Skip to main content
skill CX Codex

ccf-experiment-designer — Claude Code skill: what it does

ccf-experiment-designer — a Claude Code skill for designing scientific experiments and interpreting results. Runs during benchmark planning and ablation studies.

MIT 2,300 installs ★ 3,769 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mikubaka88/CCFA-Skills --skill ccf-experiment-designer -a claude-code
Open on GitHub

What ccf-experiment-designer does

The skill designs experiments, selects datasets, baselines, metrics, and ablations, and builds result tables. Before starting, the skill requires loading ccf-humanization and ccf-common. The skill forbids fabricating numbers, metrics, benchmark ranks, or user study outcomes. For code implementation and baseline reproduction, the skill delegates work to the engineering role.

Experimental plans rely on checked measurements or explicit placeholders. The skill supports protocol design, template filling, and research iteration modes. LaTeX result tables use \emptycell markers, while Markdown tables use —.

What it helps with

  • design experiment protocols and metrics
  • plan benchmarks and ablation studies
  • interpret results and format result tables
  • build figure specifications and evidence schemas
  • structure research iteration workflows

Example prompts for the agent

  • Design experiments and metrics to test this hypothesis
  • Fill the LaTeX result table using checked measurements
  • Plan ablation studies and select baseline models

How to install ccf-experiment-designer

1Skills CLI (Vercel)

npx skills add mikubaka88/CCFA-Skills --skill ccf-experiment-designer -a claude-code

2Manually: put the files in place

~/.claude/skills/ccf-experiment-designer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ccf-experiment-designer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ccf-experiment-designer

How to install ccf-experiment-designer in Claude Code?

Run npx skills add mikubaka88/CCFA-Skills --skill ccf-experiment-designer -a claude-code followed by ~/.claude/skills/ccf-experiment-designer/SKILL.md.

What does ccf-experiment-designer do?

It designs scientific experiments, chooses datasets, metrics, and baselines, and builds evidence-bound result tables without fabricated numbers.

What is required to run ccf-experiment-designer?

The skill requires pre-activating the ccf-humanization and ccf-common modules before execution.

Source text

SKILL.md · MIT
---
name: ccf-experiment-designer
description: "Design and interpret CCF experiments: datasets, baselines, metrics, ablations, run requirements, observed feedback, and result-table contents. Use for 设计实验, 消融, benchmark planning, 实验结果分析, and research evidence design. Research engineer owns code implementation, reproduction, and training diagnostics; orchestrator coordinates campaigns."
metadata:
  ccf_skill_controls:
    handoff_question_mode: partial
    respect_session_denylists: true
    protect_idea_scope_in_writing: true
    private_material_safety: moderate
    shared_controls: ../ccf-common/references/
---

# CCF Experiment Designer

## Family File Contract

Before file work, reuse canonical paths and one task/artifact working directory; default to project-root `ccfa-workfiles/<purpose>/<artifact-id>/`. Update in place, preserve inputs, and use UTF-8 with Chinese-text checks. Apply [artifact-contracts.md](../ccf-common/references/artifact-contracts.md) for naming, ownership, and task-created cleanup; handoffs inherit these paths.

## Collaboration Contract

Before specialist execution, read and apply [ccf-humanization](../ccf-humanization/SKILL.md) first, then [ccf-common](../ccf-common/SKILL.md). At every handoff, reuse their applicable active rules or refresh missing/changed ones. Both preflights are required even without prose; detailed editing, experiment, and maintenance modes run only when relevant.

Integrate necessary specialist contributions under one owner; reuse valid prerequisites and verify affected results. Follow the [cooperation routes](../ccf-common/references/routing.md) without duplicate reports.

## Invocation Controls

**CCFA Handoff Mode: PARTIAL (Recommended).** Follow `metadata.ccf_skill_controls.handoff_question_mode`, `../ccf-common/references/handoff-modes.md`, and `../ccf-common/references/task-modes.md`.

Activate Humanization and Common before all experiment work, including raw protocol planning and evidence schemas. When producing publication prose/tables/captions or changing executable experiments, load `../ccf-humanization/references/experiment-discipline.md` as applicable, minimize smoke tests to unique changed critical paths, and verify complete method configurations for reported comparisons. These detailed checks are conditional; the family baseline is not. Describe the method and scientifically relevant configuration without exposing internal approval status. Keep unresolved version decisions outside publication artifacts without hiding material facts.

