bindry-check
Report which compiled Bindry skills are stale, without changing anything. Use when the user asks to check for drift, staleness, or whether their Bindry skills are up to date.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- bindry-check
- description
- Report which compiled Bindry skills are stale, without changing anything. Use when the user asks to check for drift, staleness, or whether their Bindry skills are up to date.
03 SKILL.md 正文
Check whether the skills already compiled by the bindry-sync skill in this project have fallen behind the
Bindry Binder they came from. This is read-only — it never edits, deletes, or re-syncs a skill, only reports.
Invoke explicitly with $bindry-check, or let it trigger automatically when the user asks about drift/staleness.
- This needs
bindry.config.jsonin the project root (written by a previous sync) to know which Binder, API base to check against. If it's missing, tell the user to use thebindry-syncskill at least once first, then stop. - For a private Binder, also need
--token <api-key>(generated from the workspace's team page in Bindry, not Account settings) or theBINDRY_API_TOKENenvironment variable — same requirement asbindry-sync. - Locate this plugin's own installed root first (e.g. list installed Codex plugins and find the path for
bindry@<marketplace>), then run:node <resolved-plugin-root>/scripts/check-drift.mjs [--dir .agents/skills] [--api-base <url>] [--token <api-key>]If you can't locatescripts/check-drift.mjsunder this plugin's installed root, stop and say so plainly rather than guessing a path. - Report exactly what it printed: which skills are up to date, which are stale (and at what version each side
is), which are live (compiled with
--mode live— always current by design, calls the MCP server directly, never goes stale), and which it couldn't check (no pin or live comment, e.g. a hand-authored skill, or a Skill no longer in the Binder). If it failed with an authentication error, say so plainly rather than retry or guess. - If this project is pinned to a Binder version, the report ends with one of two lines, and they mean different things. "pinned to X, which is the newest published version" means there is nothing to do. "pinned to X; the Binder has since published Y" is not staleness — the project is deliberately not following the Binder. Relay it as information, and do not suggest re-syncing unless the user says they want to move off the pin.
- If anything is stale, tell the user to use the
bindry-syncskill to update it — this skill never does that for them. Live skills never need this — don't suggest re-syncing them just because they showed up in the report.
Note on "how far behind": the API doesn't expose full version history for a Skill today, only its current pinned version, so the report names the two version strings on each side (e.g. "compiled at 1.0.0, Binder now pins 2.0.0") rather than a version count. Don't invent a count if asked — say this isn't available yet.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.