New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

00 Async Dev

by ai-driven-dev in ai-driven-dev/framework

Drive the async-dev pipeline from one entry point, whether setup, run, or review.

MITAuto-check passedBackend & APIs

Install 00 Async Dev

skills CLI
$ npx skills add ai-driven-dev/framework --skill 00-async-dev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ai-driven-dev/framework 00-async-dev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ai-driven-dev/framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/aidd-orchestrator/skills/00-async-dev .claude/skills/00-async-dev && rm -rf skills-src

Use ~/.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/

Facts

Skill name
00-async-dev
GitHub stars
510
Token cost
~2.4k tokens
SKILL.md length
928 words
Files
36 (incl. references, assets)
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

Drive the async-dev pipeline from one entry point, whether setup, run, or review.

  • Works in 4 steps: Argument override. If the arguments… → Trigger env. When invoked from CI… → Repo state. → …
  • The user wants to install async dev
  • SKILL.md covers Iron rule, Routing: hybrid contract, Sub-flows and Rules, plus 4 more sections
  • Needs CLAUDE_CODE_OAUTH_TOKEN and AIDD_BOT_TOKEN

What it does

00 Async Dev is an agent skill from ai-driven-dev/framework. Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including reference files and assets (for example `actions/review/01-collect-comments.md`, `actions/review/02-detect-stop.md` and `actions/review/03-fix-iteration.md`).

It sits in Backend & APIs, covering Pull requests and Webhooks. The repository describes itself as: Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC. The licence is MIT.

When your agent uses it

  • The user wants to install async dev
  • Run a ready issue
  • Address PR review comments
  • On a webhook trigger

Example prompts

  • “/00-async-dev”

Requirements

  • A credential in CLAUDE_CODE_OAUTH_TOKEN
  • A credential in AIDD_BOT_TOKEN

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Argument override. If the arguments contain exactly setup, run, or review (case-insensitive, standalone token), route there immediately…
  2. Trigger env. When invoked from CI (GITHUB_EVENT_NAME set)
  3. Repo state.
  4. Natural-language intent. Verbs in the user prompt

What it can do on your machine

Read from SKILL.md and the folder at commit 6e30640. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CLAUDE_CODE_OAUTH_TOKEN
    • AIDD_BOT_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

00 Async Dev loads about 2.4k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 928 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.2k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from ai-driven-dev/framework at commit 6e30640, republished under its MIT licence (© ai-driven-dev). 928 words, ~2,445 tokens.

Download SKILL.mdSave it as .claude/skills/00-async-dev/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.
name
00-async-dev
description
Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.
argument-hint
setup | run | review

Async-dev

Single skill that drives the async development pipeline end to end. Three sub-flows live inside, accessed through one router:

Sub-flowWhen
SetupRepo not yet configured for async dev; user wants to install.
RunAn issue is labeled to-implement (or commented @claude /implement); no open PR closes it.
ReviewA PR is labeled to-review (or commented @claude /review); change requests pending.

Iron rule

You are the router until you commit to a sub-flow. Once committed, run that sub-flow's actions in order; do not jump back to routing mid-flow.

Routing: hybrid contract

Walk in order. First match wins.

  1. Argument override. If the arguments contain exactly setup, run, or review (case-insensitive, standalone token), route there immediately. This is the explicit override the CI workflow uses.
  2. Trigger env. When invoked from CI (GITHUB_EVENT_NAME set):
    • Label payload to-implement → run.
    • Label payload to-review → review.
    • Comment body matches @claude /implement (or /aidd-dev:02-implement) → run.
    • Comment body matches @claude /review → review.
  3. Repo state.
    • Missing .github/workflows/aidd-async.yml AND missing .claude/aidd-orchestrator.json → setup.
    • Open PR closes the referenced issue → review.
    • Fresh issue with no linked PR + intent to implement → run.
  4. Natural-language intent. Verbs in the user prompt:
    • install / configure / set up / bootstrap / rotate config → setup.
    • implement / run / process / handle queue / claude on issue → run.
    • address review / iterate on PR / fix comments / handle review → review.

