Not in the top 1,000 by GitHub stars
AIDiscovery007/qc-skills
Focused agent skills for thinking and creating · 清晰思考,自由创作。Explore qc-alchemy through 10 visual transformations.
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
skills/incubating/bdd-agents-handoff/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/incubating/qc-expert-casting/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/published/qc-alchemy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/published/qc-essence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/published/qc-image-series/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/published/qc-motion-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
skills/published/qc-skills-setup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5247f2ab77a1
No earlier version was observed for comparison.
Verified commit 5247f2ab77a1ea9ef563ca8cb6dc5ea643ad873c
git clone --filter=blob:none --no-checkout https://github.com/AIDiscovery007/qc-skills.git .hotskills/aidiscovery007-qc-skills && git -C .hotskills/aidiscovery007-qc-skills checkout --detach 5247f2ab77a1ea9ef563ca8cb6dc5ea643ad873c
# Copy each selected skill directory from .hotskills/aidiscovery007-qc-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/AIDiscovery007/qc-skills.git .hotskills/aidiscovery007-qc-skills && git -C .hotskills/aidiscovery007-qc-skills checkout --detach 5247f2ab77a1ea9ef563ca8cb6dc5ea643ad873c
# Copy each selected skill directory from .hotskills/aidiscovery007-qc-skills into .agents/skills/<skill-name>/Heat
2.6- 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
- bdd-agents-handoff
skills/incubating/bdd-agents-handoff - qc-expert-casting
skills/incubating/qc-expert-casting - qc-alchemy
skills/published/qc-alchemy - qc-essence
skills/published/qc-essence - qc-image-series
skills/published/qc-image-series - qc-motion-design
skills/published/qc-motion-design - qc-skills-setup
skills/published/qc-skills-setup
How it works
bdd-agents-handoff
When your agent uses it
Plan a feature or project as small end-to-end iterations, lock the behavior down with BDD specs and tests first, then orchestrate real developer agents (Claude Code, Codex, Cursor, or any other coding agent), running independent iterations in parallel, and review, merge and test what comes back. Use this whenever the user wants to plan and build something by delegating implementation to other coding agents, work BDD-first, parallelize implementation across agents, or break a project into minimal closed-loop iterations, even if they don't name all of these explicitly.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
2,599 tokensWhen the skill is activated
Reference documents
53,883 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How approval works (read this first)
- 0. Look around first (and again at every checkpoint)
- 1. Plan
- 2. Lock the spec with BDD, for all iterations (before any development)
- 3. Schedule: serial or parallel (you decide)
- 4. Hand off to real developer agents (one per iteration in the wave)
- 5. Review, merge, and test
- The rule that protects everything else
Scripts executed separately
scripts/scan.sh../../published/qc-image-series/scripts/render-chapter-dividers.py../../published/qc-motion-design/assets/motion-cases/advanced-components.js../../published/qc-motion-design/assets/motion-cases/advanced-motion.js../../published/qc-motion-design/assets/motion-cases/app.js../../published/qc-motion-design/assets/motion-cases/extra-components.js../../published/qc-motion-design/assets/motion-cases/extra-motion.js../../published/qc-motion-design/assets/motion-cases/motion-prompts.js../../published/qc-motion-design/assets/motion-cases/source-notes.js../../published/qc-skills-setup/scripts/create-claude-md.sh
Files
