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 |
scripts/validate.sh
View on GitHub#!/usr/bin/env bash
set -euo pipefail
skill_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
grep -q '^name: research$' "$skill_dir/SKILL.md"
grep -q '^## Investigation$' "$skill_dir/SKILL.md"
grep -q '^## Repository tracing$' "$skill_dir/SKILL.md"
grep -q '^## Pattern evidence$' "$skill_dir/SKILL.md"
grep -Fq 'A quick answer needs no report file' "$skill_dir/SKILL.md"
grep -Fq 'Research selects no work' "$skill_dir/SKILL.md"
grep -Fq 'issues no semantic verdict' "$skill_dir/SKILL.md"
grep -Fq 'source_ledger' "$skill_dir/SKILL.md"
grep -Fq 'comparison' "$skill_dir/SKILL.md"
grep -Fq 'do not launch recursive synthesis passes' "$skill_dir/SKILL.md"
test -x "$skill_dir/scripts/codebase-recon/validate-output.sh"
test -x "$skill_dir/scripts/pattern-mining/validate-output.sh"
# Claimed-state audit, folded in from the retired Reality Check skill.
grep -q '^## Claimed-state audit$' "$skill_dir/SKILL.md"
grep -Fq 'compare an' "$skill_dir/SKILL.md"
grep -Fq 'expected state with observable evidence' "$skill_dir/SKILL.md"
grep -Fq 'live entry point' "$skill_dir/SKILL.md"
grep -Fq 'production path' "$skill_dir/SKILL.md"
grep -Fq 'carries no overall PASS, FAIL, verdict or' "$skill_dir/SKILL.md"
grep -Fq 'references/advice-or-acceptance.md' "$skill_dir/SKILL.md"
grep -Fq '../validate/SKILL.md' "$skill_dir/SKILL.md"
grep -Fq 'goal snapshots and requested' "$skill_dir/SKILL.md"
grep -Fq '](references/goals.md)' "$skill_dir/SKILL.md"
grep -Fq '](references/status.md)' "$skill_dir/SKILL.md"
test -f "$skill_dir/references/goals.md"
test -f "$skill_dir/references/status.md"
test -f "$skill_dir/schemas/reality-check-report.v1.schema.json"
test -x "$skill_dir/scripts/claim-audit/validate-output.sh"
python3 -m json.tool "$skill_dir/schemas/reality-check-report.v1.schema.json" >/dev/null
grep -Fq 'Scenario: A claimed state gets a per-item ledger without a verdict' \
"$skill_dir/references/research.feature"
grep -Fq '"source_ledger"' "$skill_dir/schemas/findings.json"
grep -Fq '"comparison"' "$skill_dir/schemas/findings.json"
grep -q '^Feature: Research answers one bounded question$' \
"$skill_dir/references/research.feature"
python3 -m json.tool "$skill_dir/schemas/findings.json" >/dev/null
# grep exits 1 for no match; any other status means the scan did not run.
retired_rc=0
grep -rEn 'ao lookup|ao land|auto-redo|Gate 1|\.agents/rpi/next-work|finding-compiler' \
"$skill_dir/SKILL.md" "$skill_dir/references" "$skill_dir/schemas" || retired_rc=$?
if [[ "$retired_rc" -eq 0 ]]; then
echo 'research contract contains retired lifecycle behavior' >&2
exit 1
elif [[ "$retired_rc" -ne 1 ]]; then
echo 'research contract: retired-lifecycle scan failed to run' >&2
exit 2
fi
if grep -Eiq 'ao (pawl|land)|git (commit|push)|br (close|update)|auto-redo|next[_ -]action' \
"$skill_dir/SKILL.md"; then
echo 'research contract contains forbidden lifecycle authority' >&2
exit 1
fi
echo 'research skill contract: PASS'
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 |