SNIKO/agent-skills

A collection of high-quality agent skills for everyday agentic workflows

2Stars on the repository
20Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

git

01

SNIKO/agent-skills

Skill Claude CodeCodex

Use when user asks for git operations: branch creation, committing changes, creating pull requests.

2 10d ago A 20 tokens original MIT

handoff-session

02

SNIKO/agent-skills

Skill Claude CodeCodex

Use when the user asks to summarize, compact, hand off, or create an end-of-session summary for the next agent.

2 10d ago A 29 tokens original MIT

html-artifacts

03

SNIKO/agent-skills

Skill Claude CodeCodex

Create or revise polished, standalone HTML documents for direct human reading. Use for technical documents, proposals, reports, specifications, guides, and review artifacts when the user wants a clear, attractive HTML deliverable.

2 10d ago A 45 tokens original MIT

prompt-writer

04

SNIKO/agent-skills

Skill Claude CodeCodex

Use when creating, reviewing, or revising prompts, system prompts, developer instructions, agent policies, prompt templates, eval prompts, or skill files consumed by LLMs and AI agents. Routes to OpenAI, Anthropic/Claude, or generic prompt-writing guidance based on the target model/provider.

2 10d ago A 64 tokens original MIT

swe-execute

05

SNIKO/agent-skills

Skill Claude CodeCodex

Implement a spec or delivery plan by dispatching each slice to a fresh sub-agent, verifying the result, and maintaining execution state. Use when the user chooses to implement from spec.html or an optional plan.md.

2 10d ago A 50 tokens original MIT

swe-plan

06

SNIKO/agent-skills

Skill Claude CodeCodex

Create an optional delivery plan from a specification. Use only when implementation needs multiple independently verifiable slices, sessions, agents, migrations, backfills, or rollout coordination.

2 10d ago A 37 tokens original MIT

swe-research

07

SNIKO/agent-skills

Skill Claude CodeCodex

Answer a concrete repository, dependency, external-system, feasibility, behaviour, or impact question and preserve the evidence for reuse. Use when the answer is worth keeping — codebase inspection, authoritative sources, live probes, or disposable experiments.

2 10d ago A 51 tokens original MIT

swe-review

08

SNIKO/agent-skills

Skill Claude CodeCodex

Review an SWE brief, research report, spec, delivery plan, execution state, implementation diff, branch, or pull request. Use for fresh-context, evidence-backed findings before the human chooses the next action.

2 10d ago A 45 tokens original MIT

swe-shape

09

SNIKO/agent-skills

Skill Claude CodeCodex

Turn a software change idea into a concise, repository-grounded product brief. Use before designing or implementing non-trivial features, fixes, refactors, or migrations.

2 10d ago A 38 tokens original MIT

swe-spec

10

SNIKO/agent-skills

Skill Claude CodeCodex

Create and progressively deepen a single evolving specification document for a change, from high-level structure down to exact contracts.

2 10d ago A 25 tokens original MIT

swe-worktree

11

SNIKO/agent-skills

Skill Claude CodeCodex

Create an isolated git worktree for an SWE change workspace. Use before implementation when the user wants the change isolated from the current working tree.

2 10d ago A 33 tokens original 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: