create-skill

A workflow for creating, changing, checking, or measuring an Agent Skill: a reusable set of instructions that changes how an agent handles a task. It follows the open Agent Skills format and emphasizes small, portable procedures.

In plain words
What is it for?
Use it to create or revise a SKILL.md workflow, evaluate an existing skill, or compare its results with and without the skill.
Why use it?
It helps turn repeated work into a well-scoped skill while reducing unclear boundaries, unnecessary files, and unreliable instructions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rmjosea/agentic-sdlc-kit/create-skill
Any agent
npx skills add rmjosea/agentic-sdlc-kit --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/rmjosea/agentic-sdlc-kit

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.00723
Opus 5 $0.00036 $0.00362
Sonnet 5 $0.00014 $0.00145
Haiku 4.5 $0.00007 $0.00072

Measured 2d ago against content hash c3c2abb33f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/create-skill/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a High-Quality Agent Skill

Create the smallest reusable procedure that reliably changes agent behavior.

Select the mode

  • create or revise: change files only after responsibility and boundaries are confirmed; report files changed and validation results.
  • evaluate: do not mutate by default; report evidence-backed findings by severity, non-findings worth preserving, and approved, changes-required, or blocked.
  • benchmark: define positive and adjacent-negative prompts, quality rubrics, fresh-session procedure, baseline without the skill, and comparable results.

Understand with examples

  1. Gather two or more realistic requests that should use the skill.
  2. Gather requests that look similar but should not use it.
  3. Identify the repeated procedure, non-obvious knowledge, and failure modes.
  4. Ask one material question at a time using AGENTS.md.
  5. Confirm the skill's responsibility and boundaries before creating files.

Do not create a skill for one-off context, generic intelligence the model already has, or durable repository rules that belong in AGENTS.md.

Design progressive disclosure

Use three levels:

  1. name and description for discovery;
  2. concise SKILL.md instructions for activation;
  3. references/, scripts/, and assets/ loaded or executed only as needed.

Keep SKILL.md preferably under 200 lines and always under 500 lines. Keep references one level deep. State the exact condition for reading each resource. Do not duplicate information between files.

Choose resources

  • scripts/: deterministic or repeatedly rewritten operations; execute tests.
  • references/: focused knowledge needed only in specific conditions.
  • assets/: templates or output resources not intended as instructions.

Create no directory or file without a concrete use. Do not add auxiliary README, changelog, installation guide, or process diary inside a skill.

Write metadata

Use YAML frontmatter containing at least:

---
name: verb-led-name
description: What the skill does. Use when ... Include concrete triggers.
---

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 94 lines · 71 tokens per session scan A c3c2abb33f77

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository rmjosea/agentic-sdlc-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 723 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens