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/access-and-continuity.md
View on GitHub# Access And Continuity
Loaded only for the mode declared in [SKILL.md](../SKILL.md). Apply the relevant sections; preserve the requested objective and scope.
## Recover From Access and Search Failures
When material evidence cannot be reached through the preferred route:
1. classify what was actually accessible;
2. identify another authorized, documented, materially different access path;
3. retry using a different query, representation, interface, archive, export, index, or originating source when applicable;
4. record each meaningful attempt and result;
5. reduce the claim or confidence only after practical alternate routes are exhausted.
Never represent metadata, a title, a snippet, an inaccessible body, or another source's description as direct inspection.
## Maintain Resumable Research State
For long, multi-surface, or compaction-prone work, maintain a task-scoped checkpoint using the evidence standard. Keep it concise and recoverable. Record:
- objective, acceptance criteria, scope, and current thesis;
- coverage graph and status by material dimension;
- inspected sources and atomic claims;
- candidates screened versus deeply inspected;
- access failures and alternate attempts;
- contradictions, unresolved questions, and next highest-value actions;
- decisions changed during the challenger pass.
Resume from the checkpoint instead of restarting or relying on compressed conversation memory. Do not create durable files for a small task when an internal ledger is sufficient. Remove temporary artifacts after delivery unless they remain useful to the project or the user asks to retain them.
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 |