agentsclimarketplace
Sign in

Aidlc adapter

Skill forgegod/daidala/daidala/skills/aidlc-adapter

Apply the pinned AI-DLC v1.0.1 methodology inside Daidala's lifecycle without importing AI-DLC's runtime or state machine.From its SKILL.md

Install
npx -y skills add forgegod/daidala --skill aidlc-adapter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.5 KB, 458 tokens by cl100k_base, as published. Nobody here has run it

AI-DLC adapter

Use AI-DLC's adaptive development concepts as judgment guidance while Daidala remains authoritative for state, approval, worktrees, verification evidence, and delivery.

Stage mapping

  • define: perform inception-style intent analysis. Produce the Daidala definition artifact with requirements, constraints, ambiguities, and acceptance criteria. Do not create a separate AI-DLC state file.
  • plan: map useful inception and construction decisions into one executable Daidala plan. Identify optional work explicitly. Stop at Daidala's digest-bound human approval gate.
  • implement: execute only the approved construction slice in the assigned Daidala worktree. Keep changes incremental and update tests with behavior.
  • verify: run the real project commands and submit their exact evidence through Daidala. Never infer success from code inspection.
  • review: assess the captured immutable diff against requirements, design, security, and verification evidence.
  • deliver: report the reviewed changed-path manifest and evidence. Do not commit or push without separate authorization.

Adaptation rules

  1. Preserve AI-DLC's intent-first requirements, adaptive depth, explicit design decisions, unit-oriented construction, and build/test evidence.
  2. Represent AI-DLC's Inception across define and plan; represent Construction across implement, verify, and review; map release-readiness reporting to deliver.
  3. Operations in stable v1.0.1 is a placeholder. Do not invent deployment automation or a second runtime.
  4. Use Daidala artifacts and lifecycle tools rather than creating aidlc-state.md, audit.md, an independent approval ledger, or a nested orchestration loop.
  5. Treat upstream rule-detail files as source methodology, not executable Hermes skills. This adapter is the packaged Hermes skill.
  6. Stop on missing inputs, invalid artifacts, failed verification, or changed plans. Never fabricate fallback output.

Provenance

This adapter is derived from the AI-DLC v1.0.1 rules release at commit e49341dbeb8af82758dd85e96ed7fe9bcf38a447. The upstream project is licensed under MIT No Attribution; see references/LICENSE-AIDLC.txt.

What ships with it: 1 file

946 B alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.