define-evidence-protocol
SkillProductivityLets your agent write a clear plan for what evidence counts in a research task before searching.
Use define-evidence-protocol in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add define-evidence-protocol and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the define-evidence-protocol skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Define research questions, evidence scope, queries/concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence for an acquisition task.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/define-evidence-protocol/SKILL.md and read by ahel’s review.
Purpose
Define research questions, eligible evidence scope, query concepts, inclusion/exclusion rules, provenance requirements, and stopping evidence.
Input contract
required: [research_question, evidence_scope, inclusion_rules]
optional: [exclusion_rules, query_concepts, quality_rubric, stopping_policy]
constraints: [eligible universe, provenance fields, and stopping evidence must be explicit]
Procedure
- State the question, target population or domain, comparison, outcomes, and time boundaries.
- Define eligible evidence, exclusion rules, source-independence requirements, and extraction fields.
- Specify batch boundaries, novelty dimensions, and relative stopping evidence.
- Record unresolved scope choices before acquisition begins.
If the protocol fixes inclusion, exclusion, and stopping rules, consider select-seed-evidence as the next tactic.
Output contract
produces: [evidence_protocol, eligible_universe, query_concepts, screening_rules, provenance_requirements, stopping_evidence]
delta_fields: [decisions, assumption_updates, uncertainties, open_questions]
Quality gates
- The eligible universe and exclusion rules are operational.
- Stopping evidence names numerator, denominator, batch increment, source references, direction, threshold, and rationale when relative quantities apply.
Failure and counterexamples
Do not use provider names as a protocol, and do not declare coverage from search volume without a defined eligible universe.
Provenance map
resolved: define-search-protocolresolved: inclusion-criteria-design
Signals
- GitHub stars
- 503
- Forks
- 42
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
define-evidence-protocol- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine
github.com/yogsoth-ai/de-anthropocentric-research-engine
Related picks
Skill · coreyhaines31
The pick for Companiesquantitative-screening
Skill · agentii-ai
The pick for Companiescompetitive-matrix
Skill · alirezarezvani
The pick for Competitivecompetitive-analysis
Skill · nahid-sparktales
The pick for Competitivemarket-sizing-analysis
Skill · wshobson
The pick for Marketmarket-entry
Skill · cbrock84
The pick for Market