../../../.claude-plugin/plugin.jsonasset336 bytesSKILL.mdcore12,173 bytesreferences/agents.mddoc3,501 bytesreferences/awareness.mddoc1,841 bytesscripts/scan.shruns2,666 bytes../qc-expert-casting/SKILL.mddoc5,871 bytes../qc-expert-casting/references/agent-md.mddoc5,492 bytes../qc-expert-casting/references/prompt.mddoc3,041 bytes../../published/qc-alchemy/SKILL.mddoc4,495 bytes../../published/qc-alchemy/agents/openai.yamlasset299 bytes../../published/qc-alchemy/references/casebook.mddoc5,550 bytes../../published/qc-alchemy/references/color-matching.mddoc8,307 bytes../../published/qc-alchemy/references/domain-adaptation.mddoc6,702 bytes../../published/qc-alchemy/references/evaluation.mddoc8,550 bytes../../published/qc-alchemy/references/evidence.mddoc5,369 bytes../../published/qc-alchemy/references/prompt-contract.mddoc11,803 bytes../../published/qc-alchemy/references/source-index.jsonasset19,338 bytes../../published/qc-alchemy/references/surface-analysis.mddoc3,912 bytes../../published/qc-alchemy/references/template-reconstruction.mddoc6,173 bytes../../published/qc-alchemy/references/workflow.mddoc7,567 bytes../../published/qc-essence/SKILL.mddoc3,873 bytes../../published/qc-image-series/SKILL.mddoc6,982 bytes../../published/qc-image-series/assets/chapter-divider-reference.pngasset838,387 bytes../../published/qc-image-series/references/chapter-divider.mddoc9,850 bytes../../published/qc-image-series/references/layout.mddoc5,109 bytes../../published/qc-image-series/references/media-source.mddoc5,234 bytes../../published/qc-image-series/references/platforms.mddoc2,354 bytes../../published/qc-image-series/references/style-selection.mddoc1,182 bytes../../published/qc-image-series/scripts/render-chapter-dividers.pyruns10,108 bytes../../published/qc-image-series/styles/japn-silent.mddoc2,493 bytes../../published/qc-image-series/styles/japn-tech.mddoc4,485 bytes../../published/qc-motion-design/SKILL.mddoc4,349 bytes../../published/qc-motion-design/agents/openai.yamlasset169 bytes../../published/qc-motion-design/assets/motion-cases/README.mddoc2,321 bytes../../published/qc-motion-design/assets/motion-cases/advanced-components.jsruns10,965 bytes../../published/qc-motion-design/assets/motion-cases/advanced-motion.cssasset8,154 bytes../../published/qc-motion-design/assets/motion-cases/advanced-motion.jsruns11,153 bytes../../published/qc-motion-design/assets/motion-cases/app.jsruns29,966 bytes../../published/qc-motion-design/assets/motion-cases/assets/motion-landscape.svgasset404 bytes../../published/qc-motion-design/assets/motion-cases/extra-components.jsruns12,797 bytes../../published/qc-motion-design/assets/motion-cases/extra-motion.cssasset9,701 bytes../../published/qc-motion-design/assets/motion-cases/extra-motion.jsruns18,972 bytes../../published/qc-motion-design/assets/motion-cases/index.htmlasset4,409 bytes../../published/qc-motion-design/assets/motion-cases/motion-prompts.jsruns10,642 bytes../../published/qc-motion-design/assets/motion-cases/source-notes.jsruns5,860 bytes../../published/qc-motion-design/assets/motion-cases/sources/Benjamin_De_Cock_Motion_Playfulness_CSS_Day_2018.mddoc11,136 bytes../../published/qc-motion-design/assets/motion-cases/sources/animation-design-skill.mddoc27,335 bytes../../published/qc-motion-design/assets/motion-cases/sources/animation-vocabulary.mddoc10,237 bytes../../published/qc-motion-design/assets/motion-cases/styles.cssasset19,728 bytes../../published/qc-motion-design/references/component-patterns.mddoc7,008 bytes../../published/qc-motion-design/references/implementation.mddoc4,373 bytes../../published/qc-motion-design/references/motion-decisions.mddoc3,963 bytes../../published/qc-motion-design/references/review.mddoc3,712 bytes../../published/qc-motion-design/references/sources.mddoc6,516 bytes../../published/qc-motion-design/references/vocabulary.mddoc5,628 bytes../../published/qc-skills-setup/SKILL.mddoc576 bytes../../published/qc-skills-setup/scripts/create-claude-md.shruns911 bytes
Read SKILL.md
# BDD-first development with orchestrated developer agents
You are the orchestrator: planner, spec owner, reviewer, merger, and tester. Developer agents are the implementers. The split matters: tests stay an independent statement of intended behavior only if the people writing the code never get to shape them.
Your job is orchestration, review, merge, bug feedback, and tests. Writing feature code is the developers' job.
The developer agents can be any coding agent. Use the one the user names; if they don't name one, ask once. See `references/agents.md` for how to launch each.
## How approval works (read this first)
The user approves **once**: when they confirm the plan and spec in step 2. That approval covers every iteration in the plan, whether there is one or ten, and it covers how you schedule them. After it, run everything without asking "ready for the next one?", "shall I proceed?", "should I run these in parallel?", or for sign-off on each commit. Repeated check-ins are the main thing users dislike about this workflow, and the approved spec already says what "done" means for each iteration.
