菜单
这个仓库中的 skills
SkillsMP 已收集 ValentinNikolaev/agent-skills 中的 60 个 Skill。打开任一 Skill 可查看来源和详情。
ValentinNikolaev/agent-skills已展示 20 / 60 个已收集 Skill。
Run a capacity-aware council of independent advisor passes, anonymized peer review, and a calibrated synthesis for consequential decisions with multiple defensible options. Use when the user explicitly says "council this," "run the council," "war room,"…
原文语言：英语
Bootstrap the first useful durable project-memory baseline from the current repository and its instructions when no usable memory index exists. Use for initial repository memory creation only; do not use to import an external source, record routine facts from…
原文语言：英语
Triage and implement actionable GitHub pull-request review feedback with minimal verified edits. Use only to address PR comments or requested changes; use plan-review for plans and code-review for a fresh read-only diff review.
原文语言：英语
Import or refresh durable memory from an explicitly supplied external URL, provider record, document, pasted text, specification, or bounded source tree while preserving provenance. Use for source-backed ingestion only; do not use for initial repository…
原文语言：英语
Validate an implementation plan before coding and return an evidence-backed APPROVE, REVISE, or BLOCKED verdict without rewriting it. Use for technical plan critique; use code-review for implemented diffs and fix-pr for GitHub review-comment remediation.
原文语言：英语
Review or edit primarily English prose to remove formulaic AI-sounding phrases and structures while preserving meaning, evidence, qualifications, voice, formatting, and protected text. Use only when the user explicitly asks to humanize, de-slop, remove AI…
原文语言：英语
Maintain an existing project-memory store with durable facts learned during completed project work, decisions, fixes, migrations, or milestones. Use only when a usable baseline already exists; do not use for initial bootstrap, primary ingestion or refresh of…
原文语言：英语
Add, import, normalize, recover, or synchronize reusable agent skills into this repository's canonical agent-plugins/skills tree, then generate Claude and Codex distribution copies. Use when the user asks to bring in a skill from another repository, .claude,…
原文语言：英语
Audit repository documentation read-only for broken local links or path references, stale indexes or ADR pointers, duplicate canonical facts, migration gaps, and repository-defined language or script violations. Use for documentation-health reports; do not…
原文语言：英语
Audit an existing agent memory store read-only for schema or index drift, broken or one-way local relationships, review-due content, source freshness, duplicate or conflicting facts, and advisory capacity limits. Use only for memory-health verification; do…
原文语言：英语
Assess the commercial and financial viability of a software product, startup idea, MVP, repository, PRD, requirements folder, or concept. Use when the user asks whether a project is worth building or wants demand, competitors, MVP scope, development and…
原文语言：英语
Remove or shorten redundant source-code comments without changing behavior. Use for explicit comment cleanup or dry audits of user-specified files and directories; do not use for general refactoring, documentation generation, or generated-output cleanup.
原文语言：英语
Run a capacity-aware council of independent advisor passes, anonymized peer review, and a calibrated synthesis for consequential decisions with multiple defensible options. Use when the user explicitly says "council this," "run the council," "war room,"…
原文语言：英语
Bootstrap the first useful durable project-memory baseline from the current repository and its instructions when no usable memory index exists. Use for initial repository memory creation only; do not use to import an external source, record routine facts from…
原文语言：英语
Triage and implement actionable GitHub pull-request review feedback with minimal verified edits. Use only to address PR comments or requested changes; use plan-review for plans and code-review for a fresh read-only diff review.
原文语言：英语
Import or refresh durable memory from an explicitly supplied external URL, provider record, document, pasted text, specification, or bounded source tree while preserving provenance. Use for source-backed ingestion only; do not use for initial repository…
原文语言：英语
Validate an implementation plan before coding and return an evidence-backed APPROVE, REVISE, or BLOCKED verdict without rewriting it. Use for technical plan critique; use code-review for implemented diffs and fix-pr for GitHub review-comment remediation.
原文语言：英语
Review or edit primarily English prose to remove formulaic AI-sounding phrases and structures while preserving meaning, evidence, qualifications, voice, formatting, and protected text. Use only when the user explicitly asks to humanize, de-slop, remove AI…
原文语言：英语
Maintain an existing project-memory store with durable facts learned during completed project work, decisions, fixes, migrations, or milestones. Use only when a usable baseline already exists; do not use for initial bootstrap, primary ingestion or refresh of…
原文语言：英语
Add, import, normalize, recover, or synchronize reusable agent skills into this repository's canonical agent-plugins/skills tree, then generate Claude and Codex distribution copies. Use when the user asks to bring in a skill from another repository, .claude,…
原文语言：英语