analysis-workflow
Organize multi-step scientific analyses into reproducible, self-contained modules.
Skill by ccfwwm
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ccfwwm-analysis-workflow
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, data, research, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/analysis-workflow
What's inside
- Skill name
analysis-workflow- Description
- Organize multi-step scientific analyses into reproducible, self-contained modules. Use for workflows such as QC→PCA→DEG→GSEA that produce scripts, inputs, figures, tables, and methods. Creates a stable module layout, records exact inputs/parameters/package and database versions in each module README, keeps large data as references instead of copies, and verifies outputs before completion.
- License
- Apache-2.0
- Instructions
- 117 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Reproducible Analysis Modules
Use this skill for a scientific workflow with two or more analysis stages or
when a stage produces scripts plus result files. It defines project
organization and methods capture; load `figure-style` as well whenever a stage
creates or revises a plot.
## 1. Plan module boundaries
Before writing outputs, list the modules and the dependency edges between them.
Use stable ASCII names. Conventional acronyms such as `QC`, `PCA`, `DEG`, and
`GSEA` may stay uppercase; otherwise prefer a short kebab-case name.
Respect a compatible layout that already exists. Do not reorganize unrelated
user files merely to impose this convention.
## 2. Default module layout
Create only directories the module actually needs:
```text
<module>/
├── scripts/
├── input/
├── output/
│ ├── figures/
│ └── tables/
└── README.md
```
- `scripts/` contains the executable source for this module.
- `input/` contains small module-specific inputs or a manifest/reference to the
canonical data. Do not duplicate a large dataset by default.
- `output/figures/` contains rendered figures from this module only.
- `output/tables/` contains machine-readable results from this module only.
- `README.md` is the module's reproducibility record and methods source.
Shared immutable/raw data may live in project-level `data/`. A downstream module
references an upstream output by a project-relative path; it does not silently
copy or rename that output.
## 3. Make outputs attributable
Every output must have one producing script or recorded command. Use
deterministic filenames that identify the analysis and content. Keep temporary
files outside the final output directories or name them clearly as temporary.
Before completing a module, verify:
1. every declared output exists and is non-empty;
2. every table can be parsed in its declared format;
3. every figure was rendered and visually inspected using `figure-style`;
4. README input and output paths resolve from the project root;
5. reported thresholds and parameters match the actual script.
## 4. Update README.md at module completion
Create or update these sections:
```markdown
# <Module>
## Purpose
<scientific question and role in the workflow>
## Inputs
- `<project-relative path>` — source, upstream module, checksum or version when available
## Methods
<method in prose, including transformations, statistical tests, correction method,
thresholds, seeds, and other result-changing parameters>
## Software and data sources
- R/Python package: exact version
- External API/database: release or access date
- ZeroWall/model/runtime metadata: exact recorded value when available
## Commands and scripts
- `<project-relative script>` — how it was executed
## Outputs
- `<project-relative path>` — meaning and format
## Limitations
<assumptions, exclusions, and unresolved reproducibility gaps>
```
Write methods from executed code and recorded parameters, not from a generic
template. Do not claim a package, database, model, OS, or version that was not
actually used or observed.
## 5. Capture exact versions without dumping the world
Record direct dependencies used by the module:
- R: `packageVersion("<package>")` for named packages and `sessionInfo()` for
the runtime context.
- Python: `importlib.metadata.version("<distribution>")`; use the project lock
file when it is the authoritative environment record.
- External databases/APIs: release identifier when available, otherwise access
date plus endpoint/source.
- ZeroWall version and model profile: use runtime/session metadata only when it is
available. Write `unavailable` rather than guessing.
Do not paste an entire global `pip freeze` into every module. If a complete
environment export is useful, save it once as a separate artifact and link it
from the README.
## 6. Finish the workflow
After all modules pass their checks, summarize the dependency chain and link the
module READMEs. Treat those READMEs as the first-version source of truth.
Generate a root `METHODS.md` only when the user asks for it or a deterministic
project tool can derive it from the module records; do not maintain a second
hand-edited copy that can drift.From ccfwwm/zerowall-dsh-plugins, Apache-2.0.
More from ccfwwm/zerowall-dsh-plugins
- 0.592score
analytical-method-validation
ccfwwm
Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
ppt-maker
ccfwwm
生成/编辑/逆向/导出 PPT 与演示文稿。工具优先:用插件注册的十一个 ppt_* 工具完成创建/编辑/撤销/重做/渲染/质检/导出,以及把既有 .pptx 逆向成 PPTD 工程或外科手术式轻改(引擎 @office-kit/pptx,本地纯 TS 构建最终 pptx);Python…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
issue-triage
ccfwwm
对本仓库的 issue 与 PR 做分类/判别(类型 · 领域 · 优先级),给出「关闭 / 追信息 / 留待办 / 等 review」的结论,并把结果同步到 Projects v2 排期看板与分诊文档。触发词:分诊 issue、整理/清理 issue、打优先级标签、判 issue 还是 PR、PR 排队、把 PR…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
alphafold2
ccfwwm
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
agent-infini
ccfwwm
Use the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and task workspace files.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
dsh-release-notes
ccfwwm
根据缓存的候选 commit 为 dsh-file-review 生成精简、易读的 GitHub Release 草稿,仅包含 Features 和 Bug Fixes。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
media-create
ccfwwm
通过对话创作用户明确要求的独立视频、音乐与宣传片。普通图片生成和编辑使用 gpt-image-generator;媒体项目中的图片只作为视频参考素材。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
academic-research-shared
ccfwwm
Shared contracts and references used by the integrated Academic Research Skills.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ars-cache-invalidate
ccfwwm
ARS /ars-cache-invalidate — drop cached verification entries for a citation key
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ars-3w
ccfwwm
ARS deep-research `three-way-scan` mode — WHY / HOW / WHAT paper comparison
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ars-citation-check
ccfwwm
ARS academic-paper `citation-check` mode — citation error report
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
ars-abstract
ccfwwm
ARS academic-paper `abstract-only` mode — bilingual abstract + keywords
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 12, 2026 (17 days ago)
- Last release
- Oct 21, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/ccfwwm/zerowall-dsh-plugins
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ccfwwm
- 0.592score
analytical-method-validation
ccfwwm
Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
ppt-maker
ccfwwm
生成/编辑/逆向/导出 PPT 与演示文稿。工具优先:用插件注册的十一个 ppt_* 工具完成创建/编辑/撤销/重做/渲染/质检/导出,以及把既有 .pptx 逆向成 PPTD 工程或外科手术式轻改(引擎 @office-kit/pptx,本地纯 TS 构建最终 pptx);Python…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
issue-triage
ccfwwm
对本仓库的 issue 与 PR 做分类/判别(类型 · 领域 · 优先级),给出「关闭 / 追信息 / 留待办 / 等 review」的结论,并把结果同步到 Projects v2 排期看板与分诊文档。触发词:分诊 issue、整理/清理 issue、打优先级标签、判 issue 还是 PR、PR 排队、把 PR…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
alphafold2
ccfwwm
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
agent-infini
ccfwwm
Use the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and task workspace files.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
dsh-release-notes
ccfwwm
根据缓存的候选 commit 为 dsh-file-review 生成精简、易读的 GitHub Release 草稿,仅包含 Features 和 Bug Fixes。
SkillAFreshness: A★ 1Claude Code +9
Cite this page
analysis-workflow skill. Agent Mart. https://agentmart.dev/skills/ccfwwm-analysis-workflow (last updated 2026-10-24)