leifericf

70 mods across 1 repository, 5 stars between them.

check-correctness

25

leifericf/agentic-sdk

Skill Claude Code

Review dimension for logic bugs, boundary edges, and arithmetic defects over one module shard. Invoked by reviewer agents.

not rated 5 1mo ago A 28 tokens original MIT archived

check-design

26

leifericf/agentic-sdk

Skill Claude Code

Review dimension for the design language, view-spec data cleanliness, and UI experience targets. Invoked by reviewer agents over a UI shard when the descriptor has :ui? true.

not rated 5 1mo ago A 38 tokens original MIT archived

check-factoring

27

leifericf/agentic-sdk

Skill Claude Code

Review dimension for module boundaries, dependency direction, pure/effect and native leakage, duplication, and oversized units. Invoked by reviewer agents over one module shard.

not rated 5 1mo ago A 36 tokens original MIT archived

check-memory

28

leifericf/agentic-sdk

Skill Claude Code

Review dimension for ownership, lifetimes, leaks, and GC safety over one C or Zig module shard. Invoked by reviewer agents when the descriptor activates :memory.

not rated 5 1mo ago A 36 tokens original MIT archived

check-performance

29

leifericf/agentic-sdk

Skill Claude Code

Review dimension for hot-path allocation, budget breaks, and needlessly unbounded work. Invoked by reviewer agents over one module shard.

not rated 5 1mo ago A 30 tokens original MIT archived

check-portability

30

leifericf/agentic-sdk

Skill Claude Code

Review dimension for platform branches, endianness, filesystem semantics, and integer-width assumptions. Invoked by reviewer agents over native or platform shards.

not rated 5 1mo ago A 33 tokens original MIT archived

check-security

31

leifericf/agentic-sdk

Skill Claude Code

Review dimension for untrusted input reaching unsafety, path and capability bypass, and boundary integrity. Invoked by reviewer agents over one module shard.

not rated 5 1mo ago A 32 tokens original MIT archived

check-style

32

leifericf/agentic-sdk

Skill Claude Code

Review dimension for naming, idiom, comment debt, and AI tells against the codified per-language and prose standards. Invoked by reviewer agents over one module shard.

not rated 5 1mo ago A 37 tokens original MIT archived

create-backlog

33

leifericf/agentic-sdk

Skill Claude Code

Create a prioritized backlog from the technical design.

not rated 5 1mo ago A 12 tokens original MIT archived

describe-problem

35

leifericf/agentic-sdk

Skill Claude Code

Clarify the user problem, constraints, and success criteria.

not rated 5 1mo ago A 15 tokens original MIT archived

design-ui

37

leifericf/agentic-sdk

Skill Claude Code

Design a UI surface before it is implemented, the four-layer procedure (intent, information architecture, interaction, presentation) chosen from tokens, plus the full set of states. Invoked before write-ui when a new or changed UI surface needs a design.

not rated 5 1mo ago A 53 tokens original MIT archived

design-ux

38

leifericf/agentic-sdk

Skill Claude Code

Establish UX guardrails and interaction patterns.

not rated 5 1mo ago A 12 tokens original MIT archived

develop-at-repl

39

leifericf/agentic-sdk

Skill Claude Code

The project's interactive eval loop. Connect once, evaluate small forms, read the value, adjust. The discipline the write-time recipes run inside.

not rated 5 1mo ago A 33 tokens original MIT archived

fix-bug

40

leifericf/agentic-sdk

Skill Claude Code

Fix one bug end to end, from reproducer to one commit.

not rated 5 1mo ago A 17 tokens original MIT archived

leifericf/agentic-sdk

Skill Claude Code

Produce a compact module brief for a dispatched agent, built from disk, returned as the final message, never written to disk.

not rated 5 1mo ago A 30 tokens original MIT archived

implement-change

42

leifericf/agentic-sdk

Skill Claude Code

Build one change end to end on the current tip, review-clean and ready to land.

not rated 5 1mo ago A 20 tokens original MIT archived

leifericf/agentic-sdk

Skill Claude Code

Promote captured guidance from the inbox into its durable home, empty the inbox, one commit.

not rated 5 1mo ago A 24 tokens original MIT archived

investigate

44

leifericf/agentic-sdk

Skill Claude Code

Triage an incident to root cause and a follow-up plan.

not rated 5 1mo ago A 15 tokens original MIT archived

maintain-toolchain

45

leifericf/agentic-sdk

Skill Claude Code

Toolchain maintenance. The pin, the doctor check, the bump ritual, and the investigated-ceiling cache. Invoked by the verifier agent and maintainer dispatches.

not rated 5 1mo ago A 39 tokens original MIT archived

pick-feature

46

leifericf/agentic-sdk

Skill Claude Code

Select and triage the next feature to implement.

not rated 5 1mo ago A 12 tokens original MIT archived

plan-feature

47

leifericf/agentic-sdk

Skill Claude Code

Turn a backlog item into slices, a Gherkin spec, and a plan.

not rated 5 1mo ago A 19 tokens original MIT archived

plan-system

48

leifericf/agentic-sdk

Skill Claude Code

Turn a problem or idea into an approved backlog and feature plan.

not rated 5 1mo ago A 15 tokens original MIT archived

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: