Is the Executing Analysis skill free?

Yes. The skill itself is free from K-Dense-AI/science-superpowers. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Executing Analysis SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Executing Analysis?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Executing Analysis with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Executing Analysis

Runs a frozen pre-registered analysis inline with validation gates and stop-on-anomaly

by K-Dense-AI · K-Dense-AI/science-superpowers

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 422072f

Fetched SKILL.md via raw GitHub; frontmatter parses with name+description; single-file skill with no scripts, but its 6 referenced sibling skills all resolve HTTP 200. No security smells. For OUTPUT I built a tiny frozen pre-registration (H1: mean B>A, valid score range 0-100, no exclusions) over an 8-row raw.csv with a planted 999 data-entry error, then ran two Python executions. Baseline naively computed mean B=295.75 and reported a "significant" reject-H0 result; skill-followed execution applied the body's Step 2.4 range-validation gate, caught the out-of-range value, halted, and refused to produce a p-value instead of silently dropping the row.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Executing Analysis does

A procedural skill that executes an already pre-registered, frozen analysis plan step by step in the current session, validating each output's shape/ranges/counts, applying the registered decision rule as written, and halting on anomalies instead of silently dropping data. Triggers when you have a locked pre-registration to run inline on a platform without subagents, with review checkpoints between step groups. Delegates anomaly root-causing, verification, and reporting to sibling science-superpowers skills.

How to install Executing Analysis

git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git /tmp/executing-analysis-src
mkdir -p ~/.claude/skills
cp -R /tmp/executing-analysis-src/skills/executing-analysis ~/.claude/skills/executing-analysis
# No external deps (zero third-party deps, POSIX shell only).
# Works best as part of the full science-superpowers set: this skill references sibling skills
# (preregistering-analysis, setting-up-reproducible-analysis, verifying-results-before-claiming,
#  investigating-anomalous-results, reporting-and-archiving-findings, requesting-red-team-review).
# To install all of them:  cp -R /tmp/executing-analysis-src/skills/* ~/.claude/skills/

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Executing Analysis

/executing-analysis Runs a frozen pre-registered analysis inline with validation gates and stop-on-anomaly

It also activates on plain-language prompts like these:

Execute this analysis plan step by step
Run the pre-registered analysis with checkpoints
Walk through this analysis plan for review

Frequently asked questions

Is the Executing Analysis skill free?: Yes. The skill itself is free from K-Dense-AI/science-superpowers. SkillProof publishes the install command and an independent test verdict at no cost.
Does Executing Analysis work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub; frontmatter parses with name+description; single-file skill with no scripts, but its 6 referenced sibling skills all resolve HTTP 200. No security smells. For OUTPUT I built a tiny frozen pre-registration (H1: mean B>A, valid score range 0-100, no exclusions) over an 8-row raw.csv with a planted 999 data-entry error, then ran two Python executions. Baseline naively computed mean B=295.75 and reported a "significant" reject-H0 result; skill-followed execution applied the body's Step 2.4 range-validation gate, caught the out-of-range value, halted, and refused to produce a p-value instead of silently dropping the row.
What is the Executing Analysis SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Executing Analysis?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Executing Analysis with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.