] - Access to secretsline 286
[Credential-related source omitted] - Access to secretsline 288
[Credential-related source omitted] - Access to secretsline 288
[Credential-related source omitted] - Network accessline 295
# --- Temp files (0600, auto-removed) for the request body + curl stderr. - Network accessline 295
# --- Temp files (0600, auto-removed) for the request body + curl stderr. - Dangerous shell operationline 300
trap 'rm -f "$BODY_FILE" "$ERR_FILE"' EXIT - Dangerous shell operationline 300
trap 'rm -f "$BODY_FILE" "$ERR_FILE"' EXIT - Network accessline 308
# Escape a value for a curl-config double-quoted field: backslash + double-quote, # and drop CR/LF — so a key / URL / header value can't break out of its quotes # and inject an extra curl option (e.g. a second url/proxy/output line). - Network accessline 308
# Escape a value for a curl-config double-quoted field: backslash + double-quote, # and drop CR/LF — so a key / URL / header value can't break out of its quotes # and inject an extra curl option (e.g. a second url/proxy/output line). - Network accessline 310
# and inject an extra curl option (e.g. a second url/proxy/output line). - Network accessline 310
# and inject an extra curl option (e.g. a second url/proxy/output line). - Network accessline 315
[Credential-related source omitted] - Network accessline 315
[Credential-related source omitted] - Network accessline 317
emit_curl_config() { printf 'url = "%s"\n' "$(cfg_escape "$API_URL")" - Network accessline 317
emit_curl_config() { printf 'url = "%s"\n' "$(cfg_escape "$API_URL")" - Network accessline 318
printf 'url = "%s"\n' "$(cfg_escape "$API_URL")" - Network accessline 318
printf 'url = "%s"\n' "$(cfg_escape "$API_URL")" - Access to secretsline 320
[Credential-related source omitted] - Access to secretsline 320
[Credential-related source omitted] - Network accessline 329
set +e API_RESPONSE="$(emit_curl_config | curl -sS --max-time "$TIMEOUT" -K - 2>"$ERR_FILE")" - Network accessline 329
set +e API_RESPONSE="$(emit_curl_config | curl -sS --max-time "$TIMEOUT" -K - 2>"$ERR_FILE")" - Network accessline 330
API_RESPONSE="$(emit_curl_config | curl -sS --max-time "$TIMEOUT" -K - 2>"$ERR_FILE")" - Network accessline 330
API_RESPONSE="$(emit_curl_config | curl -sS --max-time "$TIMEOUT" -K - 2>"$ERR_FILE")" - Network accessline 335
# curl error text (e.g. "curl: (28) Operation timed out") contains no secrets - Network accessline 335
# curl error text (e.g. "curl: (28) Operation timed out") contains no secrets - Network accessline 336
echo "[api-dispatch] $DISPLAY_NAME 请求失败 (curl exit $curl_rc): $(head -c 200 "$ERR_FILE")" >&2 - Network accessline 336
echo "[api-dispatch] $DISPLAY_NAME 请求失败 (curl exit $curl_rc): $(head -c 200 "$ERR_FILE")" >&2
skills/giasip-dispatch/scripts/codex-appserver.mjs
skills/giasip-dispatch/scripts/dispatch-persist.mjs
skills/giasip-dispatch/scripts/gemini-supervisor.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 242
rm -f "$out_file" "$err_file" - Dangerous shell operationline 242
rm -f "$out_file" "$err_file" - Dangerous shell operationline 249
rm -f "$out_file" "$err_file" - Dangerous shell operationline 249
rm -f "$out_file" "$err_file" - Dangerous shell operationline 282
rm -f /tmp/gemini-supervisor-err.$$ - Dangerous shell operationline 282
rm -f /tmp/gemini-supervisor-err.$$ - Dangerous shell operationline 289
rm -f /tmp/gemini-supervisor-err.$$ - Dangerous shell operationline 289
rm -f /tmp/gemini-supervisor-err.$$
skills/giasip-dispatch/scripts/kimi-dispatch.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Network accessline 104
api_started=$(date +%s) API_RESPONSE=$(curl -s --max-time "$TIMEOUT" \ - Network accessline 104
api_started=$(date +%s) API_RESPONSE=$(curl -s --max-time "$TIMEOUT" \ - Network accessline 105
[Credential-related source omitted] - Network accessline 105
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Network accessline 106
https://api.kimi.com/coding/v1/messages \ - Network accessline 106
https://api.kimi.com/coding/v1/messages \ - Access to secretsline 108
[Credential-related source omitted] - Access to secretsline 108
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Network accessline 205
