abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
@yogsoth-aiInstall SkillAutomation
Skill
/analyze-leaderboard-dynamics
Analyze leaderboard score distributions, compression/saturation, anomalies, selective reporting, and regime shifts.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill analyze-leaderboard-dynamics -a windsurf -y
SKILL.md
analyze-leaderboard-dynamics.SKILL.mdname: analyze-leaderboard-dynamics
description: "Analyze leaderboard score distributions, compression/saturation, anomalies, selective reporting, and regime shifts."
analyze-leaderboard-dynamics
Purpose
Analyze leaderboard score distributions, compression or saturation, anomalies, selective reporting, and regime shifts.
Input contract
required: [leaderboard_records, metric_schema, time_or_version_field]
optional: [evaluation_protocols, source_quality, method_metadata]
constraints: [scores require task, metric, condition, source, and observation provenance]
Procedure
1. Normalize scores and evaluation conditions into comparable groups. 2. Inspect distributions, rank movement, compression, and missingness. 3. Identify anomalies, selective reporting, and regime changes. 4. State whether additional evidence is continuing, near-saturated, or saturated.
Output contract
produces: [leaderboard_distribution, regime_segments, anomaly_report, saturation_assessment]
delta_fields: [findings, evidence_updates, uncertainties, decisions]
Quality gates
- Every reported regime or anomaly must cite the records and comparison basis.
- Do not compare scores across incompatible protocols without an explicit limitation.
Failure and counterexamples
Do not treat rank order as progress when metric definitions or evaluation conditions changed; preserve ties and missing observations.
Provenance map
- `resolved: leaderboard-dynamics-analysis`
Read more
name: analyze-leaderboard-dynamics description: "Analyze leaderboard score distributions, compression/saturation, anomalies, selective reporting, and regime shifts."
analyze-leaderboard-dynamics
Purpose
Analyze leaderboard score distributions, compression or saturation, anomalies, selective reporting, and regime shifts.
Input contract
required: [leaderboard_records, metric_schema, time_or_version_field] optional: [evaluation_protocols, source_quality, method_metadata] constraints: [scores require task, metric, condition, source, and observation provenance]
Procedure
1. Normalize scores and evaluation conditions into comparable groups. 2. Inspect distributions, rank movement, compression, and missingness. 3. Identify anomalies, selective reporting, and regime changes. 4. State whether additional evidence is continuing, near-saturated, or saturated.
Output contract
produces: [leaderboard_distribution, regime_segments, anomaly_report, saturation_assessment] delta_fields: [findings, evidence_updates, uncertainties, decisions]
Quality gates
- Every reported regime or anomaly must cite the records and comparison basis.
- Do not compare scores across incompatible protocols without an explicit limitation.
Failure and counterexamples
Do not treat rank order as progress when metric definitions or evaluation conditions changed; preserve ties and missing observations.
Provenance map
- `resolved: leaderboard-dynamics-analysis`
Ships withde-anthropocentric-research-engine
A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.
507200 skills
Stars on GitHub
Momentum
- stars in total
- 507
Other skills on de-anthropocentric-research-engine.
@yogsoth-aiInstall Skilladjudicate-exchange
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
@yogsoth-aiInstall Skilladjust-abstraction-sco…
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context,…
@yogsoth-aiInstall Skilladversarial-deliberati…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target,…
@yogsoth-aiInstall Skillaggregate-ranking
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
@yogsoth-aiInstall Skillanalogical-discovery
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
@yogsoth-aiInstall SkillMore skills from other plugins.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
@browser-useInstall Skillagent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…
@vercel-labs-2Install Skill
Questions about analyze-leaderboard-dynamics.
- Which coding agents can use analyze-leaderboard-dynamics?
- analyze-leaderboard-dynamics installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.