Best for
- Use when the user requests a package or named external-AI result for review, research, cross-review/互审, final-result retention, image work, or an exact saved user instruction such as 进行三方会审; also handles legacy ask-chat…
idaibin/skills/skills/ask-ai/SKILL.md
Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.
Decision brief
Use when the user requests a package or named external-AI result for review, research, cross-review/互审, final-result retention, image work, or an exact saved user instruction such as 进行三方会审; also handles legacy ask-chatgpt wording, but do not use when Codex or an available host tool can complete the result directly.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Declared | Source record | Install path and trigger |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/idaibin/skills --skill "skills/ask-ai"Inspect the Agent Skill "ask-ai" from https://github.com/idaibin/skills/blob/5573877c2df129a3cf6115d6a8ec60802b36b5bc/skills/ask-ai/SKILL.md at commit 5573877c2df129a3cf6115d6a8ec60802b36b5bc. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
1. Read effective guidance and normalize the request into outcome, provider set, subject, known facts, decision or review basis, constraints, exclusions, evidence needs, workflow, requested rounds or turns, and stop condition. Ask only when a missing choice would materially chan…
Keep account/workspace, conversation/container identity, host/browser/CLI route, login, model/reasoning, native capabilities, submission, completion, recovery, quota, and policy provider-specific and live-verified. Every executable route follows provider-adapter.md; conformance…
Local review, mapping, implementation, browser verification, GitHub-native work, Git
Keep Codex as intent interpreter, local evidence owner, verifier, and executor.
Report the Codex-first decision, fixed basis, provider, authorization, capability, verified route, operation states, attributed output, local verification, cleanup, owner, blockers, and gaps. Add image attribution, relay turn/verdict/stop state, or final-sync target/hash/receipt…
Permission review
No configured static risk pattern was detected
This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.
Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 91/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 6 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Coordinate one useful external-AI result without treating providers as interchangeable or replacing work Codex and local owners can complete directly. Ask AI owns authorization, request packaging, basis identity, operation idempotency, response attribution, and local verification. Provider references own only their verified product surfaces, capabilities, route requirements, and completion evidence. Package-only preparation and explicit manual user relay are portable; direct external collaboration requires a verified provider-specific host operation or browser route.
Legacy requests that explicitly say ask-chatgpt route here with provider ChatGPT; do not maintain a second public collaboration owner.
互审; when no valid default exists, keep the result Package-only
and request an explicit provider order and turn cap before any external action;final-result-sync instruction authorizes one sanitized terminal local-review
result to one exact external retention target. Load
final-result-sync.md; this is a post-review
retention operation, not another review round..codex/reviews/<review-id>-package.md under the
verified ignored parent; create its response ledger only for an authorized round or
explicit empty-ledger request. Record provider, basis, facts, questions, evidence,
exclusions, and output contract without seeding conclusions. Package-only stops.
Manual relay returns the copy-ready prompt and records awaiting-user-relay with
zero external action; reconcile that fingerprint before any duplicate relay.
For a local coding-agent CLI, bind the exact verified repository or Worktree root;
do not replace it with the outbound package or treat task paths as a file allowlist.
Load cli-artifact-handoff.md for directory
permissions, exclusions, isolation, and the frozen task/invocation barrier. Hand the
sealed invocation to the configured runtime-verified executor, which starts once,
monitors the original operation, and reports metadata without reading the result.
The primary coordinator then retrieves, quarantines, and verifies the result. Stop
before launch on required executor mismatch. Package-only never launches the CLI.provider-cli.md; review retains no source
writes, while named implementation also requires the matching implementation owner.
For Web review, apply browser-profile.md, preflight
the configured primary each task, and use only its authorized fallback. Preserve a
required verified persistent container even when the outbound package excludes the
current conversation; names/titles and empty tab inventories never prove or change
container, transport, or browser identity.user-local-browser, carry the resolved workspace policy,
including its source, configured control-session/group names, naming/creation
permissions, and any controller requirement for task-specific session naming.
