aidd-dev:00:sdlc
Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, and review by composing other skills and agents. Holds no business logic of its own — every step is delegated.
ai-driven-dev · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add ai-driven-dev/framework --skill aidd-dev:00:sdlc技能说明
name: aidd-dev:00:sdlc description: Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, and review by composing other skills and agents. Holds no business logic of its own — every step is delegated.
Skill: sdlc
Pure orchestrator. Takes a free-form request and drives it through spec → plan → implementation → done by composing other skills and agents. This skill is a workflow descriptor: every step delegates to a skill or an agent. No business logic lives here.
Iron rule
You are the conductor, not a player.
You never write code. You never run tests. You never commit. You never load a skill into your own context.
Every action — including invoking another skill — is delegated to a sub-agent that runs in a fresh context. You only ever read structured outputs (YAML) returned by sub-agents. You never read the contents of files produced (spec.md, plan.md, source code) — those belong to the agents that wrote them.
If you find yourself about to use the Skill, Write, Edit, Bash tool yourself for anything other than reading a sub-agent output or routing it to the next phase, you have violated the protocol. Stop and re-delegate.
Skill invocation protocol
You never call Skill(...) directly. Every skill invocation is wrapped in an Agent spawn:
-
Spawn the Agent tool with
subagent_type: general-purpose. -
Prompt template:
Invoke skill `<skill-id>` with these inputs: <yaml inputs> Run the skill in your fresh context. When done, return ONLY the structured output described by the skill's frontmatter, in YAML, with no surrounding prose. Do not include the file contents you produced. -
Parse the agent's YAML response. Use the values, not the produced content.
This applies to: aidd-pm:05:spec, aidd-vcs:01:commit, aidd-vcs:02:pull-request. Skills used by planner, implementer, or reviewer are loaded inside those agents' own contexts — that already satisfies the rule.
When to use
- A human invokes
/sdlc <request>to start a new run from a free-form description - A Gardener (async) decides a new run is needed and invokes this skill
- A previous run was paused and needs to be resumed with refined input
When NOT to use
- A spec already exists and is validated → invoke the
planneragent directly - A milestone implementation is needed in isolation → invoke the
implementeragent directly - A standalone review is needed → invoke the
revieweragent directly - A human just wants a draft spec without execution → invoke
aidd-pm:05:specdirectly
Inputs
At least one of request or prd_path is required. If both are provided, prd_path wins and the request becomes additional context.
request: <free-form human description of what to build, optional>
prd_path: <path to an existing PRD file, optional>
working_dir: <optional — defaults to current working directory>
options:
quality_threshold: <0-100, default 90>
retry_cap_per_step: <n, default 3>
open_pr: <true | false, default false>
Commits are always produced — at every phase boundary and at every ticked checkbox during implementation. There is no auto_commit: false mode. The audit trail is mandatory.
Outputs
status: done | blocked | aborted
spec_path: <path to validated spec>
plan_summary: <count of milestones, count of decisions made/blocked>
commits:
spec_validated: <sha>
plan_validated: <sha>
per_milestone: [<sha>, ...]
final: <sha if status=done>
pr_url: <if open_pr and status=done>
duration: <hh:mm>
notes: <relevant observations>
Orchestration
Four phases. Each phase delegates. Defaults below are overridable per invocation via options.
Phase 1 — Spec generation and validation
- Spawn a sub-agent (per Skill invocation protocol) to invoke
aidd-pm:05:specwith inputs{request, prd_path, working_dir}. The agent loads the skill in its fresh context, writes the draft spec atworking_dir/spec.md, and returns{spec_path, status, notes}. You never load the skill yourself; you only read the YAML output. - Spawn
revieweragent (Agent tool,subagent_type: reviewer) with:- artifact: the draft spec at the returned
spec_path - validator:
{{TOOLS}}/plugins/aidd-pm/skills/05-spec/assets/spec-validator.yml(filesystem path, resolved by Claude Code)
- artifact: the draft spec at the returned
- Read the reviewer's output:
completion_score = 100andquality_score >= quality_threshold→ proceed to step 4quality_score < quality_threshold→ re-spawn the spec sub-agent withexisting_specandfindings, retry- Beyond
retry_cap_per_stepretries → escalate to human, return withstatus: blocked
- Commit the validated spec. Spawn a sub-agent (per Skill invocation protocol) to invoke
aidd-vcs:01:commitwith{mode: auto, message: "spec: <feature-name> validated", files: [<spec_path>], push: false}. Record the returnedcommit_shaincommits.spec_validated.
Phase 2 — Planning
- Spawn
planneragent with the validated spec. - The planner uses
aidd-dev:01:planinternally. The skill writes toaidd_docs/tasks/<yyyy_mm>/...md(simple plan) or to*-master.mdplus one*-part-N.mdper child plan (master plan). The planner returnsplan_pathandchild_pathsin its output — use those, never assume a hardcoded path. - Read the planner's output:
plan_pathempty → planner failed to produce a plan, retry once then escalatedecisions_blockednon-empty → ask the human, get answers, re-spawn the planner with the answers as inputplan_status: blocked→ escalate, return withstatus: blocked- Beyond
retry_cap_per_stepretries → escalate to human
- Commit the validated plan. Spawn a sub-agent (per Skill invocation protocol) to invoke
aidd-vcs:01:commitwith `{mode: auto, message: "plan: val