Tie-break: most-specific signal wins (PR number > label > free-text keyword > config absence).

If none of the above resolves, surface the three sub-flows with one-line triggers and ask the human which to run. Never proceed blindly.

If repo state contradicts intent (e.g. user says "run" but .claude/aidd-orchestrator.json is absent), surface the conflict before delegating; never silently switch.

See references/routing.md for the full decision tree, signal precedence, and edge cases.

Sub-flows

Setup (11 actions)

Sets up async-dev in a repo. Detects context, asks for runtime parameters, generates artefacts, bootstraps labels, installs user-scope plugins (local mode), configures secrets (remote mode), schedules the poll routine (local mode), commits and pushes the generated files, and offers a smoke test on the chosen issue.

#ActionRole
01detect-contextIdentify repo, default branch, existing config, CI permissions
02ask-configCollect runtime parameters (mode, auth, labels, schedule, agents)
03generate-workflowEmit .github/workflows/aidd-async.yml from assets/setup/workflow-template.yml
04generate-local-scriptEmit poll/daemon scripts (local mode only) from assets/setup/local-*-template.sh
05write-configPersist .claude/aidd-orchestrator.json from assets/setup/config-template.json
06bootstrap-labelsCreate to-implement / to-review / claude/* labels via gh
07install-user-scope-pluginsInstall aidd-orchestrator + aidd-dev at user scope (local mode)
08configure-remote-secretsSync CLAUDE_CODE_OAUTH_TOKEN, AIDD_BOT_TOKEN, etc. (remote mode)
09bootstrap-schedulingSchedule the poll routine (local) or rely on workflow webhook (remote)
10commit-and-pushStage generated files, conventional-commit, push
11smoke-testLabel a throwaway issue with to-implement; verify the pipeline reacts

Files: actions/setup/01-detect-context.md ... actions/setup/11-smoke-test.md.

Default flow: 01 → 02 → 03 → 04 → 05 → 06 → 07 → 08 → 09 → 10 → 11. Actions self-skip when their preconditions are not met (e.g. 07 skips in remote mode, 08 skips in local mode).

Run (6 actions)

Executes one orchestration cycle on a fresh issue. Reads ready issues, resolves blockers, acquires the lock label, hands the implementation to the active SDLC orchestration capability, observes the resulting git and VCS state, and emits a run-result.json summary the workflow's post-job consumes.

#ActionRole
01poll-readyFind the next issue with to-implement, no claude/working, no open closing PR
02resolve-depsCheck linked issues / dependencies; abort if blocked
03acquire-lockApply claude/working label; refuse if already held
04check-sdlcVerify an SDLC orchestration capability is loaded
05delegate-sdlcHand the issue to the SDLC capability; observe outcome
06write-auditEmit run-result.json for the workflow's post-job

Files: actions/run/01-poll-ready.md ... actions/run/06-write-audit.md.

Default flow: 01 → 02 → 03 → 04 → 05 → 06. One cycle per ready issue.

Show full SKILL.md (333 more words)Show less
Review (4 actions)

Closes the loop after a PR is opened by the run flow. Detects when to keep auto-fixing and when to hand off to a human. Idempotent on re-runs.

#ActionRole
01collect-commentsRead all PR + linked-issue comments newer than the last bot activity
02detect-stopDecide stop vs continue using references/review/stop-conditions.md
03fix-iterationDelegate fixes to the SDLC capability; reply to each addressed comment
04finalizeResolve threads, post the structured summary, set claude/awaiting-review or blocked

Files: actions/review/01-collect-comments.md ... actions/review/04-finalize.md.

Default flow: 01 → 02 → (03 → 01 loop if continue) → 04. Stop conditions in references/review/stop-conditions.md.

Rules

  • Exactly one sub-flow runs per invocation. The router commits, then runs that sub-flow to completion.
  • Never inline a sub-flow's logic at the router level. The router decides; the actions execute.
  • Each action enforces its own pre-flight checks and exit codes. The router never enforces post-conditions.
  • If a sub-flow aborts, surface the exit state; do not retry by switching sub-flows.
  • For batch invocations (e.g. multiple ready issues), the workflow re-invokes the skill once per item; the router does not loop.