Stop and ask only when one of these happens:
View the complete source on GitHubqc-expert-casting
When your agent uses it
Recommends the single best public expert, thinker, operator, or creator to reason through a user's problem and produces either a prompt suffix or a Sub Agent agent.md/system prompt for that expert lens. Use when the user asks for celebrity casting, expert casting, a famous person to solve a problem, a named-person thinking framework, or a subagent/persona/system prompt based on a public figure.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,190 tokensWhen the skill is activated
Reference documents
1,678 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Output Modes
- Casting Workflow
- Candidate Rules
- Artifact Rules
- Mini Examples
- Final Check
Files
SKILL.mdcore5,871 bytesreferences/agent-md.mddoc5,492 bytesreferences/prompt.mddoc3,041 bytes
Read SKILL.md
# QC Expert Casting
Cast one public figure as the sharpest thinking lens for the user's actual problem.
## Purpose
Use this skill when the user wants a person name that can unlock a useful knowledge system, thinking style, domain judgment, or practical problem-solving frame from the model. The core job is not to name a famous person; it is to infer the user's real problem structure and choose the public figure whose known methods best fit it.
Treat the person name as a compressed retrieval key. Use it to activate the model's public-work-informed knowledge of that person's methods, domains, standards, and reasoning patterns. Do not claim to be the real person, access private consciousness, hidden parameters, private beliefs, or guaranteed faithful replicas.
## Output Modes
- Default mode: output one person, a brief recommendation reason, and a pasteable `Prompt 后缀`.
- Sub Agent mode: when the user mentions Sub Agent, `agent.md`, system prompt, persona, or agent workflow, output one person, a brief recommendation reason, and a complete `Agent.md`.View the complete source on GitHubqc-alchemy
When your agent uses it
Reverse-engineer reference images into actionable recreation prompts or transferable visual styles. Use for recreating references, adapting templates to new subjects, changing rendering styles while preserving structure, combining references, or correcting generated results across photography, illustration, products, spaces, landscapes, posters, and graphics. Not for OCR-only tasks or general image Q&A.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,146 tokensWhen the skill is activated
Reference documents
17,619 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 执行入口
- 核心判断
Files
SKILL.mdcore4,495 bytesagents/openai.yamlasset299 bytesreferences/casebook.mddoc5,550 bytesreferences/color-matching.mddoc8,307 bytesreferences/domain-adaptation.mddoc6,702 bytesreferences/evaluation.mddoc8,550 bytesreferences/evidence.mddoc5,369 bytesreferences/prompt-contract.mddoc11,803 bytesreferences/source-index.jsonasset19,338 bytesreferences/surface-analysis.mddoc3,912 bytesreferences/template-reconstruction.mddoc6,173 bytesreferences/workflow.mddoc7,567 bytes
Read SKILL.md
# QC Alchemy — 参考图逆向与风格重构
从当前图片提炼生成决策,不从固定人物、风格名称或历史案例套答案。逆向产物是可执行的近似复刻方案,不能据一张图片还原唯一的原始提示词、模型、seed或制作流程。
## 执行入口
1. 按用户意图选择:**还原参考图 / 提炼可迁移风格 / 以新主体重演模板 / 保留结构仅迁移画法 / 修正已有结果**。单张参考图已经是有效输入,不要求补主体图。区分用户明确锁定的字段与先前由助手自行加入的限制;用户纠正取舍后清理旧限制。
2. 实际查看可用图片,按 [分析流程](references/workflow.md) 完成首次“整体结构 → 关键表面局部 → 整图回看”,联动判断颜色角色与表面表现;提交前核对重要观察已转为区域指令,不等待用户点名色差或质感。记录输入角色、硬约束和最重要的视觉锚点。多图按实际顺序标识,不能默认“图1永远是人物”。
3. 根据当前题材查 [场景适配](references/domain-adaptation.md) 的相关条目。先解释画面中的关系,再选择画法词;没有人物时不输出人脸规则,没有文字时不补排版要求。
