A skill your agent uses when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-results --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/investigating-anomalous-results .claude/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .claude/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-resultsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-results --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/investigating-anomalous-results .agents/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .agents/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-results --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/investigating-anomalous-results .cursor/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .cursor/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/K-Dense-AI/science-superpowers.git --path skills/investigating-anomalous-results--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-results --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/investigating-anomalous-results .gemini/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .gemini/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-resultsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/investigating-anomalous-results .github/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .github/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install K-Dense-AI/science-superpowers investigating-anomalous-results --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/K-Dense-AI/science-superpowers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/investigating-anomalous-results .opencode/skills/investigating-anomalous-results && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "investigating-anomalous-results" agent skill from https://github.com/K-Dense-AI/science-superpowers/tree/main/skills/investigating-anomalous-results into .opencode/skills/investigating-anomalous-results/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigating-anomalous-results", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
investigating-anomalous-resultsA skill your agent uses when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
Investigating Anomalous Results is an agent skill from K-Dense-AI/science-superpowers. Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Databases, covering Database administration. The repository describes itself as: Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0374bdf. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Investigating Anomalous Results loads about 1.9k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 1,024 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,024 words (~1,916 tokens).
“Random tweaks waste time and manufacture false findings. Quietly dropping the inconvenient data point, nudging the cutoff, or re-running until it "works" doesn't fix the problem — it fabricates a result.”
Just SKILL.md in skills/investigating-anomalous-results of K-Dense-AI/science-superpowers.
Open the folder on GitHubat commit 0374bdf
Investigating Anomalous Results next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Investigating Anomalous Results this skillK-Dense-AI/science-superpowers | 350 | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Bio Multi Omics Similarity NetworkGPTomics/bioSkills | 1.2k | 1 repos | ~4.3k | Automated safety check: Pass | MIT | |
| Apsr Transparency And Data Policyfranklee16/academic-research-skills | 223 | 1 repos | ~1.1k | Automated safety check: Pass | None | |
| Est Study Designfranklee16/academic-research-skills | 223 | 1 repos | ~882 | Automated safety check: Pass | None | |
| Jape Replication And Data Policyfranklee16/academic-research-skills | 223 | 1 repos | ~671 | Automated safety check: Pass | None | |
| Jbes Replication And Data Policyfranklee16/academic-research-skills | 223 | 1 repos | ~1k | Automated safety check: Pass | None |
GPTomics/bioSkills
Stratifies patients into multi-omics subtypes by building one patient-by-patient similarity network per omic, fusing them with SNF's cross-network diffusion, and spectral-clustering the fused graph…
franklee16/academic-research-skills
A skill your agent uses when preparing the reproducibility / replication materials for an American Political Science Review (APSR) manuscript.
franklee16/academic-research-skills
A skill your agent uses when designing experiments, sampling campaigns, or modeling studies for Environmental Science & Technology (ES&T) so the design survives expert review — environmental…
franklee16/academic-research-skills
A skill your agent uses when assembling the mandatory JAE Data Archive deposit for an accepted Journal of Applied Econometrics paper — plain-ASCII/CSV data with a readme, the programs that replicate…
franklee16/academic-research-skills
A skill your agent uses when assembling the reproducible data-and-code supplement for a Journal of Business & Economic Statistics (JBES) paper under the American Statistical Association (ASA)…
franklee16/academic-research-skills
A skill your agent uses when assembling the supplementary-materials / replication deposit for a Journal of Monetary Economics (JME) manuscript — depositing data, code (Dynare/MATLAB/Stata/R), and…
K-Dense-AI/science-superpowers
A skill your agent uses when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model
K-Dense-AI/science-superpowers
A skill your agent uses when facing 2+ independent investigations that can proceed without shared state - parallel literature survey, multi-dataset replication, or pre-specified robustness checks
K-Dense-AI/science-superpowers
A skill your agent uses when your human partner has explicitly opted into exploratory or feasibility mode - a compute-heavy simulation, an unproven pipeline, an unbenchmarked solver, an untested…
K-Dense-AI/science-superpowers
You MUST use this before any data analysis or investigation - before exploring a dataset, loading or profiling data, running a model, computing a statistic, or testing an idea, and before any…
K-Dense-AI/science-superpowers
A skill your agent uses when receiving critical feedback on an analysis or manuscript, before implementing suggestions, especially if feedback seems unclear or methodologically questionable -…
K-Dense-AI/science-superpowers
A skill your agent uses when an analysis is complete and verified, and you need to decide how to report it and archive the work for reproducibility
Categories
A skill your agent uses when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything. Investigating Anomalous Results is an agent skill from K-Dense-AI/science-superpowers.
Investigating Anomalous Results fits situations like: A result is surprising; contradicts a sanity check; A pipeline fails; A model wont converge.
Run `npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a claude-code`. Or copy the skill folder (skills/investigating-anomalous-results in K-Dense-AI/science-superpowers) into .claude/skills/investigating-anomalous-results in your project. Claude Code loads it when a task matches its description.
Run `npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a codex`. Or copy the skill folder (skills/investigating-anomalous-results in K-Dense-AI/science-superpowers) into .agents/skills/investigating-anomalous-results in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/investigating-anomalous-results, .gemini/skills/investigating-anomalous-results, .github/skills/investigating-anomalous-results and .opencode/skills/investigating-anomalous-results in your project.
Going by SKILL.md and its folder, Investigating Anomalous Results needs the command-line tools its instructions call (git).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Investigating Anomalous Results has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Investigating Anomalous Results: Bio Multi Omics Similarity Network (GPTomics/bioSkills, 1.2k stars), Apsr Transparency And Data Policy (franklee16/academic-research-skills, 223 stars), Est Study Design (franklee16/academic-research-skills, 223 stars) and Jape Replication And Data Policy (franklee16/academic-research-skills, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/science-superpowers, which has 350 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 13, 2026.
Source: K-Dense-AI/science-superpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
