Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Search & research

ai-agents-research-methodology

How a hunch becomes an accepted result in this repo. Covers the

rjmurillo · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add rjmurillo/ai-agents --skill ai-agents-research-methodology

About this skill


name: ai-agents-research-methodology version: 1.0.0 license: MIT description: How a hunch becomes an accepted result in this repo. Covers the evidence bar, hypothesis-predicts-numbers discipline, and the idea lifecycle from contradiction log through probe, eval baseline, ADR debate, calibrated gate, and post-ship monitoring. Use when you say how do I prove this idea, run the idea lifecycle, what is the evidence bar. Do NOT use for the open research programs (use ai-agents-research-frontier) or probe recipe depth (use ai-agents-empirical-probe-toolkit). metadata: routing: role: conditional-adjunct invoker: ai-agents-external-claims trigger: ai-agents-external-claims points here to prove a repo-internal idea with a probe, eval, or ADR debate user-facing: false

AI Agents Research Methodology

This repo runs on verification-based governance: labels like "MANDATORY" or "NON-NEGOTIABLE" are insufficient, every requirement needs a verification mechanism. The same standard applies to ideas. An idea is not accepted because it sounds right, because a model agreed with it, or because a retro asserted it. It is accepted when it survives the lifecycle below and leaves an inspectable artifact at every stage.

This skill is the discipline. For the specific probe recipes, use ai-agents-empirical-probe-toolkit. For the three open research programs, use ai-agents-research-frontier. For the archive of past settled results, use ai-agents-failure-archaeology.

Triggers

  • how do I prove this idea
  • run the idea lifecycle
  • what is the evidence bar
  • turn this hunch into a result

The Evidence Bar

A result is accepted here when ONE mechanism explains ALL observations, including the negative ones, and the explanation survives adversarial refutation. Partial explanations that cover only the confirming observations are hypotheses, not results.

The cautionary tale is PR #1989. Mitigation M1 was built on a root-cause claim inherited from a retro RCA that nobody re-verified: the RCA said pagination was missing, but get_unresolved_review_threads.py already paginated correctly (.project-toolkit/retrospective/2026-05-10-pr-1989-recursive-failure.md:20). Five commits were spent building on the false premise. The mechanism-check that would have caught it costs one file read.

Map each claim type to the adversarial machinery that already exists. Do not invent a new review ritual; route into these:

Claim typeAdversarial mechanismHow to invoke
Architectural decision (ADR)adr-review 6-agent debate (architect, critic, independent-thinker, security, analyst, high-level-advisor) until consensus, 10 rounds maxAuto-fires on any ADR-*.md create/edit (AGENTS.md "ADR Review"); or /adr-review path
A single decision's reasoningdecision-critic skillSay Poke holes in this decision or Validate my thinking on ...
Contrarian read of a planindependent-thinker or critic agent (.claude/agents/)Task tool with that subagent_type
Strategic build/buy/deferbuy-vs-build-framework (Quick tier: 1-2 hours)Required gate for new capabilities, see Phase 3
"Why does this constraint exist"chestertons-fenceBefore proposing removal of anything settled
Behavioral claim about a prompt or ruleEval harness (ADR-057)See Predict Numbers Before Running
Prose claims in the write-upprose-self-check, doc-accuracyBefore emitting the artifact

Predict Numbers Before Running

Write the predicted outcome down BEFORE running the measurement. A prediction made after seeing the data is a description, not a test. Concretely:

  1. State the hypothesis and the number it predicts (pass-rate delta, activation score, firing rate) in the session log or spike note.

  2. Validate the setup with zero spend first:

    uv run python scripts/eval/eval-prompt-change.py \
      --prompt templates/agents/analyst.shared.md \
      --scenarios tests/evals/analyst-scenarios.json \
      --base-ref main --dry-run
    

    (Both paths exist in-tree; there is no per-skill scenario fixture for every prompt. Substitute your own prompt path and a real tests/evals/*.json fixture; ls tests/evals/ lists what is available.)

    --dry-run validates inputs and makes no API calls (scripts/eval/eval-prompt-change.py:633, Validate inputs, no API calls). It is the only no-spend path; there is no --mock.

  3. Run the real eval, compare against the written prediction, and record both in the write-up. A miss is a finding, not an embarrassment.

Available instruments (all under scripts/eval/, verified 2026-07-03): eval-prompt-change.py (before/after scenario judgment per ADR-057), eval-agent-vs-baseline.py (agent prompt vs fixed baseline), eval-rule-activation.py (does a .claude/rules/*.md file actually change behavior: baseline vs description-only vs full-body, judged on activation, citation, behavior). Interpretation guidance lives in ai-agents-diagnostics-toolkit.

Process

The lifecycle. Every stage produces an artifact; every transition has a gate. Skipping a stage is how #1989 happened.

Phase 1: Hunch, Then Search, Then Contradiction Log

Before building anything, search: this codebase, Serena memories (memory-search), ADRs, then external docs (the programming-advisor skill's references/search-before-building.md). Most hunches die here because the answer already exists; that is a cheap success.

If your first-principles position contradicts the conventional answer (an ADR, a memory, a canonical pattern), log it before proceeding: Serena memory named decision-<short-slug> with five fields: question,

Read the complete source ↗