参考图加新主体、强调模板效果或出现“只像滤镜”的偏差时,读取 [模板重演与适配判断](references/template-reconstruction.md),判断模板是否适配目标、哪些视觉机制需要改变姿态、可见度或配件才能成立。模板人物姿态可辨且允许重演时,按其中的整体姿态规则协调支撑、躯干、头颈、肢体和视线,身份特征随新视角重新表现。
4. 读取并执行 [提示词结构](references/prompt-contract.md):先确定模式与字段归属,再按对应骨架组织提交词,逐项核对关键锚点是否写成了可执行的区域与关系。有旧词先清理冲突;没有旧词从观察起写。批量任务逐条适配与检查,不以统一前后缀代替分析。不依赖历史实验文件或某个指定图像模型。
5. 只有用户要求出图时,使用可用的 imagegen Skill;若不可用,交付提示词并说明执行限制,不谎称已生成。遵循用户指定的输入、数量和工具,按 [校验规则](references/evaluation.md) 检查结果并定点修正。
## 核心判断View the complete source on GitHubqc-essence
When your agent uses it
Performs model-guided essence extraction into a final judgment, memorable aha moment, core pillars, and minimal reasons for decision clarity. Use when the user wants to strip a topic, article, product, plan, or problem down to its decisive essence.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
833 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
- Workflow
- Internal Stack
- Internal Tests
- Reverse Challenge
- Output Rules
- Shape
- Bad Examples
- Final Check
Files
SKILL.mdcore3,873 bytes
Read SKILL.md
# QC Essence
Compress complex input to its irreducible essence. Think deeply; answer briefly.
## Workflow
1. Read the user's input directly; do not interview.
2. If there is no object to analyze, ask for the object in one short sentence.
3. Silently spread out the representative surface facts, claims, symptoms, and examples.
4. Strip filler, repeated claims, decorative wording, and points that only rename another point.
5. Find the smallest set of independent generators that can explain the whole.
6. Reverse-challenge the result, then output only the final judgment, aha moment, pillars, and minimal reasons.
## Internal StackView the complete source on GitHubqc-image-series
When your agent uses it
Creates one series-spec.md with consistent prompts for image series, social covers, carousels, or fixed-layout chapter divider title cards. Use when the user asks to turn a file, article, script, storyboard, outline, video, or audio source into series images, cover prompts, chapter split images, section divider images, or stable prompt packs.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,479 tokensWhen the skill is activated
Reference documents
7,050 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Deliverable
- Core Rules
- Fixed SOP
- Prompt Assembly Order
- Output Shape
- Don't Do
- QA Checklist
Scripts executed separately
scripts/render-chapter-dividers.py
Files
SKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesSKILL.mdcore6,982 bytesassets/chapter-divider-reference.pngasset838,387 bytesreferences/chapter-divider.mddoc9,850 bytesreferences/layout.mddoc5,109 bytesreferences/media-source.mddoc5,234 bytesreferences/platforms.mddoc2,354 bytesreferences/style-selection.mddoc1,182 bytesscripts/render-chapter-dividers.pyruns10,108 bytesstyles/japn-silent.mddoc2,493 bytesstyles/japn-tech.mddoc4,485 bytes
Read SKILL.md
# QC Image Series
## Purpose
Turn a source object into a controlled image-series spec. The output should feel visually consistent and make the source's core information immediately legible. For chapter dividers, produce fixed-layout title-card prompts only by default; render actual divider images only when the user explicitly asks for raster assets.
## Deliverable
Create exactly one short slug folder under `qc-image-series-output/` in the current repository root. Put exactly one file inside it: `series-spec.md`.
## Core Rules
- Message first: every image needs one concrete claim and one visual proof/cue. If the selected style uses text, add exact visible text; if the style is textless, set `Visible text: none`.