Provider, model, task, agent, emoji, page, and conversation labels are never browser
session or group names. A controller that requires task-specific naming conflicts
with unified reuse and must return capability-unavailable before setup; use only an
already authorized fallback, never a newly named group. Never resend an already submitted or ambiguous operation; retry
only a proven failed-before-submit attempt with the original operation ID. For a
running CLI operation, use the adaptive same-process monitoring contract in
provider-cli.md and the artifact handoff when selected; a quiet observation
interval or unchanged progress file is not a failure or retry trigger.
Before any browser submit, run the configured browser-capture artifact gate to
precreate and read back package, invocation, events, response-partial, and
response-final files. Gate failure stops at Package-only. After capture, accept
completion only after atomic finalization, SHA-256 verification, and final-path
readback; otherwise record completion-not-verified without resend.prompt-text/v1 fingerprints, and
operation evidence. Shared browser
availability never transfers account, cookie, tab, identity, or completion evidence.final-result-sync instruction is
active, freeze that verdict before attempting its one permitted sanitized sync.
Report synchronization separately and never reopen, change, or delay the verdict
because of the provider response or sync failure. Route source edits, design
decisions, publication, Git mutation, defaults migration, or any other external
turn outside the explicitly authorized round, relay limit, or final-sync operation
only with separate authorization.
When a user-owned ask-ai-feedback/v1 record explicitly enables local feedback,
load feedback-recording.md and append the
terminal metadata events after local reconciliation. Recording failure is
feedback-deferred; it never changes the provider outcome, authorizes a retry, or
delays returning the result.Keep account/workspace, conversation/container identity, host/browser/CLI route, login, model/reasoning, native capabilities, submission, completion, recovery, quota, and policy provider-specific and live-verified. Every executable route follows provider-adapter.md; conformance standardizes the boundary, not provider capability. Keep volatile selectors and installed-runtime facts outside the portable package.
final-result-sync permits only its one sanitized terminal-result retention attempt;
its response is receipt evidence, never review or mutation authority.ops-browser workspace policy; never derive browser session/group names
from provider, model, task, agent, emoji, page, or conversation labels.repo-delivery authority.Not found
or Not verified.Report the Codex-first decision, fixed basis, provider, authorization, capability, verified route, operation states, attributed output, local verification, cleanup, owner, blockers, and gaps. Add image attribution, relay turn/verdict/stop state, or final-sync target/hash/receipt only when applicable. State that Package-only performed no external action and final sync cannot change the frozen verdict.
Frequently asked questions
Use when the user requests a package or named external-AI result for review, research, cross-review/互审, final-result retention, image work, or an exact saved user instruction such as 进行三方会审; also handles legacy ask-chatgpt wording, but do not use when Codex or an available host tool can complete the result directly.
The source record exposes this install command: npx skills add https://github.com/idaibin/skills --skill "skills/ask-ai". Inspect the command and pinned source before running it.
The pinned source record declares support for: codex.
Alternatives
vasilyu1983/AI-Agents-public
Scans public GitHub repos for agent skills, dev practices, and code patterns. Use when enriching skills, setting team policy, or researching a build domain.
PramodDutta/qaskills
Gate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.
upex-galaxy/agentic-qa-boilerplate
Execute regression test suites via CI/CD, analyze results, classify failures, and produce GO/NO-GO release decisions. Use when running regression, smoke, or sanity suites through GitHub Actions, monitoring workflow runs, downloading Allure or Playwright artifacts, classifying failures (REGRESSION vs FLAKY vs KNOWN vs ENVIRONMENT vs NEW TEST), computing pass-rate and trend metrics, deciding release readiness, generating executive quality reports, or creating regression issues. Triggers on: run re
wanshuiyin/Auto-claude-code-research-in-sleep
Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.