Orca Linear Ticket Workflow
stablyai/orca
Linear ticket work through Orca's CLI. Use when working from a linked Linear issue, finishing work with a PR/MR link and a completion comment, moving a ticket…
A skill your agent uses to search project-backed ADE chats across registered projects and search the active project's terminals, PRs, commits, branches, lanes, files, Linear issues, and proof…
$ npx skills add arul28/ADE --skill ade-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install arul28/ADE ade-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .claude/skills/ade-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .claude/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add arul28/ADE --skill ade-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install arul28/ADE ade-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .agents/skills/ade-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .agents/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add arul28/ADE --skill ade-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install arul28/ADE ade-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .cursor/skills/ade-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .cursor/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/arul28/ADE.git --path apps/desktop/resources/agent-skills/ade-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add arul28/ADE --skill ade-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install arul28/ADE ade-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .gemini/skills/ade-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .gemini/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install arul28/ADE ade-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add arul28/ADE --skill ade-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .github/skills/ade-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .github/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add arul28/ADE --skill ade-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install arul28/ADE ade-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-search .opencode/skills/ade-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ade-search" agent skill from https://github.com/arul28/ADE/tree/main/apps/desktop/resources/agent-skills/ade-search into .opencode/skills/ade-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ade-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ade-searchA skill your agent uses to search project-backed ADE chats across registered projects and search the active project's terminals, PRs, commits, branches, lanes, files, Linear issues, and proof…
Ade Search is an agent skill from arul28/ADE. Use this skill to search project-backed ADE chats across registered projects and search the active project's terminals, PRs, commits, branches, lanes, files, Linear issues, and proof artifacts via ade search instead of grepping .ade/ internals.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Linear. The licence is AGPL-3.0.
Read from SKILL.md and the folder at commit c14d06f. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitkindFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ade Search loads about 1.6k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 679 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from arul28/ADE at commit c14d06f, republished under its AGPL-3.0 licence (© arul28). 679 words, ~1,602 tokens.
.claude/skills/ade-search/SKILL.md (or your agent's skills folder).ade search queries deterministic full-text indexes maintained by ADE. Chat
queries include project-backed chats from every project registered with the
machine brain. Other kinds — terminal/CLI scrollback, PRs, commits, branches,
lanes, workspace files, Linear issues, and proof artifacts — come from the
active project. Personal/no-project chats are intentionally excluded and stay
on the separate personal-chat surface.
This policy is identical for session-bound agents and unbound human shells;
search does not silently narrow chat hits to the caller's own session. It is
not a grep over .ade/: the runtime keeps each project index fresh and the
machine router combines bounded chat result pages. Each project contributes at
most its first 200 matches to one aggregate query; resultsTruncated: true (and
the text-mode bounded: line) means you should narrow the query rather than
assuming the tail was exhaustive. Every hit carries a deep
link back to the exact ADE surface.
Use it instead of poking at .ade/ade.db, replaying git log, or asking the
user "which chat was that in". It answers "where did this happen in ADE" across
kinds in one call.
ade search "<query>" # ranked results as JSON (default)
ade search "<query>" --text # aligned rows + count summary
ade search "<query>" --kind chat,terminal # restrict to kinds
ade search "<query>" --lane fix-login # restrict to a lane (id or name)
ade search "<query>" --limit 20 # cap result count
ade search "<query>" --cursor <nextCursor> # next page from a prior query
ade search --status --text # index doc counts + backfill state
ade search --rebuild --text # rebuild the index (CTO-only)The query string is passed through to the index. It supports:
| Form | Meaning | Example |
|---|---|---|
| bare terms | AND-ed together | ade search "retry backoff" |
"quoted phrase" | exact adjacent phrase | ade search '"connection refused"' |
kind:<kind> | restrict to a kind inline | ade search "kind:pr merge queue" |
lane:<name> | restrict to a lane inline | ade search "lane:fix-login timeout" |
session:<id> | restrict to one session | ade search "session:abc123 panic" |
since:<date> | recency floor (ISO date) | ade search "since:2026-06-01 crash" |
Inline kind: / lane: filters and the --kind / --lane flags can be mixed;
the flags are the scriptable form and validate their input.
Kind values: lane, chat, terminal, pr, commit, branch, file,
linear, artifact. --kind takes a comma-separated list and rejects unknown
kinds with a usage error (exit 2).
| kind | deep-links to |
|---|---|
chat | the Work chat session, scrolled to the matching message |
terminal | the terminal/CLI session, at the matching scrollback offset |
pr | the PR detail tab |
commit | the commit in the lane's history |
branch | the branch (find-or-offer-to-create lane) |
lane | the lane |
file | the workspace file |
linear | the Linear pane for the issue |
artifact | the proof/artifact in the proof drawer |
Each result also carries laneId/laneName, sessionId, and updatedAt; the
deepLink is an ade://… URL you can hand to ade open. Machine-routed
results additionally carry projectId, projectName, and projectRoot so
same-named lanes and chats remain distinguishable.