- Text policy comes from the selected style. Never plan a separate base image followed by Python, canvas, SVG, Pillow, ImageMagick, or other post-processing text overlay.View the complete source on GitHubqc-motion-design
When your agent uses it
Design, implement, explain, or review interaction motion for web interfaces and frontend components. Use for button feedback, overlay transitions, state changes, drag gestures, timing, easing, motion performance, and reduced-motion support. Not for static layout, typography, or color design alone.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,082 tokensWhen the skill is activated
Reference documents
20,301 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 目标与边界
- 执行流程
- 参考文件路由
- 可运行案例
- 核心约束
- 指令与交付用语
Scripts executed separately
assets/motion-cases/advanced-components.jsassets/motion-cases/advanced-motion.jsassets/motion-cases/app.jsassets/motion-cases/extra-components.jsassets/motion-cases/extra-motion.jsassets/motion-cases/motion-prompts.jsassets/motion-cases/source-notes.js
Files
SKILL.mdcore4,349 bytesagents/openai.yamlasset169 bytesassets/motion-cases/README.mddoc2,321 bytesassets/motion-cases/advanced-components.jsruns10,965 bytesassets/motion-cases/advanced-motion.cssasset8,154 bytesassets/motion-cases/advanced-motion.jsruns11,153 bytesassets/motion-cases/app.jsruns29,966 bytesassets/motion-cases/assets/motion-landscape.svgasset404 bytesassets/motion-cases/extra-components.jsruns12,797 bytesassets/motion-cases/extra-motion.cssasset9,701 bytesassets/motion-cases/extra-motion.jsruns18,972 bytesassets/motion-cases/index.htmlasset4,409 bytesassets/motion-cases/motion-prompts.jsruns10,642 bytesassets/motion-cases/source-notes.jsruns5,860 bytesassets/motion-cases/sources/Benjamin_De_Cock_Motion_Playfulness_CSS_Day_2018.mddoc11,136 bytesassets/motion-cases/sources/animation-design-skill.mddoc27,335 bytesassets/motion-cases/sources/animation-vocabulary.mddoc10,237 bytesassets/motion-cases/styles.cssasset19,728 bytesreferences/component-patterns.mddoc7,008 bytesreferences/implementation.mddoc4,373 bytesreferences/motion-decisions.mddoc3,963 bytesreferences/review.mddoc3,712 bytesreferences/sources.mddoc6,516 bytesreferences/vocabulary.mddoc5,628 bytes
Read SKILL.md
# qc-motion-design
## 目标与边界
让动效解释操作反馈、状态关系、空间方向与流程变化。
依据操作频率和用户目的判断是否需要动画,优先复用项目已有组件与动画机制。
只调整任务涉及的交互与动效;示例时长、幅度和弹簧参数作为调试起点,不作为通用标准。
## 执行流程
1. 明确目标组件、触发操作、起止状态、使用频率和输入方式。从需求与现有代码中获取信息;只有必要信息缺失时,才询问用户。
2. 按 [动效决策](references/motion-decisions.md) 判断是否保留动画,并为保留的动画选择目的、时长、缓动与方向。
3. 按需读取组件模式和工程实现,处理连续触发、中断、取消、键盘与减少动态效果路径。让业务状态驱动反馈,不用动画结束事件决定业务成功。
4. 根据用户请求直接修改目标代码、交付设计说明或报告审查问题。实现时复用项目已有机制,并清理动画、监听器与异步工作。View the complete source on GitHubqc-skills-setup
When your agent uses it
Sets up qc-skills compatibility files for OpenClaw, Claude Code, and agent users by bridging AGENTS.md to CLAUDE.md. Use when bootstrapping qc-skills or preparing Claude-style agents to read Codex-style instructions.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
145 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
Scripts executed separately
scripts/create-claude-md.sh
Files
SKILL.mdcore576 bytesscripts/create-claude-md.shruns911 bytes
Read SKILL.md
# QC Skills Setup
From the target repo root, run this skill's `scripts/create-claude-md.sh`.
It creates `CLAUDE.md` with `@AGENTS.md`, or appends that import without overwriting existing Claude instructions.
Stop if `AGENTS.md` is missing.