# 把 SSE 解析脚本落地成临时文件，避免 `python3 - <<HEREDOC` 模式吃掉 stdin pipe 的坑 # （已知 bug：`python3 - <<'PY' ... PY` 中 `-` + heredoc 同时占用 stdin，curl 流无法流入 python） - Network accessline 205
# 把 SSE 解析脚本落地成临时文件，避免 `python3 - <<HEREDOC` 模式吃掉 stdin pipe 的坑 # （已知 bug：`python3 - <<'PY' ... PY` 中 `-` + heredoc 同时占用 stdin，curl 流无法流入 python） - Network accessline 206
# （已知 bug：`python3 - <<'PY' ... PY` 中 `-` + heredoc 同时占用 stdin，curl 流无法流入 python） - Network accessline 206
# （已知 bug：`python3 - <<'PY' ... PY` 中 `-` + heredoc 同时占用 stdin，curl 流无法流入 python） - Dangerous shell operationline 208
trap 'rm -f "$SSE_PARSER" /tmp/kimi-curl-err.$$' EXIT - Dangerous shell operationline 208
trap 'rm -f "$SSE_PARSER" /tmp/kimi-curl-err.$$' EXIT - Network accessline 242
# SSE streaming + idle guard： # --no-buffer：禁 curl 输出缓冲（必须，否则 streaming 失效） - Network accessline 242
# SSE streaming + idle guard： # --no-buffer：禁 curl 输出缓冲（必须，否则 streaming 失效） - Network accessline 243
# --no-buffer：禁 curl 输出缓冲（必须，否则 streaming 失效） - Network accessline 243
# --no-buffer：禁 curl 输出缓冲（必须，否则 streaming 失效） - Network accessline 246
[Credential-related source omitted] - Network accessline 246
[Credential-related source omitted] - Access to secretsline 246
[Credential-related source omitted] - Access to secretsline 246
[Credential-related source omitted] - Network accessline 249
--speed-time "$IDLE_TIMEOUT" \ --max-time "$STREAM_TIMEOUT" \ https://api.moonshot.cn/v1/chat/completions \ - Network accessline 249
--speed-time "$IDLE_TIMEOUT" \ --max-time "$STREAM_TIMEOUT" \ https://api.moonshot.cn/v1/chat/completions \ - Network accessline 250
--max-time "$STREAM_TIMEOUT" \ https://api.moonshot.cn/v1/chat/completions \ -H "Content-Type: application/json" \ - Network accessline 250
--max-time "$STREAM_TIMEOUT" \ https://api.moonshot.cn/v1/chat/completions \ -H "Content-Type: application/json" \ - Network accessline 251
https://api.moonshot.cn/v1/chat/completions \ - Network accessline 251
https://api.moonshot.cn/v1/chat/completions \ - Access to secretsline 253
[Credential-related source omitted] - Access to secretsline 253
[Credential-related source omitted] - Dangerous shell operationline 260
rm -f /tmp/kimi-curl-err.$$ - Dangerous shell operationline 260
rm -f /tmp/kimi-curl-err.$$ - Network accessline 271
# 失败诊断：分别报告 curl 错误和 latency - Network accessline 271
# 失败诊断：分别报告 curl 错误和 latency - Network accessline 275
elif [[ -n "$curl_err" ]]; then log_event "kimi-moonshot" 1 "curl_error" "$api_latency" "null" echo "[kimi-dispatch] curl error: $curl_err" >&2 - Network accessline 275
elif [[ -n "$curl_err" ]]; then log_event "kimi-moonshot" 1 "curl_error" "$api_latency" "null" echo "[kimi-dispatch] curl error: $curl_err" >&2 - Network accessline 276
log_event "kimi-moonshot" 1 "curl_error" "$api_latency" "null" echo "[kimi-dispatch] curl error: $curl_err" >&2 else - Network accessline 276
log_event "kimi-moonshot" 1 "curl_error" "$api_latency" "null" echo "[kimi-dispatch] curl error: $curl_err" >&2 else - Network accessline 277
echo "[kimi-dispatch] curl error: $curl_err" >&2 - Network accessline 277
echo "[kimi-dispatch] curl error: $curl_err" >&2
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 8 facts
- Contacts openrouter.ai, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:124High confidence
- Contacts api.siliconflow.cn, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:160High confidence
- Contacts siliconflow.cn, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:176High confidence
- Contacts dashscope.aliyuncs.com, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:195High confidence
- Contacts api.deepseek.com, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:202High confidence
- Contacts open.bigmodel.cn, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:209High confidence
- Contacts ark.cn-beijing.volces.com, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:216High confidence
- Contacts api.minimaxi.com, which SKILL.md, the README and the plugin manifest do not mentiongiasip-dispatch/scripts/api-dispatch.sh:226High confidence
Signal confidence: 268 facts
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:3Low confidence
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:4Low confidence
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:5Low confidence
- Network access in code of the SKILL.mdgiasip-dispatch/SKILL.md:60High confidence
- Network access in code of the SKILL.mdgiasip-dispatch/SKILL.md:61High confidence
- Network access in prose of the SKILL.mdgiasip-dispatch/SKILL.md:196Low confidence
- Access to secrets in code of the SKILL.mdgiasip-dispatch/SKILL.md:199High confidence
