V
ValentinNikolaev/agent-skills
Cross-platform agent skills and plugin distributions for OpenAI Codex and Claude Code
SECURITY.md ✓
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 1 ★ · ValentinNikolaev/agent-skills · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-10-23 · last seen 2026-11-14 · seen 26× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Agent 技能. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
ValentinNikolaev/agent-skills;first catalogued 2026-10-23;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# Agent Plugins for Codex and Claude Code
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Reusable agent workflows for code review, documentation, project memory, product decisions, writing, and publishing. Install the collection once, then ask your agent to use a skill by name.
## Quick start
### Codex
bash
codex plugin marketplace add ValentinNikolaev/agent-skills --ref master
codex plugin add agent-plugins@valentin-agent-plugins
codex plugin list
### Claude Code
bash
claude plugin marketplace add ValentinNikolaev/agent-skills@master
claude plugin install agent-plugins@valentin-agent-plugins
If Claude Code is already running, use /reload-plugins after installation.
### Try it
text
Use code-review to review my uncommitted changes.
Use audit-docs to find stale documentation references.
Use business-viability-assessment to assess this product idea.
## Skill catalog
### Review and quality
audit-docs — Find broken references, stale indexes, and documentation drift.
clean-code-comments — Remove redundant comments without changing behavior.
code-review — Review changes for bugs, regressions, and test gaps.
code-simplification — Simplify code while preserving behavior and contracts.
fix-pr — Implement actionable pull-request review feedback.
plan-review — Validate implementation plans and revisions.
review-arch — Assess system boundaries and architecture tradeoffs.
review-spec — Review proposed specifications and revisions.
verify-impl — Trace specification requirements to implementation evidence.
### Engineering checks
monitor-ci — Follow required GitHub Actions jobs to a verified outcome.
prove-checks — Verify that a green check could detect the claimed failure.
vet-dependency — Assess a library against project contracts and maintenance evidence.
### Engineering workflows
debugging-and-error-recovery — Find the cause of observed failures and verify fixes.
deprecation-and-migration — Move live consumers across contract changes safely.
planning-and-task-breakdown — Create ordered implementation steps with acceptance checks.
test-driven-development — Implement behavior through a focused red-green loop.
write-spec — Draft testable requirements for a proposed change.
### Project memory
audit-memory — Check memory stores for drift, stale facts, and broken relationships.
create-memory — Bootstrap durable project memory from a repository.
ingest-memory — Import source-backed knowledge into project memory.
update-memory — Record durable facts learned during completed work.
### Decision-making
business-viability-assessment — Assess demand, costs, economics, risks, and viability.
council — Pressure-test consequential decisions with independent advisor passes.
### Interface design
api-and-interface-design — Design stable API and module contracts.
console-ux-design — Design usable, automation-safe console commands.
### Writing and publishing
audit-github-pages-ux — Audit rendered GitHub Pages experiences.
create-github-pages — Build or repair repository-grounded GitHub Pages sites.
github-pages-content-architecture — Structure Pages content around reader tasks.
github-pages-visual-system — Design accessible visual systems for Pages sites.
improve-github-pages — Propose and apply approved Pages improvements.
stop-slop — Humanize prose while preserving meaning and evidence.
## Quick start
### Codex
bash
codex plugin marketplace add ValentinNikolaev/agent-skills --ref master
codex plugin add agent-plugins@valentin-agent-plugins
codex plugin list
### Claude Code
bash
claude plugin marketplace add ValentinNikolaev/agent-skills@master
claude plugin install agent-plugins@valentin-agent-plugins
If Claude Code is already running, use /reload-plugins after installation.
### Try it
text
Use code-review to review my uncommitted changes.
Use audit-docs to find stale documentation references.
Use business-viability-assessment to assess this product idea.
## Skill catalog
### Review and quality
audit-docs — Find broken references, stale indexes, and documentation drift.
clean-code-comments — Remove redundant comments without changing behavior.
code-review — Review changes for bugs, regressions, and test gaps.
code-simplification — Simplify code while preserving behavior and contracts.
fix-pr — Implement actionable pull-request review feedback.
plan-review — Validate implementation plans and revisions.
review-arch — Assess system boundaries and architecture tradeoffs.
review-spec — Review proposed specifications and revisions.
verify-impl — Trace specification requirements to implementation evidence.
### Engineering checks
monitor-ci — Follow required GitHub Actions jobs to a verified outcome.
prove-checks — Verify that a green check could detect the claimed failure.
vet-dependency — Assess a library against project contracts and maintenance evidence.
### Engineering workflows
debugging-and-error-recovery — Find the cause of observed failures and verify fixes.
deprecation-and-migration — Move live consumers across contract changes safely.
planning-and-task-breakdown — Create ordered implementation steps with acceptance checks.
test-driven-development — Implement behavior through a focused red-green loop.
write-spec — Draft testable requirements for a proposed change.
### Project memory
audit-memory — Check memory stores for drift, stale facts, and broken relationships.
create-memory — Bootstrap durable project memory from a repository.
ingest-memory — Import source-backed knowledge into project memory.
update-memory — Record durable facts learned during completed work.
### Decision-making
business-viability-assessment — Assess demand, costs, economics, risks, and viability.
council — Pressure-test consequential decisions with independent advisor passes.
### Interface design
api-and-interface-design — Design stable API and module contracts.
console-ux-design — Design usable, automation-safe console commands.
### Writing and publishing
audit-github-pages-ux — Audit rendered GitHub Pages experiences.
create-github-pages — Build or repair repository-grounded GitHub Pages sites.
github-pages-content-architecture — Structure Pages content around reader tasks.
github-pages-visual-system — Design accessible visual systems for Pages sites.
improve-github-pages — Propose and apply approved Pages improvements.
stop-slop — Humanize prose while preserving meaning and evidence.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/valentinnikolaev-agent-skills/)
- Source
- github · https://github.com/ValentinNikolaev/agent-skills
- Browse by field
- Agent skills
- Traction
- 1 ★
- added
- today
- Security policy
- the repository has
SECURITY.mdat its root (we checked that the file exists, not what it says)
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.