Verify `CLAUDE.md` contains `@AGENTS.md` and `AGENTS.md` is unchanged.View the complete source on GitHubSkills included
- bdd-agents-handoff
- qc-expert-casting
- qc-alchemy
- qc-essence
- qc-image-series
- qc-motion-design
- qc-skills-setup
Repository facts
- License
- MIT
- Created
- May 11, 2026
- Last pushed
- Oct 21, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 18 notes
skills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/extra-motion.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/styles.css:2Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/styles.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Plugin-wide analysis incomplete; see repository notesskills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Plugin-wide analysis incomplete; see repository notesskills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Plugin-wide analysis incomplete; see repository notesskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-image-series/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/extra-motion.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/styles.css:2Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/styles.css:1Analysis incomplete: physical or joined line exceeds character limitskills/published/qc-motion-design/assets/motion-cases/advanced-motion.css:1Plugin-wide analysis incomplete; see repository notes
- No broad tool permissions
- No dangerous shell commands
- No hidden or obfuscated text
- No instruction overrides
- No access to secrets
- No requests to vote in Hot
Show all 43 signals by file
skills/incubating/bdd-agents-handoff/references/agents.md
- Network accessline 17
| Codex app | `codex://new?prompt=<prompt>&path=<abs path>` | Opens the session in the Codex app. Also `codex://threads/new?...` and `originUrl=<git remote>`. Needs at least one of `prompt`, `path`, `originUrl`. Effort: no public docs list - Network accessline 19
| Cursor | `cursor://anysphere.cursor-deeplink/prompt?text=<prompt>` | Opens in the current workspace, no path parameter. Web form: `https://cursor.com/link/prompt?text=...`. Full URL max 10,000 chars. |
skills/incubating/bdd-agents-handoff/scripts/scan.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/published/qc-alchemy/references/color-matching.md
- Network accessline 73
工具接口可查 [Pillow ImageCms](https://pillow.readthedocs.io/en/stable/reference/ImageCms.html),色彩评估与色域限制可查 [ICC FAQ](https://www.color.org/faqs/)。具体案例色号留在实验记录中,不作为新任务的默认色板。 - Network accessline 73
工具接口可查 [Pillow ImageCms](https://pillow.readthedocs.io/en/stable/reference/ImageCms.html),色彩评估与色域限制可查 [ICC FAQ](https://www.color.org/faqs/)。具体案例色号留在实验记录中,不作为新任务的默认色板。
skills/published/qc-image-series/scripts/render-chapter-dividers.py
skills/published/qc-motion-design/assets/motion-cases/README.md
skills/published/qc-motion-design/assets/motion-cases/advanced-components.js
skills/published/qc-motion-design/assets/motion-cases/advanced-motion.js
skills/published/qc-motion-design/assets/motion-cases/app.js
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 79
const sourceCache=new Map(); async function readSource(index){ if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));} - Network accessline 79
const sourceCache=new Map(); async function readSource(index){ if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));} - Network accessline 80
async function readSource(index){ if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));} return sourceCache.get(ind - Network accessline 80
async function readSource(index){ if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));} return sourceCache.get(ind - Network accessline 81
if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));} - Network accessline 81
if(!sourceCache.has(index)){const response=await fetch(docs[index].file);if(!response.ok)throw new Error('无法读取原文');sourceCache.set(index,(await response.text()).split('\n'));}
skills/published/qc-motion-design/assets/motion-cases/assets/motion-landscape.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 360"><rect width="640" height="360" fill="#e7ece1"/><circle cx="474" cy="87" r="38" fill="#dfbc74"/><path d="M0 280 186 84 395 310 640 129V360H0Z" fill="#9aaa8c"/><path d="m0 360 297- - Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 360"><rect width="640" height="360" fill="#e7ece1"/><circle cx="474" cy="87" r="38" fill="#dfbc74"/><path d="M0 280 186 84 395 310 640 129V360H0Z" fill="#9aaa8c"/><path d="m0 360 297-
skills/published/qc-motion-design/assets/motion-cases/extra-components.js
skills/published/qc-motion-design/assets/motion-cases/extra-motion.js
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 22
loadImage.classList.remove('ready');loadImage.hidden=true;imageState.textContent='正在载入…'; try{ const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal}); - Network accessline 22
loadImage.classList.remove('ready');loadImage.hidden=true;imageState.textContent='正在载入…'; try{ const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal}); - Network accessline 23
try{ const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal}); if(!response.ok)throw new Error('load failed'); - Network accessline 23
try{ const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal}); if(!response.ok)throw new Error('load failed'); - Network accessline 24
const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal}); - Network accessline 24
const response=await fetch(fail?'data:image/svg+xml,invalid-svg':'assets/motion-landscape.svg',{signal:controller.signal});
skills/published/qc-motion-design/assets/motion-cases/motion-prompts.js
skills/published/qc-motion-design/assets/motion-cases/source-notes.js
skills/published/qc-motion-design/assets/motion-cases/sources/animation-design-skill.md
- Network accessline 12
> I'm ready to help you build interfaces that feel right, my knowledge comes from Emil Kowalski's design engineering philosophy. If you want to dive even deeper, check out Emil’s course: [animations.dev](https://animations.dev/). - Network accessline 12
> I'm ready to help you build interfaces that feel right, my knowledge comes from Emil Kowalski's design engineering philosophy. If you want to dive even deeper, check out Emil’s course: [animations.dev](https://animations.dev/). - Network accessline 123
**Easing curve resources:** Don't create curves from scratch. Use [easing.dev](https://easing.dev/) or [easings.co](https://easings.co/) to find stronger custom variants of standard easings. - Network accessline 123
**Easing curve resources:** Don't create curves from scratch. Use [easing.dev](https://easing.dev/) or [easings.co](https://easings.co/) to find stronger custom variants of standard easings.