- Access to secrets in code of the SKILL.mdgiasip-dispatch/SKILL.md:205High confidence
- Network access in the frontmatter of the SKILL.mdskills/giasip-dispatch/SKILL.md:3Low confidence
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:3Low confidence
- Network access in the frontmatter of the SKILL.mdskills/giasip-dispatch/SKILL.md:4Low confidence
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:4Low confidence
- Network access in the frontmatter of the SKILL.mdskills/giasip-dispatch/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdgiasip-dispatch/SKILL.md:5Low confidence
- Network access in code of the SKILL.mdskills/giasip-dispatch/SKILL.md:64High confidence
- Network access in code of the SKILL.mdgiasip-dispatch/SKILL.md:64High confidence
- Network access in code of the SKILL.mdskills/giasip-dispatch/SKILL.md:65High confidence
- Network access in code of the SKILL.mdgiasip-dispatch/SKILL.md:65High confidence
- Network access in code of the SKILL.mdskills/giasip-dispatch/SKILL.md:66High confidence
- Network access in code of the SKILL.mdgiasip-dispatch/SKILL.md:66High confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/SKILL.md:121Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuegiasip-dispatch/SKILL.md:121Low confidence
- Network access in prose of the SKILL.mdskills/giasip-dispatch/SKILL.md:124Low confidence
- Network access in prose of the SKILL.mdgiasip-dispatch/SKILL.md:124Low confidence
- Access to secrets in prose of the SKILL.mdskills/giasip-dispatch/SKILL.md:125Low confidence
- Access to secrets in prose of the SKILL.mdgiasip-dispatch/SKILL.md:125Low confidence
- Network access in prose of the SKILL.mdskills/giasip-dispatch/SKILL.md:126Low confidence
- Network access in prose of the SKILL.mdgiasip-dispatch/SKILL.md:126Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/SKILL.md:126Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuegiasip-dispatch/SKILL.md:126Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/SKILL.md:233Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuegiasip-dispatch/SKILL.md:233Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/SKILL.md:239Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuegiasip-dispatch/SKILL.md:239Low confidence
- Network access in prose of documentationskills/giasip-dispatch/references/model-roster.md:11Low confidence
- Network access in prose of documentationgiasip-dispatch/references/model-roster.md:11Low confidence
- Network access in prose of documentationskills/giasip-dispatch/references/model-roster.md:26Low confidence
- Network access in prose of documentationgiasip-dispatch/references/model-roster.md:26Low confidence
- Network access in prose of documentationskills/giasip-dispatch/references/model-roster.md:38Low confidence
- Network access in prose of documentationgiasip-dispatch/references/model-roster.md:38Low confidence
- Executable script in code of a file that runsskills/giasip-dispatch/scripts/api-dispatch.sh:1High confidence
- Executable script in code of a file that runsgiasip-dispatch/scripts/api-dispatch.sh:1High confidence
- Access to secrets in a comment of a file that runsskills/giasip-dispatch/scripts/api-dispatch.sh:4Low confidence
- Access to secrets in a comment of a file that runsgiasip-dispatch/scripts/api-dispatch.sh:4Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/scripts/api-dispatch.sh:26Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valuegiasip-dispatch/scripts/api-dispatch.sh:26Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/scripts/api-dispatch.sh:30Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valuegiasip-dispatch/scripts/api-dispatch.sh:30Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valueskills/giasip-dispatch/scripts/api-dispatch.sh:31Low confidence
- Access to secrets in a comment of a file that runs: a variable, placeholder or call, not a stored valuegiasip-dispatch/scripts/api-dispatch.sh:31Low confidence
and 218 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md locales/zh/skills/giasip-dispatch/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md locales/zh/skills/giasip-dispatch/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md locales/zh/skills/giasip-dispatch/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md locales/zh/skills/giasip-dispatch/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md locales/zh/skills/giasip-dispatch/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