Say when this orchestration is over

Once the sub-flow you committed to has run its last action, and only then, run:

shell
echo "aidd:step-end aidd-orchestrator:00-async-dev"

No host reports when an orchestration finished. A skill call's own result comes back in a tenth of a second, which is the dispatch and not the completion, so a measurement that never hears this ends the run at the next pause — and an orchestration is mostly pauses. Everything it drove afterwards then reads as work that belonged to nothing.

References

  • references/routing.md - full decision tree, signal precedence, conflict resolution.
  • references/setup/auth-modes.md - local vs remote auth contracts.
  • references/setup/claude-action-auth.md - claude-code-action token setup.
  • references/setup/local-mode-scheduling.md - poll routine options.
  • references/review/stop-conditions.md - when the review loop hands off to a human.

Assets

Setup-only templates copied into the target repo by the setup sub-flow:

  • assets/setup/workflow-template.yml - .github/workflows/aidd-async.yml skeleton.
  • assets/setup/local-poll-template.sh - local-mode poll script.
  • assets/setup/local-daemon-template.sh - local-mode daemon script.
  • assets/setup/config-template.json - .claude/aidd-orchestrator.json skeleton.

Test

Each sub-flow's final action carries a ## Test block that exercises the full sub-flow with mocked dependencies.

© ai-driven-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 35 other files (references, assets) in plugins/aidd-orchestrator/skills/00-async-dev of ai-driven-dev/framework.

  • SKILL.md
  • actions/review/01-collect-comments.md
  • actions/review/02-detect-stop.md
  • actions/review/03-fix-iteration.md
  • actions/review/04-finalize.md
  • actions/run/01-poll-ready.md
  • actions/run/02-resolve-deps.md
  • actions/run/03-acquire-lock.md
  • actions/run/04-check-sdlc.md
  • actions/run/05-delegate-sdlc.md
  • actions/run/06-write-audit.md
  • actions/setup/01-detect-context.md
  • actions/setup/02-ask-config.md
  • actions/setup/03-generate-workflow.md
  • actions/setup/04-generate-local-script.md
  • actions/setup/05-write-config.md
  • actions/setup/06-bootstrap-labels.md
  • … and 19 more

Open the folder on GitHubat commit 6e30640

Compare with similar skills

00 Async Dev 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.

00 Async Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
00 Async Dev this skillai-driven-dev/framework510—~2.4kAutomated safety check: PassMIT
PR Review Provideryansongda/pay5.4k—~2.4kAutomated safety check: PassMIT
Stewardbomzheg/Shvatka144—~574Automated safety check: PassMIT
Forgejo CLImagnus919/agent-skills111—~645Automated safety check: PassMIT
Bktavivsinai/bitbucket-cli2311 repos~1kAutomated safety check: PassMIT
GitHub MCPvibeeval/vibecosystem531—~2.3kAutomated safety check: NotesMIT

Similar skills

  • PR Review Provider

    yansongda/pay

    A skill your agent uses when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.

    5.4k GitHub stars~2.4k tokensUpdated 9 days ago
    Backend & APIsAuto-check passed

  • Steward

    bomzheg/Shvatka

    How an agent watches a pull request in this repository — webhooks only, no scheduled check-ins.

    144 GitHub stars~574 tokensUpdated 15 days ago
    Backend & APIsAuto-check passed

  • Forgejo CLI

    magnus919/agent-skills

    A skill your agent uses when managing a Forgejo or Gitea server from the terminal: issues, pull requests, repositories, file contents, labels, milestones, releases, webhooks, user settings, or any…

    111 GitHub stars~645 tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Bkt

    avivsinai/bitbucket-cli

    Operate Bitbucket Cloud or Data Center repositories, pull requests, branches, issues, pipelines, permissions, and webhooks with bkt.

    231 GitHub starsUsed in 1 repo~1k tokens
    DevelopmentAuto-check passed

  • GitHub MCP

    vibeeval/vibecosystem

    GitHub MCP Server ile GitHub API erisimi. An agent skill from vibeeval/vibecosystem.

    531 GitHub stars~2.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check: notes

  • Novu Design Workflow

    novuhq/novu

    Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state.

    40k GitHub stars~2.6k tokensUpdated today
    Backend & APIsAuto-check passed

More from ai-driven-dev/framework

All 52 skills in this repo

  • 01 Plan

    ai-driven-dev/framework

    Turn a request, ticket, or file into a phased implementation plan.

    510 GitHub stars~517 tokensUpdated today
    Auto-check passed

  • 01 Sdlc

    ai-driven-dev/framework

    Autonomously orchestrates a request from framing to a draft pull request, isolating implementation, independent review, and final outcome challenge.

    510 GitHub stars~583 tokensUpdated today
    Auto-check passed

  • 02 Backlog

    ai-driven-dev/framework

    Orchestrates a product backlog end to end. An agent skill from ai-driven-dev/framework.

    510 GitHub stars~613 tokensUpdated today
    Auto-check passed

  • 00 Onboard

    ai-driven-dev/framework

    Guide a project's journey through AIDD, from first setup to shipping a feature.

    510 GitHub stars~242 tokensUpdated today
    Auto-check passed

  • 01 Acceptance QA

    ai-driven-dev/framework

    Validate a reviewed candidate's observable behavior against its acceptance criteria and record short named videos as reviewer evidence.

    510 GitHub stars~434 tokensUpdated today
    Auto-check passed

  • 01 Brainstorm

    ai-driven-dev/framework

    Clarify a vague product or technical intent through natural discovery.

    510 GitHub stars~305 tokensUpdated today
    Auto-check passed

Categories

Questions about 00 Async Dev

What does 00 Async Dev do?

Drive the async-dev pipeline from one entry point, whether setup, run, or review. 00 Async Dev is an agent skill from ai-driven-dev/framework. Drive the async-dev pipeline from one entry point, whether setup, run, or review.

When should I use 00 Async Dev?

00 Async Dev fits situations like: the user wants to install async dev; run a ready issue; address PR review comments; on a webhook trigger.

How do I install 00 Async Dev in Claude Code?

Run `npx skills add ai-driven-dev/framework --skill 00-async-dev -a claude-code`. Or copy the skill folder (plugins/aidd-orchestrator/skills/00-async-dev in ai-driven-dev/framework) into .claude/skills/00-async-dev in your project. Claude Code loads it when a task matches its description.

How do I install 00 Async Dev in Codex?

Run `npx skills add ai-driven-dev/framework --skill 00-async-dev -a codex`. Or copy the skill folder (plugins/aidd-orchestrator/skills/00-async-dev in ai-driven-dev/framework) into .agents/skills/00-async-dev in your project. Codex loads it when a task matches its description.

Can I use 00 Async Dev in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ai-driven-dev/framework --skill 00-async-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/00-async-dev, .gemini/skills/00-async-dev, .github/skills/00-async-dev and .opencode/skills/00-async-dev in your project.

What does 00 Async Dev need to run?

Going by SKILL.md and its folder, 00 Async Dev needs credentials named CLAUDE_CODE_OAUTH_TOKEN and AIDD_BOT_TOKEN. Our summary lists: A credential in CLAUDE_CODE_OAUTH_TOKEN; A credential in AIDD_BOT_TOKEN.

Does 00 Async Dev access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is 00 Async Dev safe to install?

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.

What licence does 00 Async Dev use?

00 Async Dev is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does 00 Async Dev use?

About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.7k tokens, read only when the agent opens those files.

What are the alternatives to 00 Async Dev?

Skills that share tags, products or a category with 00 Async Dev: PR Review Provider (yansongda/pay, 5.4k stars), Steward (bomzheg/Shvatka, 144 stars), Forgejo CLI (magnus919/agent-skills, 111 stars) and Bkt (avivsinai/bitbucket-cli, 231 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 00 Async Dev?

ai-driven-dev (a GitHub organization) maintains it in ai-driven-dev/framework, which has 510 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 7, 2026.

Source: ai-driven-dev/framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.