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.
Signal confidence: 41 facts
- Network access in prose of documentationbdd-agents-handoff/references/agents.md:17Low confidence
- Network access in prose of documentationbdd-agents-handoff/references/agents.md:19Low confidence
- Executable script in code of a file that runsbdd-agents-handoff/scripts/scan.sh:1High confidence
- Network access in prose of documentationskills/published/qc-alchemy/references/color-matching.md:73Low confidence
- Network access in prose of documentationqc-alchemy/references/color-matching.md:73Low confidence
- Executable script in code of a file that runsskills/published/qc-image-series/scripts/render-chapter-dividers.py:1High confidence
- Executable script in code of a file that runsqc-image-series/scripts/render-chapter-dividers.py:1High confidence
- Network access in prose of documentationskills/published/qc-motion-design/assets/motion-cases/README.md:15Low confidence
- Network access in prose of documentationqc-motion-design/assets/motion-cases/README.md:15Low confidence
- Executable script in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/advanced-components.js:1High confidence
- Executable script in code of a file that runsqc-motion-design/assets/motion-cases/advanced-components.js:1High confidence
- Executable script in a comment of a file that runsskills/published/qc-motion-design/assets/motion-cases/advanced-motion.js:1Low confidence
- Executable script in a comment of a file that runsqc-motion-design/assets/motion-cases/advanced-motion.js:1Low confidence
- Executable script in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/app.js:1High confidence
- Executable script in code of a file that runsqc-motion-design/assets/motion-cases/app.js:1High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/app.js:79High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/app.js:79High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/app.js:80High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/app.js:80High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/app.js:81High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/app.js:81High confidence
- Executable script in a comment of a file that runsskills/published/qc-motion-design/assets/motion-cases/extra-components.js:1Low confidence
- Executable script in a comment of a file that runsqc-motion-design/assets/motion-cases/extra-components.js:1Low confidence
- Executable script in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/extra-motion.js:1High confidence
- Executable script in code of a file that runsqc-motion-design/assets/motion-cases/extra-motion.js:1High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/extra-motion.js:22High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/extra-motion.js:22High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/extra-motion.js:23High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/extra-motion.js:23High confidence
- Network access in code of a file that runsskills/published/qc-motion-design/assets/motion-cases/extra-motion.js:24High confidence
- Network access in code of a file that runsqc-motion-design/assets/motion-cases/extra-motion.js:24High confidence
- Executable script in a comment of a file that runsskills/published/qc-motion-design/assets/motion-cases/motion-prompts.js:1Low confidence
- Executable script in a comment of a file that runsqc-motion-design/assets/motion-cases/motion-prompts.js:1Low confidence
- Executable script in a comment of a file that runsskills/published/qc-motion-design/assets/motion-cases/source-notes.js:1Low confidence
- Executable script in a comment of a file that runsqc-motion-design/assets/motion-cases/source-notes.js:1Low confidence
- Network access in prose of documentationskills/published/qc-motion-design/assets/motion-cases/sources/animation-design-skill.md:12Low confidence
- Network access in prose of documentationqc-motion-design/assets/motion-cases/sources/animation-design-skill.md:12Low confidence
- Network access in prose of documentationskills/published/qc-motion-design/assets/motion-cases/sources/animation-design-skill.md:123Low confidence
- Network access in prose of documentationqc-motion-design/assets/motion-cases/sources/animation-design-skill.md:123Low confidence
- Executable script in code of a file that runsskills/published/qc-skills-setup/scripts/create-claude-md.sh:1High confidence
- Executable script in code of a file that runsqc-skills-setup/scripts/create-claude-md.sh:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/incubating/bdd-agents-handoff/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/incubating/bdd-agents-handoff/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/incubating/bdd-agents-handoff/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/incubating/bdd-agents-handoff/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.