Is the Dispatching Parallel Investigations 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 Dispatching Parallel Investigations 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 Dispatching Parallel Investigations?

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 Dispatching Parallel Investigations 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.

Dispatching Parallel Investigations

Split independent investigations into focused parallel subagent tasks with a report-all guard

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 · 87d1f13

Fetched SKILL.md raw; the skill dir contains only SKILL.md (no scripts), and the four sibling skills it references all exist in the repo tree. No security smells in the body. Trigger: judged 5 phrasings — SHOULD-fire: "replicate the same OLS across 5 independent datasets, report all coefficients", "survey prior work across several independent sub-topics in parallel", "run my pre-specified robustness checks all at once"; should-NOT: "refactor this function to be faster", "run one analysis where step 2 depends on step 1's output" (shared state) — all 5 correct. Output: built two real dispatch-prompt artifacts (baseline2.md vs skill2.md) for a 3-dataset replication task; baseline used vague "see if the effect holds" prompts, the skill version embedded the exact pre-registered spec, a seed, immutable data path, a no-alternative-specs constraint, result+method+N reporting for verification, and a report-all-sites mandate — the concrete, quotable difference.

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 Dispatching Parallel Investigations does

Guides how to split 2+ independent investigations (multi-dataset replication, parallel literature survey, pre-specified robustness checks) into focused, self-contained subagent tasks and then synthesize the results. Triggers when a user has several independent analyses that share no state and can run concurrently. Enforces a pre-registration guard so parallel dispatch reports all results rather than cherry-picking the specification that "works."

How to install Dispatching Parallel Investigations

git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git /tmp/dispatching-parallel-investigations-src
mkdir -p ~/.claude/skills
cp -R /tmp/dispatching-parallel-investigations-src/skills/dispatching-parallel-investigations ~/.claude/skills/dispatching-parallel-investigations
# No scripts or deps — SKILL.md is self-contained guidance.
# References sibling skills in the same repo (verifying-results-before-claiming, surveying-prior-work,
# subagent-driven-analysis, investigating-anomalous-results); cp -R the whole skills/ dir to get them too.

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

Commands — how to trigger Dispatching Parallel Investigations

/dispatching-parallel-investigations Split independent investigations into focused parallel subagent tasks with a report-all guard

It also activates on plain-language prompts like these:

Run these robustness checks in parallel
Dispatch parallel literature surveys on this topic
Replicate this analysis across multiple datasets

Frequently asked questions

Is the Dispatching Parallel Investigations 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 Dispatching Parallel Investigations work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md raw; the skill dir contains only SKILL.md (no scripts), and the four sibling skills it references all exist in the repo tree. No security smells in the body. Trigger: judged 5 phrasings — SHOULD-fire: "replicate the same OLS across 5 independent datasets, report all coefficients", "survey prior work across several independent sub-topics in parallel", "run my pre-specified robustness checks all at once"; should-NOT: "refactor this function to be faster", "run one analysis where step 2 depends on step 1's output" (shared state) — all 5 correct. Output: built two real dispatch-prompt artifacts (baseline2.md vs skill2.md) for a 3-dataset replication task; baseline used vague "see if the effect holds" prompts, the skill version embedded the exact pre-registered spec, a seed, immutable data path, a no-alternative-specs constraint, result+method+N reporting for verification, and a report-all-sites mandate — the concrete, quotable difference.
What is the Dispatching Parallel Investigations 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 Dispatching Parallel Investigations?: 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 Dispatching Parallel Investigations 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.