Updated 2w ago
by yogsoth-ai
de-anthropocentric-research-engine
A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, composed in any order with explicit backtracking. One npx install, no runtime, no MCP bindings. The AI is the researcher; you set the direction.
503 GitHub stars (503)
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | +1 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | +1 |
| Oct 11 | +1 |
| Oct 12 | −1 |
| Oct 13 | +1 |
| Oct 14 | −4 |
| Oct 15 | +1 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 42 forks (42 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add yogsoth-ai/de-anthropocentric-research-engine
Asks which skills and agents to install. Just one: npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill abstract-structure — add -g for every project.
Claude Code
git clone https://github.com/yogsoth-ai/de-anthropocentric-research-enginecp -r "de-anthropocentric-research-engine/skills/abstract-structure" ~/.claude/skills/
Copies the abstract-structure skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add yogsoth-ai/de-anthropocentric-research-engine
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 271 files.
-
abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
skills/abstract-structure/SKILL.md on GitHub (opens in a new tab) -
adjudicate-exchange
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
skills/adjudicate-exchange/SKILL.md on GitHub (opens in a new tab) -
adjust-abstraction-scope
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful explanatory and experimental leverage.
skills/adjust-abstraction-scope/SKILL.md on GitHub (opens in a new tab) -
adversarial-deliberation
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth, loser-resurrection, and steelman/winner-stress modes are parameters; role execution is runtime-agnostic.
skills/adversarial-deliberation/SKILL.md on GitHub (opens in a new tab) -
aggregate-ranking
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
skills/aggregate-ranking/SKILL.md on GitHub (opens in a new tab) -
analogical-discovery
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
skills/analogical-discovery/SKILL.md on GitHub (opens in a new tab) -
analyze-constraints-readiness
Characterize what blocks a research target: readiness dimensions, obstacles, bottlenecks, resource gaps, causal constraints, dependencies, conflicts, removability, and mitigation pathways. Depth selects lightweight triage, readiness assessment, or causal/TOC-style constraint analysis.
skills/analyze-constraints-readiness/SKILL.md on GitHub (opens in a new tab) -
analyze-experiment-results
Interpret completed experimental outputs after host/runtime execution using pre-declared statistical tests, effect/uncertainty estimates, reproducibility checks, and calibrated synthesis.
skills/analyze-experiment-results/SKILL.md on GitHub (opens in a new tab) -
analyze-future-scenarios
Construct and compare plausible future/competitive/temporal/stress scenarios and test whether the research path remains robust across them.
skills/analyze-future-scenarios/SKILL.md on GitHub (opens in a new tab) -
analyze-heterogeneity
Identify clinical, methodological, and statistical heterogeneity sources and prioritize subgroup/meta-regression/outlier investigation.
skills/analyze-heterogeneity/SKILL.md on GitHub (opens in a new tab) -
analyze-intervention
Apply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.
skills/analyze-intervention/SKILL.md on GitHub (opens in a new tab) -
analyze-leaderboard-dynamics
Analyze leaderboard score distributions, compression/saturation, anomalies, selective reporting, and regime shifts.
skills/analyze-leaderboard-dynamics/SKILL.md on GitHub (opens in a new tab) -
analyze-patent-citation-network
Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies.
skills/analyze-patent-citation-network/SKILL.md on GitHub (opens in a new tab) -
analyze-scaling-regime
Analyze how conclusions/performance change across scale and identify regime shifts, saturation, power-law/log-law behavior, or frontier transitions.
skills/analyze-scaling-regime/SKILL.md on GitHub (opens in a new tab) -
analyze-temporal-trajectory
Analyze an ordered temporal trajectory, including persistence/narrowing/widening tests, regime changes, inflection points, and optional extrapolation with uncertainty. Entity type, window, and forecast mode are parameters.
skills/analyze-temporal-trajectory/SKILL.md on GitHub (opens in a new tab) -
apply-perturbation
Apply a controlled change to an assumption, factor, component, parameter, or condition and record response.
skills/apply-perturbation/SKILL.md on GitHub (opens in a new tab) -
apply-question-framework
Select and instantiate a research-question schema appropriate to study type.
skills/apply-question-framework/SKILL.md on GitHub (opens in a new tab) -
apply-separation-principle
Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.
skills/apply-separation-principle/SKILL.md on GitHub (opens in a new tab) -
apply-stage-gate
Apply explicit GO / HOLD / RECYCLE / KILL (or supplied) stage-gate criteria with evidence thresholds and next-step conditions.
skills/apply-stage-gate/SKILL.md on GitHub (opens in a new tab) -
apply-veto-filter
Eliminate alternatives that violate any hard threshold and report the exact violation.
skills/apply-veto-filter/SKILL.md on GitHub (opens in a new tab) -
appreciative-reframe
Reframe a problem around functioning exceptions, existing strengths, positive deviance, and conditions under which desired behavior already occurs.
skills/appreciative-reframe/SKILL.md on GitHub (opens in a new tab) -
assess-construct-validity
Assess whether a benchmark measures its claimed capability using content, convergent, discriminant, and confound analysis.
skills/assess-construct-validity/SKILL.md on GitHub (opens in a new tab) -
assess-evidence-saturation
Estimate marginal information gain of new evidence batches relative to the current corpus and classify continuing/near-saturation/saturated.
skills/assess-evidence-saturation/SKILL.md on GitHub (opens in a new tab) -
assess-goal-feasibility
Cross-check goal branches against resources, obstacles, and timeline; label feasible/stretch/infeasible and propose OR alternatives.
skills/assess-goal-feasibility/SKILL.md on GitHub (opens in a new tab) -
assess-patent-claim-scope
Assess protection breadth, limiting elements, support, overlap, design-around vulnerability, and likely scope uncertainty for a patent claim without making legal conclusions beyond the evidence.
skills/assess-patent-claim-scope/SKILL.md on GitHub (opens in a new tab) -
assess-patent-legal-status
Classify observed patent/legal status and flag uncertainty or jurisdiction dependence.
skills/assess-patent-legal-status/SKILL.md on GitHub (opens in a new tab) -
assess-prior-art-and-claims
Assess novelty/prior art and claim scope by decomposing claims, tracing relevant families, and checking status/provenance.
skills/assess-prior-art-and-claims/SKILL.md on GitHub (opens in a new tab) -
assess-problem-wickedness
Assess whether the problem is tame, complex, or wicked by examining stakeholder disagreement, moving boundaries, feedback, value conflict, and absence of a stable stopping rule.
skills/assess-problem-wickedness/SKILL.md on GitHub (opens in a new tab) -
assess-publication-bias
Assess or plan tests for publication/reporting/time-lag/citation/language bias using appropriate diagnostics.
skills/assess-publication-bias/SKILL.md on GitHub (opens in a new tab) -
assess-question-quality
Audit a research question for scope and FINER-style quality; return targeted repairs.
skills/assess-question-quality/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
scientific-agent-skillsby K-Dense-AI Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use va…
-
academic-research-skills-codexby Imbad0202 Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows
-
autoresearchby uditgoenka Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep…
-
Vibe-Skillsby foryourhealth111-pixel Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
-
codex-autoresearchby leo-lilinxiao Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard,…
-
evoby evo-hq turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel s…