--json (default): the full SearchQueryResult — results[] (each with
kind, id, title, snippet, matchRanges, laneId, laneName,
sessionId, deepLink, updatedAt, and machine-routed project fields),
totalByKind, nextCursor, and project coverage metadata. Use this when you
need the deep link or want to page.--text: aligned KIND PROJECT TITLE SNIPPET ID rows when project
metadata is present, then a
N results (chat 3, terminal 2, …) summary from totalByKind, and a
more: --cursor <value> line when another page exists. Use this for a quick
human-readable scan.Exit codes are script-friendly: 0 when the query matched at least one result,
1 when it matched nothing (so ade search "x" >/dev/null && … works), and 2
on a usage error such as an unknown --kind.
ade search "X" --kind chat --text, then
ade open <deepLink> or read a bounded window with
ade chat read <session> --limit 20 --max-chars 8000 --text. Use
--page --cursor <nextCursor> only when you need older content.ade search "<command or error>" --kind terminal --text; the result offset
drops you at the failure in scrollback.ade search "Y" --kind pr --text.ade search "Z" --lane <lane> --text across files, commits, and chats.ade search --status --text to see
docCount, per-kind counts, and backfillComplete; rebuild with
ade search --rebuild only if backfill is genuinely broken.Reach for ade search before grepping .ade/ internals or asking the user to
locate something. Remember the boundary: chats span registered projects;
non-chat kinds use the active project; personal chats are excluded.
© arul28, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in apps/desktop/resources/agent-skills/ade-search of arul28/ADE.
Open the folder on GitHubat commit c14d06f
Ade Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ade Search this skillarul28/ADE | 114 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | |
| Orca Linear Ticket Workflowstablyai/orca | 88k | 1 repos | ~522 | Automated safety check: Pass | MIT | |
| Review Triage Phaseprisma/orm | 48k | — | ~995 | Automated safety check: Pass | Apache-2.0 | |
| Commitdinerojs/dinero.js | 6.8k | — | ~667 | Automated safety check: Pass | MIT | |
| Draft Pull Request Creatorwordpress-mobile/WordPress-Android | 3.2k | — | ~881 | Automated safety check: Notes | GPL-2.0 | |
| Linear Tickets via Orcastablyai/orca | 88k | — | ~558 | Automated safety check: Pass | MIT |
stablyai/orca
Linear ticket work through Orca's CLI. Use when working from a linked Linear issue, finishing work with a PR/MR link and a completion comment, moving a ticket…
prisma/orm
Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.
dinerojs/dinero.js
Create a git commit with optional automatic Linear issue linking.
wordpress-mobile/WordPress-Android
Commits and pushes current changes, writes a pull request title and body from the branch history and template, and opens a draft PR on GitHub after you approve it.
stablyai/orca
Linear ticket work through Orca's CLI. Use when working from a linked Linear issue, finishing work with a PR/MR link and a completion comment, moving a ticket…
lobehub/lobe-icons
Add or modify icon keyword mappings for providers, models, or agents in lobe-icons.
arul28/ADE
A skill your agent uses when you need to run or drive a local Electron/desktop app and capture what it does — launch it or attach to a running renderer, read its logs or answer its terminal prompts…
arul28/ADE
Iteratively optimize an ADE tab's CPU/memory/IPC/render performance.
arul28/ADE
A skill your agent uses for any browser behavior at all — opening a URL, checking a localhost page, clicking or filling a form, logging in, screenshotting, inspecting the DOM, or verifying a page…
arul28/ADE
A skill your agent uses when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump…
arul28/ADE
A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.
arul28/ADE
A skill your agent uses when creating, inspecting, syncing, committing, pushing, archiving, or rebasing ADE lanes and lane worktrees through ade lanes and ade git.
Works with
A skill your agent uses to search project-backed ADE chats across registered projects and search the active project's terminals, PRs, commits, branches, lanes, files, Linear issues, and proof…. Ade Search is an agent skill from arul28/ADE.ade/ internals.
Ade Search fits situations like: search project-backed ADE chats across registered projects and search the active projects terminals; proof artifacts via ade search instead of grepping .ade/ internals.
Run `npx skills add arul28/ADE --skill ade-search -a claude-code`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-search in arul28/ADE) into .claude/skills/ade-search in your project. Claude Code loads it when a task matches its description.
Run `npx skills add arul28/ADE --skill ade-search -a codex`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-search in arul28/ADE) into .agents/skills/ade-search in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add arul28/ADE --skill ade-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ade-search, .gemini/skills/ade-search, .github/skills/ade-search and .opencode/skills/ade-search in your project.
Going by SKILL.md and its folder, Ade Search needs the command-line tools its instructions call (git and kind).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ade Search is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ade Search: Orca Linear Ticket Workflow (stablyai/orca, 88k stars), Review Triage Phase (prisma/orm, 48k stars), Commit (dinerojs/dinero.js, 6.8k stars) and Draft Pull Request Creator (wordpress-mobile/WordPress-Android, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
arul28 (a GitHub user) maintains it in arul28/ADE, which has 114 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 9, 2026.
Source: arul28/ADE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.