TheGoat395/Codex-Skills / skills/deep-research
deep-research
VerifiedResearch with scoped depth and counterevidence.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.3 KB |
| agents/openai.yaml | config | 229 B |
| references/access-and-continuity.md | markdown | 1.6 KB |
| references/challenger-and-handoff.md | markdown | 1.8 KB |
| references/coverage-and-research-passes.md | markdown | 2.6 KB |
| references/evidence-standard.md | markdown | 4.7 KB |
| references/research-delivery.md | markdown | 1.0 KB |
references/challenger-and-handoff.md
View on GitHub# Challenger And Handoff
Loaded only for the mode declared in [SKILL.md](../SKILL.md). Apply the relevant sections; preserve the requested objective and scope.
## Make Consecutive Maximum-Reasoning Passes Additive
When the user selects the available maximum-reasoning route for an exceptionally ambiguous, high-impact, system-wide, or repeatedly unresolved decision, divide consecutive passes deliberately:
- **Pass 1 — Discovery and thesis:** map the field, build the evidence-backed working model, and identify decisive unknowns.
- **Pass 2 — Challenger and completion:** pursue omissions, counterevidence, weak identities, alternate interpretations, and unresolved branches; record what changed, survived, or remained uncertain.
Do not use the second pass to restate the first. De-escalate implementation or repetition once the difficult direction is settled.
When `$deep-research` and `$godmode` are invoked together, use Deep Research to establish the defensible decision and GODMODE to execute and verify every feasible in-scope component.
## Run the Autonomous Completion Check
Before delivery, test whether a rigorous reviewer could expose a material omission by asking about:
- an adjacent entity, alternative, evidence class, relationship, or counterexample implied by the scope;
- a mismatch between claims and observable behavior, delivery, economics, incentives, or implementation;
- direct evidence versus inferred connection;
- current constraints, total cost, operational burden, ownership, scale, or failure behavior;
- duplication, regression, or an unjustified change from the existing baseline;
- an untried practical access route;
- evidence that points away from the user's initial belief or the working thesis.
Continue automatically when the omission is material and in scope. Do not expand into a different objective.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |