Skip to main content
EvolveHQ
GitHub クリエイタープロフィール

EvolveHQ

1 件の GitHub リポジトリにある 11 件の収集済み skills をリポジトリ単位で表示します。

収集済み skills
11
リポジトリ
1
更新
2026-07-31
リポジトリマップ

skills がある場所

収集済み skill 数が多いリポジトリを、このクリエイターカタログ内の比率と職業範囲とともに表示します。

リポジトリエクスプローラー

リポジトリと代表的な skills

audit
ソフトウェア開発者

Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity, cross-reference resolution, language mandate, ADR-privacy leaks into user-visible code, cross-worktree collisions (duplicate numbers, duplicate plan ownership, same ADR edited on two branches), and — for a multi-repo product — cross-repo federation checks (bidirectional membership, identity collisions, dangling cross-repo references, roll-up drift, convention drift). Reports a punch list and offers to fix the mechanical issues. Use when the user says "audit the ADRs", "lint the conventions", "check repo consistency", "are the ADRs in sync", or invokes /audit. NOT for pressure-testing a draft or eliciting unstated boundaries (use /challenge — this checks the written record, that interrogates what is proposed or unsaid) and NOT for decomposing new work (use /brainstorm).

2026-07-31
bootstrap
ソフトウェア開発者

Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, _agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", "add AGENTS.md and a plan queue", or invokes /bootstrap. Works on fresh repos and existing ones — preserves existing content and merges rather than overwrites. Opens with an express / guided / full depth choice, so a quick conservative setup needs almost no questions.

2026-07-31
brainstorm
ソフトウェア開発者

Decompose a problem, feature, or goal into CLASSIFIED candidate records for a documentation-led repo — each candidate labelled (a choice → decision record; a behaviour → capability record; a rule → convention; a boundary → constraint; an outcome → goal entry; a job → plan item) with dependency edges and suggested ordering, then routed to the right writer skill on approval. The front door — you never need to know which writer to call, and the goal you typed becomes a recorded goal where the repo keeps them. Proposes drafts for review and writes nothing until approved. Use when the user says "brainstorm", "break this down", "what do we need for X", "record this as a goal", "plan out the work", or invokes /brainstorm. NOT for interrogating a draft or eliciting unstated boundaries (use /challenge — this generates, that interrogates) and NOT for checking the existing record (use /audit).

2026-07-31
new-adr
ソフトウェア開発者

Author a new ADR — record a DECISION (what the system must do, or how it is built) in a documentation-led repo. Picks the next contiguous number, chooses the shape (capability vs technology), fills the template, sets status Proposed, regenerates INDEX, updates domain READMEs, handles supersede/deprecate linkage, commits. Use when the user says "add an ADR", "new ADR", "record a decision", "create an architecture decision record", or invokes /new-adr. NOT for queueing a unit of work against an existing decision (use /new-plan), NOT for recording a reusable rule, practice, or naming/process standard (use /add-convention), and NOT for a living capability spec on the decisions+specs record model (use /new-spec).

2026-07-31
new-spec
ソフトウェア開発者

Author a new CAPABILITY SPEC — a living, slug-identified record of what the system must do — in a documentation-led repo whose record model separates decisions from specs. Picks a unique slug, fills the spec template, sets status Draft, walks Draft→Agreed as a human gate, regenerates INDEX, commits. Use when the user says "add a spec", "new spec", "record a capability", "write the spec for X", or invokes /new-spec. NOT for recording a decision or its rationale (use /new-adr), NOT for queueing a unit of work (use /new-plan), and NOT for a reusable rule or term (use /add-convention). Refuses cleanly in repos whose record model has no specs.

2026-07-31
ship-item
ソフトウェア開発者

Ship a plan/todo item in a documentation-led repo — run the verify gate, integrate per the repo's model (fast-forward or PR), git mv todo→done with a shipped footer, advance the owning ADR(s) to Implemented, regenerate INDEX, append WORKLOG, update the live snapshot. Use when the user says "ship this", "complete the plan item", "mark done", "close out the queue item", or invokes /ship-item.

2026-07-31
add-convention
ソフトウェア開発者

Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if it is really a one-off decision). Pushes back on premature or duplicate conventions. Use when the user says "add a convention", "make this a rule", "document this practice", "we should always X", or invokes /add-convention. NOT for recording a single architectural/product decision (use /new-adr) and NOT for queueing work (use /new-plan).

2026-07-30
agent-wave
ソフトウェア開発者

Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a soft cap), and whether to checkpoint after each wave or run continuously. Spawns isolated worktree subagents, assigns one queue item each, collects results. Use when the user says "spawn a wave of agents", "run the queue in parallel", "fan out the work", "agent wave", or invokes /agent-wave.

2026-07-30
このリポジトリの収集済み skills 11 件中、上位 8 件を表示しています。
1 件中 1 件のリポジトリを表示
すべてのリポジトリを表示しました