Executes one orchestration cycle. Reads ready issues, resolves blockers, acquires a per-issue lock, hands the implementation to the active SDLC orchestration capability discovered in the runtime, and records audit + observability artifacts.
Available actions
#
Action
Role
Input
01
poll-ready
List ready issues by label, project column, or mention
repo + config
02
resolve-deps
Filter out blocked issues via dependency chain
candidate issues
03
acquire-lock
Add ai:running label to dedupe parallel runs
target issue
04
check-sdlc
Discover an active SDLC orchestration capability
runtime context
05
delegate-sdlc
Invoke the discovered SDLC capability with issue context
locked issue
06
write-audit
Persist run record to aidd_docs/async-runs/ and Check Run
run result
07
emit-webhook
POST run record to SIEM webhook if configured
run record
Default flow
Sequential: 01 -> 02 -> 03 -> 04 -> 05 -> 06 -> 07. Action 03 runs once per selected issue. If no issue passes 02, the skill stops cleanly without locking.
Transversal rules
Read .claude/aidd-async-dev.json first; abort with a clear message if absent (refer the user to the setup skill of this plugin).
Acquire the lock before delegating. Release the lock by removing ai:running only after 06-write-audit succeeds, regardless of pipeline outcome.
On any failure between 03 and 06, attach the error to the audit record and the issue as a comment; keep ai:running so a human can investigate.
Never auto-merge. The pipeline ends at PR creation.
Apply tool_allowlist from config via the plugin PreToolUse hook when hooks are wired.
External data
aidd_docs/async-runs/ -- run history directory shared with this plugin's review skill
.claude/aidd-async-dev.json -- runtime config produced by this plugin's setup skill
1---2name: 02-run3description: Run4---56# Run78Executes one orchestration cycle. Reads ready issues, resolves blockers, acquires a per-issue lock, hands the implementation to the active SDLC orchestration capability discovered in the runtime, and records audit + observability artifacts.910## Available actions1112| # | Action | Role | Input |13| --- | ----------------- | ------------------------------------------------------------ | ---------------- |14| 01 | `poll-ready` | List ready issues by label, project column, or mention | repo + config |15| 02 | `resolve-deps` | Filter out blocked issues via dependency chain | candidate issues |16| 03 | `acquire-lock` | Add `ai:running` label to dedupe parallel runs | target issue |17| 04 | `check-sdlc` | Discover an active SDLC orchestration capability | runtime context |18| 05 | `delegate-sdlc` | Invoke the discovered SDLC capability with issue context | locked issue |19| 06 | `write-audit` | Persist run record to `aidd_docs/async-runs/` and Check Run | run result |20| 07 | `emit-webhook` | POST run record to SIEM webhook if configured | run record |2122## Default flow2324Sequential: `01 -> 02 -> 03 -> 04 -> 05 -> 06 -> 07`. Action 03 runs once per selected issue. If no issue passes 02, the skill stops cleanly without locking.2526## Transversal rules2728- Read `.claude/aidd-async-dev.json` first; abort with a clear message if absent (refer the user to the setup skill of this plugin).29- Acquire the lock before delegating. Release the lock by removing `ai:running` only after `06-write-audit` succeeds, regardless of pipeline outcome.30- On any failure between 03 and 06, attach the error to the audit record and the issue as a comment; keep `ai:running` so a human can investigate.31- Never auto-merge. The pipeline ends at PR creation.32- Apply `tool_allowlist` from config via the plugin `PreToolUse` hook when hooks are wired.3334## External data3536- `aidd_docs/async-runs/` -- run history directory shared with this plugin's review skill37- `.claude/aidd-async-dev.json` -- runtime config produced by this plugin's setup skill
Run npx skillmds@latest add ai-driven-dev/02-run in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Run It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
ai-driven-dev (@ai-driven-dev) published this skill. Their other Agent Skills are listed on their SkillMD profile.
ai-driven-dev