hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/research
research
VerifiedAnswer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.4 KB |
| references/adoption-and-lineage.md | markdown | 2.4 KB |
| references/codebase-recon/codebase-recon.feature | other | 1.8 KB |
| references/codebase-recon/pack-contract.md | markdown | 3.3 KB |
| references/goals.md | markdown | 1.2 KB |
| references/pattern-mining/pack-contract.md | markdown | 2.2 KB |
| references/pattern-mining/pattern-mining.feature | other | 824 B |
| references/research.feature | other | 530 B |
| references/status.md | markdown | 2.0 KB |
| schemas/findings.json | config | 3.3 KB |
| schemas/reality-check-report.v1.schema.json | config | 1.5 KB |
| scripts/claim-audit/validate-output.shexecutable | script | 1.6 KB |
| scripts/codebase-recon/validate-output.shexecutable | script | 19.0 KB |
| scripts/pattern-mining/validate-output.shexecutable | script | 2.1 KB |
| scripts/validate.shexecutable | script | 2.9 KB |
references/pattern-mining/pack-contract.md
View on GitHub# Pattern-mining pack contract
Applies only when a durable `pattern-mining.v1` record is selected.
`<skill-dir>` is defined in [SKILL.md](../../SKILL.md).
A promotion needs at least three independent lineages, one anchored exemplar
each (copies and ports of one source count once, under Research's
[evidence rules](../../SKILL.md#evidence-rules)), a candidate formed before
inspecting a separate holdout, a passing holdout and successful
back-application of every refinement to the original exemplars. Every invariant
needs supporting alignment. Otherwise preserve the result as
`outcome: hypothesis` with `route: no-action`; do not package weak evidence as a rule.
Save `pattern-mining.json` by Research's
[save rule](../../SKILL.md#output-and-boundaries) and run
`bash "<skill-dir>/scripts/pattern-mining/validate-output.sh" <pattern.json>`.
A hypothesis record has this shape (`<...>` is a value to fill):
```json
{
"schema_version": "pattern-mining.v1",
"outcome": "hypothesis",
"exemplars": ["<first file:line>", "<second file:line>"],
"invariants": ["<what every exemplar shares>"],
"variations": ["<legitimate difference>"],
"incidental": ["<syntax or naming>"],
"holdout": {"source": "<file:line not among exemplars, or empty>", "result": "not-run"},
"back_application": "not-run",
"route": "no-action",
"shape": "no-action"
}
```
`holdout.result` is `pass`, `fail`, `inconclusive` or `not-run`;
`back_application` is `pass`, `fail` or `not-run`. A promotion sets
`outcome: "promote"`, `route: "operationalize"` and both results to `pass`.
The recommended `shape` (`no-action`, `reference-line`, `template`, `helper`
or `gate`) and the demonstrated `cost` of violation are optional, and a
`gate` needs `outcome: promote` and a `cost`. The validator checks that
exemplar strings differ, not that their lineages are independent: list copies
under their source, not as exemplars.
`route` is a compatibility field. `operationalize` marks a valid promotion and
dispatches nothing; what to build is `shape`, and a helper, template or gate
stays with the caller. Packaging a promoted pattern as a skill is
[Skill Builder's distillation mode](../../../skill-builder/SKILL.md#distill-expertise).
See the [pattern scenarios](pattern-mining.feature).
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: 114k | 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: 114k | 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: 114k | 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: 114k | Updated | Claude CodeCodex | Verified | Install |