H Abduct
H Abduct runs a structured four-step abductive cycle to generate ≥3 competing typed hypotheses for an observed signal, applying plausibility filters and surfacing the prime candidate alongside rivals. It's designed as an internal subroutine for h-diagnose's parallel testing, though manual invocation is supported when disciplined abduction without parallel overhead is needed.
H Abduct generates competing typed hypotheses through a four-step abductive framework, though h-diagnose is the recommended user-facing entry point.
AI-generated summary based on this skill's SKILL.md
Install
m0n0x41d/haft/h-abduct · repository language: Go
generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is H Abduct?
H Abduct is a skill that runs a structured four-step abductive cycle to generate competing typed hypotheses for an observed signal. It applies plausibility filters and surfaces the prime candidate alongside rivals, making it ideal for systematic hypothesis generation when you need disciplined abduction without parallel overhead.
How to use H Abduct?
H Abduct is designed as an internal subroutine for h-diagnose's parallel testing, though manual invocation is supported. When you invoke H Abduct, it executes its four-step abductive cycle on your observed signal, generating at least 3 competing typed hypotheses and filtering them by plausibility before returning results.
What are H Abduct's main features and capabilities?
H Abduct generates ≥3 competing typed hypotheses for observed signals through a structured four-step abductive cycle. Its key capabilities include plausibility filtering, ranking hypotheses by likelihood, and surfacing both the prime candidate and rival explanations—enabling systematic diagnostic reasoning.
Is H Abduct skill available for standalone use?
Yes, H Abduct supports manual invocation for cases where you need structured abduction independently. While it's designed as an internal subroutine within h-diagnose's parallel testing framework, you can invoke H Abduct directly when you prefer disciplined hypothesis generation without parallel processing overhead.
What kind of hypotheses does H Abduct generate?
H Abduct generates typed hypotheses—meaning each hypothesis is categorized by type—for your observed signal. The skill produces at least 3 competing candidates and applies plausibility filters to rank them, ensuring you get both the most likely explanation and credible alternatives for comparison.
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Discover what H Abduct skill does and how to use it”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Trace systematically investigates why something happened by generating competing hypotheses and evaluating evidence for and against each one. It's built for ambiguous causal questions—runtime bugs, performance regressions, and architecture issues—where you need to explain the most likely explanation. The skill structures your investigation through observation, hypothesis generation, evidence gathering, and discriminating probes.
This skill systematically discovers drug repurposing opportunities by analyzing disease-target associations, drug mechanisms, and pathway overlap. It guides you through target-based, compound-based, and disease-driven workflows, then scores candidates by genetic evidence, safety profile, literature support, and drug properties to prioritize the most viable options.
Agent Tools equips your AI agent with a unified CLI to invoke hundreds of cloud-hosted AI models and services. Generate images and videos, call LLMs like Claude and Gemini, perform web searches, automate Twitter, and create 3D models—all without managing GPUs or infrastructure.
This skill helps you troubleshoot organic traffic declines by systematically analyzing technical health, search ranking shifts, and content performance. It guides you through root-cause investigation to pinpoint whether issues stem from indexing problems, algorithm updates, competitor activity, or content quality gaps.
Debug Investigator replaces ad-hoc troubleshooting with structured investigation: capture symptoms, build a reproducible feedback loop, analyze evidence from stacktraces and logs, generate ranked hypotheses, and design bisection strategies. Use it for non-obvious bugs—intermittent failures, performance regressions, or issues requiring systematic root cause analysis—where native debugging falls short.
This skill maps transcription factor regulation by combining binding motif analysis, chromatin immunoprecipitation data, and expression quantitative trait loci to answer which TFs control a gene and which genes a TF targets. It separates direct regulatory evidence (ChIP-seq binding) from indirect signals (co-expression), integrates protein interaction networks, and grounds claims in perturbation experiments rather than computational prediction alone.