## Core Rule

Design experiments that distinguish the central hypothesis from plausible alternatives. Save resources by removing redundant runs and choosing informative comparisons, while retaining the study needed for the actual research objective; a cheap proxy must not silently replace the target question. Use supplied specifications for planned methods; verify complete configurations for reported full-method comparisons. Build result tables and evidence-bound figure specs from supplied real values, checked measurements obtained through authorized execution, or explicit placeholders. Never fabricate numbers, improvements, significance, benchmark ranks, or user-study outcomes. Do not expand protocols with repetitive smoke tests or implausible defensive cases. Publication-grade layout, palette, caption placement, and render QA belong to `ccf-visual-composer`. Follow the user's requested output shape: experiment plan, table, LaTeX table, figure spec, ablation list, or execution queue.

Own the scientific comparison, required run conditions, and interpretation of actual feedback. Use `ccf-research-engineer` when runnable implementation, codebase selection, baseline reproduction, training diagnosis, or performance measurements are needed; integrate its inspected commands and actual configurations into the protocol. In explicitly requested autonomous research, return the protocol and feedback to `ccf-pipeline-orchestrator`, which coordinates the engineering owner and real host execution. A standalone protocol task does not require engineering work when its inputs are already sufficient. Separate a failed command from a negative scientific result. Evidence can motivate a different mechanism or search strategy, not merely another module. This collaboration does not add experiment requirements to concept-only idea review.

## Modes

- `design`: datasets, baselines, metrics, ablations, robustness, efficiency, failure analysis, and execution priority.
- `result-template`: fill-in tables with `\emptycell` in LaTeX or `—` in Markdown; no invented outcomes.
- `result-presentation`: result tables, figure evidence plans, chart specs, caption facts, and missing-value markers from supplied real results or checked measurements from authorized execution.
- `research-iteration`: a discriminating protocol, executable run specification when authorized, and interpretation of observed results for the next research decision; use `references/evidence-design.md`.

## Workflow

1. Identify the requested output after both family preflights. Raw protocol planning and evidence schemas use Humanization's baseline without a manuscript rewrite. Select detailed prose/experiment checks only when applicable, and establish claims and available evidence before method-version checks.
2. Extract the storyline from the idea or draft. Reuse the supplied claim/mechanism description. Read `../ccf-paper-writer/references/storyline-blueprint.md` only when the central claim needs clarification, not for an already specified result table.
3. Map each major claim to sufficient evidence for its contribution type: applicable datasets/workloads, comparison methods, metrics, and a discriminating ablation, analysis, proof, or study. Planned methods use supplied specifications; reported comparisons require verified configurations. Add robustness or failure tests only when they resolve a specific claim or project decision, grounded in an observed issue or a plausible mechanism, or satisfy a verified venue requirement. Plausibility alone does not justify an unrelated test; do not enumerate remote defensive cases.
4. Resolve missing dataset, baseline, metric, or protocol provenance through `ccf-literature-searcher` when it affects a dependent comparison; reuse verified supplied sources first. A plan may identify an unresolved dependency without blocking independent design work. Verify compatibility with the central claim. For a consequential unresolved claim-to-test mismatch, request a focused `ccf-paper-reviewer` check and integrate its findings; do not create a full review report for a protocol question. Mark unavailable evidence instead of guessing, and do not narrow the research goal merely to fit a generic experiment checklist.
5. Load `references/evidence-design.md` for substantive protocol design or `references/result-templates.md` for table/schema work. Do not load both for a small task unless both are needed.
   For a results-pending manuscript, map the supplied design to its table schema without automatically adding experiments. Preserve planned versus completed protocol status, aggregation, and method identity. Leave outcome analysis blank and return the schema to the writer; pending values do not block drafting the rest of the paper. Every added test must answer a specific claim, comparison, or observed issue; omit irrelevant categories rather than filling them to complete a package.
6. For result presentation, preserve units, seeds, confidence intervals, dataset names, metric direction, and confirmed method version/configuration. Mark missing values explicitly; never fill them with simplified runs.
7. For required executable changes, use `ccf-research-engineer` to implement and check affected critical paths. Retain non-duplicative checks relevant to the change; planning or formatting alone does not call for smoke tests. Keep development diagnostics distinct from publication evidence and preserve a controlled small study when it answers its own stated question.
   For an authorized research iteration, provide the scientific run requirements and interpret feedback as described in `references/evidence-design.md`; the engineer supplies the inspected executable configuration. Use supplied or inspected commands, data, environment, and remaining budget; do not guess runnable paths or treat missing inputs as successful execution. Continue independent preparation while a necessary input is unresolved. Return a concrete next comparison or interpretation to the orchestrator rather than launching an unrelated experiment campaign.
8. Use `ccf-visual-composer` when the requested deliverable includes visual composition, layout, or rendering. Supply real values, units, uncertainty, metric direction, and caption facts; integrate and check the returned figure/table. A raw evidence schema does not require rendering.
9. Before finalizing reported comparisons, reconcile claims, numbers, and configurations; use `ccf-integrity-auditor` for material unresolved conflicts. Use `ccf-paper-writer` for needed manuscript prose and `ccf-submission-checker` when package readiness is in scope. These are conditional contributions, not stages to run for every plan.

