Menu
Structured research process for investigating topics and producing findings. Use when exploring unfamiliar domains, evaluating options, or gathering evidence to inform decisions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Dispatch Codex to review all unreviewed repository work, then verify its correlated findings ticket or clean result. Use when requesting an independent Codex review, auditing all changes, checking work since the last review, or waiting for Codex findings. Trigger: dispatch codex review, independent review, review all changes, check codex findings, run review agent.
Always-on: when a project has tickets, work the frontier (first unblocked open ticket), mark done, update plan status.
Incremental and full-history repository review with resumable adoption batches. Use when reviewing new work, initializing review tracking, reviewing all work to date, resuming historical review, inspecting unreviewed commits, or reviewing changed tickets. Trigger: review new work, adopt repository, review all history, resume review, review marker, unreviewed commits.
End-of-session handoff that captures current state for the next session. Use when ending a work session, switching context, or before a long break.
Consolidate project artifacts — promote scratch to memory, deduplicate memory, process decisions, organize scripts, update steering/skills accuracy. Use periodically or when the project feels cluttered.
Run and interpret crew-research evals — run.sh flags, scores.jsonl fields, activation TPR/FPR verdicts, resuming interrupted runs. Use when running evals, reading eval results, diagnosing a failing definition, or resuming a dead run. Trigger: run the evals, eval results, scores.jsonl, activation test, TPR, delta threshold, resume the run, skip-completed, known gap.
| name | research-methodology |
| description | Structured research process for investigating topics and producing findings. Use when exploring unfamiliar domains, evaluating options, or gathering evidence to inform decisions. |
| metadata | {"type":"protocol","invocation":"both","practice":null} |
When assessing an unfamiliar source, apply these criteria to place it in the authority hierarchy (see source-authority steering):
| Criterion | Question | Effect |
|---|---|---|
| Accountability | Named author/org with reputation at stake? | Anonymous → cap at L6 |
| Recency | Updated within the domain's decay window? | Stale → downgrade confidence |
| Specificity | Addresses your exact version/context? | Generic → note in relevance |
| Corroboration | Do independent sources agree? | Single-source → cap at "reported" |
| Incentive | Informing or selling? | Vendor marketing → note bias |
| Traction | Stars, forks, dependents, citations? | Prioritize investigation order; evaluate fit independently |
[L{n}:{confidence}]--depth 1 to .scratch/references/) over fetching individual files via HTTPUse the research-output skill's template — it is the canonical format for all research findings (frontmatter with topic/date/status/confidence; Summary, Findings, Sources with [L{n}:{confidence}] tags, Related Topics, Related Tools, Open Questions). Do not invent an inline structure; one format keeps findings reusable across sessions and consumable by other agents.