Command Claude Code
Run the Spec-First App consistency audit workflow.
not rated 0 1mo ago A 9 tokens
original MIT
Command Claude Code
Run the Spec-First brainstorm workflow.
not rated 0 1mo ago A 7 tokens
original MIT
Command Claude Code
Run the Spec-First code review workflow.
not rated 0 1mo ago A 8 tokens
original MIT
Command Claude Code
Refresh stale Spec-First solution docs.
not rated 0 1mo ago A 7 tokens
original MIT
Command Claude Code
Run the Spec-First knowledge capture workflow.
not rated 0 1mo ago B 8 tokens
original MIT
spec-debug
06Command Claude Code
Run the Spec-First debug workflow.
not rated 0 1mo ago B 7 tokens
original MIT
Command Claude Code
Run the Spec-First document review workflow.
not rated 0 1mo ago A 8 tokens
original MIT
spec-dogfood
08Command Claude Code
Run autonomous diff-scoped browser dogfood QA for a branch or PR.
not rated 0 1mo ago C 14 tokens
original MIT
spec-ideate
09Command Claude Code
Run the Spec-First ideation workflow.
not rated 0 1mo ago B 8 tokens
original MIT
Command Claude Code
Run metric-driven iterative optimization loops.
not rated 0 1mo ago A 6 tokens
original MIT
spec-polish
11Command Claude Code
Start the dev server and iterate on browser-visible polish.
not rated 0 1mo ago A 10 tokens
original MIT
spec-prd
12Command Claude Code
Run the Spec-First PRD requirements workflow.
not rated 0 1mo ago A 9 tokens
original MIT
Command Claude Code
Install, configure, verify, and refresh required harness runtime readiness facts for spec-first workflows.
not rated 0 1mo ago C 17 tokens
original MIT
spec-work
14Command Claude Code
Run the Spec-First execution workflow.
not rated 0 1mo ago A 7 tokens
original MIT
Command Claude Code
Design and author project-owned Agent Skills, or validate packages read-only.
not rated 0 1mo ago A 13 tokens
original MIT
Command Claude Code
Public workflow entrypoint (spec-write-tasks): compile a settled local spec-plan into an optional derived task pack for spec-work, or validate an existing local task pack before execution. Use for explicit plan-splitting/task-doc requests or high-complexity work suitability; do not use for plan authoring…
not rated 0 1mo ago A 110 tokens
original MIT
Skill Claude Code
Internal landing helper for public workflows that already hold explicit commit and landing authorization; commits scoped changes, pushes, and creates or updates a PR with a value-first description.
not rated 0 1mo ago A 40 tokens
original MIT
spec-commit
18Skill Claude Code
Internal commit helper for public workflows that already hold explicit commit authorization; creates scoped, value-communicating commits without owning push or PR landing.
not rated 0 1mo ago A 32 tokens
original MIT
spec-explain
19Skill Claude Code
Create a durable, visual teaching artifact for a concept, diff, idea, or recent-work window, with an optional check-in that makes it stick. Use when the user asks to be taught or wants a deep explainer; not for ordinary Q&A, brief why-followups, diagnosis, status updates, or concise trade-off answers.
not rated 0 1mo ago B 71 tokens
original MIT
Agent Claude Code
You are a work-recap scout. Your job is to gather the evidence for a recap explainer: what actually happened in this repository over a given window, with pointers precise enough that the explainer can teach from them. You extract and quote; you do not interpret, rank, or editorialize.
not rated 0 1mo ago A 0 tokens
copy · 92% MIT
spec-handoff
21Skill Claude Code
Create a durable cross-session handoff or resume from a user-selected continuity source. Use only when the user explicitly wants work to continue in a fresh session, asks to create a handoff, or asks to find/resume a prior handoff; do not trigger for ordinary continuation in the current conversation, workflow-internal…
not rated 0 1mo ago A 81 tokens
original MIT
spec-lfg
22Skill Claude Code
Run the full hands-off engineering pipeline from planning through a green PR. Use only when the current user explicitly requests spec-lfg or selects an option that clearly states it will commit, push, open a PR, and watch CI.
not rated 0 1mo ago A 50 tokens
original MIT
spec-pov
23Skill Claude Code
Give a decisive, project-grounded verdict on an external input — judged against the current project, not in the abstract. Use to decide whether to adopt, switch to, or revisit a technology, library, pattern, platform, or architecture; to compare a candidate against what the project already uses; to judge whether an…
not rated 0 1mo ago B 114 tokens
original MIT
Agent Claude Code
Note: Use the current date from the active host context. Use this when weighting external sources and dating artifacts.
not rated 0 1mo ago A 0 tokens
copy · 86% MIT
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: