implement

Solid

Implement work from a ticket, spec, or inline description; auto-detects the next item from the task folders when no argument is given.

AI & Automation 2 stars 1 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
16
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Implement Follows the `aiwork-protocol` skill. Don't enter plan mode — the input artifact is the plan. ## 1. Resolve input to one work item `$ARGUMENTS` is one of: - **Ticket path**: use directly. Verify the ticket is `status: ready` and every `blocked_by` ticket is `status: done`; if not, warn and ask. - **Spec/PRD path**: scan its folder for a `tickets/` subfolder and pick the lowest-numbered **frontier** ticket (`status: ready`, all `blocked_by` done). If there are no tickets, the spec/PRD itself is the work item. - **Inline feature description**: if trivial (fits one session, obvious approach), treat it as the work item. If non-trivial, stop and suggest `/to-spec`. - **No args**: find the most recently modified task folder (per `aiwork-protocol` conventions), then apply the same order: frontier ticket, then spec/PRD. If everything is `done` but no `review.md` exists in the task folder, go straight to Wrap-up (§4). Nothing found → tell the user and stop. ## 2. Clarity gate Before touching code, check the work item is concrete enough for one run. **Warn and stop for confirmation** if any hold: - Open questions, TBDs, or unresolved decisions - Scope spans many subsystems — suggest `/to-tickets` instead - Key technical choices (data model, API shape, file targets) unspecified - Success criteria too vague to tell when "done" - Content is contradictory, out of order, or otherwise corrupted Warn: "<item> is underspecified because <reason>. Implement anyway?" Wait. The...

Details

Author
lttr
Repository
lttr/claude-marketplace
Created
8 months ago
Last Updated
4 days ago
Language
JavaScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category