Planning

Skill LaProgrammerie/ai-engineering-core/skills/planning

Global Kiro steering + skills — portable AI engineering layer. Pairs with template-generic-project (spec → handoff → code).

Install

npx -y skills add LaProgrammerie/ai-engineering-core --skill planning

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

One thing to look at

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.

What its author says it does

Copied from the file, not written here

Turn a goal into a structured plan suitable for requirements/design/tasks workflows: scoped decomposition, dependencies, risks, and explicit non-goals.

SKILL.md

2.0 KB, as published. Nobody here has run it

Planning (global)

Objective

Produce an actionable plan: ordered work, dependencies, risks, and done criteria — without inventing unstated product context.

Anti-invention guardrails

Do not invent product constraints, domain rules, architecture choices, or team process (branching, review gates, release train) when the user has not provided them.
If something is required to plan safely, list it under Unknowns / to confirm instead of assuming.
Distinguish facts (from repo or user) from assumptions (label explicitly).

When to use

Non-trivial or ambiguous task
Need to decompose before specifying or implementing

Expected inputs

User goal / intended outcome
Explicit constraints (time, compatibility, quality)
Out of scope if the user mentioned it
Repo context only if the user opened or described the project

Steps

Restate goal and non-goals in one short paragraph.
List constraints and unknowns (flag what must be validated).
Produce a structured decomposition — prefer hierarchical breakdown (phases → work packages → tasks) over a single flat list when the problem is large.
Mark quick wins vs risky items; note dependencies between items.
Identify risks and realistic mitigations.
Define Definition of Done: verifiable criteria (tests, review, metric, demo).

Spec workflow alignment

Output should be reusable as input to a spec workflow: clear enough to map to requirements → design → tasks without re-deriving intent.
Prefer structured sections (e.g. scope, milestones, task groups) over an unstructured bullet dump.

Output format

Structured plan (sections or table)
Risks + mitigations
Explicit Definition of Done
Open questions only if blocking