abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Construct a dependency graph and identify cycles, critical paths, and parallelizable branches.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-dependencies -a windsurf -y
name: map-dependencies description: "Construct a dependency graph and identify cycles, critical paths, and parallelizable branches."
Construct a dependency graph and identify cycles, critical paths, and parallelizable branches.
required: [items, dependency_evidence, relation_schema] optional: [criticality_rule, execution_context, candidate_order] constraints: [the graph contains at least 2 items when the source protocol applies; dependency direction and strength are explicit]
1. Normalize item identifiers and proposed dependency relations. 2. Classify each edge as strong or weak with evidence. 3. Detect cycles, compute critical paths, and identify independent branches. 4. Return the dependency graph and unresolved relation questions.
If dependency types and blocking relations are explicit, consider `sequence-work` as the next tactic.
produces: [dependency_graph, cycle_register, critical_paths, independent_branches] delta_fields: [findings, evidence_updates, uncertainties, open_questions]
The caller must provide item/subproblem schema, edge vocabulary, strength scale, evidence links, critical-path rule, and the scope in which parallel independence is assessed.
Reject self-justifying edges, cycles hidden by reordering, or "parallel" labels where shared prerequisites remain.
| source | physical line | kind | source criterion | |---|---:|---|---| | hypothesis-formation/dependency-mapping | 12 | numeric | Requires >=2 subproblems; labels strong/weak dependencies, detects cycles, identifies critical path and parallel opportunities. |
A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context,…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…