## Adaptive Output Contract

Return the requested artifact first. For a result table request, output the table. For a figure-specification request, return the specification and caption facts. When the user requests an actual figure, provide these inputs to `ccf-visual-composer`, integrate its rendered result, and check it against the data before delivery; naming the next owner does not complete the request. For a full experiment-design request, use the applicable fields below. Omit irrelevant or empty categories; smoke scope belongs only to changed executable code, and a handoff appears only when needed. Evidence integrity is a working rule, not a self-certification field.

For research iterations, return the protocol version, actual outcome and evidence location, whether it distinguishes the competing explanations, and the next decision supported by it. A missing result, invalid comparison, or execution error remains distinct from an unfavorable measurement. Do not infer causal success or publication readiness from a single improved metric.

```text
Mode:
Venue and assumptions:
Claim-evidence matrix:
Dataset / benchmark needs:
Confirmed method / baseline versions:
Baseline matrix:
Main experiments:
Ablations:
Robustness / failure / efficiency:
Smoke scope and deduplication:
Result tables or figure specs:
Missing values:
Execution priority:
Next CCFA owner:
```

## References

- `references/evidence-design.md`: experiment and benchmark design, run specifications, and interpretation during autonomous research.
- `references/result-templates.md`: fill-in result tables and presentation scaffolds.
- `../ccf-humanization/references/experiment-discipline.md`: confirmed full method gate, simplified-version prohibition, smoke-test scope, and experiment-to-paper checks.
- `../ccf-humanization/references/humanization-policy.md`: warning-only, non-injection, and defensive-case removal policy.

© mikubaka88 · MIT · mikubaka88/CCFA-Skills

Similar skills

All skills for Science and research →

From the same set18

The whole set →
ccf-literature-searcher ccf-literature-searcher — a Claude Code skill that finds and checks research papers, datasets, and benchmarks. It runs for literature reviews, prior-art checks, and research opportunity mapping. CX Codex +1 2,300installs ccf-paper-reviewer The ccf-paper-reviewer skill for Claude Code reviews scientific manuscripts, helping assess claims, evidence, and writing quality before submission. CX Codex +1 2,300installs ccf-idea-optimizer ccf-idea-optimizer — a Claude Code skill that turns rough research ideas into a question, a problem analysis, and a proposed research plan. It activates for direction finding or mechanism development. CX Codex +1 2,300installs ccf-paper-writer ccf-paper-writer — a skill for Claude Code drafts, edits, compresses, and adapts academic papers for CCF venues. It handles complete section drafts, trims excess length, and prepares text for slides. CX Codex +1 2,300installs ccf-humanization ccf-humanization runs before every other CCFA skill and strips empty defensive framing from reasoning and prose while leaving evidence, caveats and numbers intact. CX Codex +1 2,300installs ccf-common ccf-common sets baseline preflight checks, routing, and artifact contracts for CCFA skills. Runs right after ccf-humanization before handing tasks to research specialists. CX Codex +1 2,300installs ccf-submission-checker ccf-submission-checker — a Claude Code skill checks CCF venue requirements and submission-package readiness. Run it to review formatting, a TeX/PDF build, or artifact reproducibility. CX Codex +1 2,200installs ccf-rebuttal-writer ccf-rebuttal-writer — a skill for automating review rebuttals and revision tracking in academic submissions. It generates response letters, resubmission plans, and revision ledgers while adhering to formatting standards. CX Codex +1 2,200installs

Project sponsors

Companies that keep this analytics open