skill-workshop

A workshop process for improving a skill, meaning a reusable set of instructions for an agent, through group feedback and simulated use.

In plain words
What is it for?
Reviewing proposed changes with multiple agents, testing the skill against scenarios, and repeating the cycle until the instructions improve.
Why use it?
It exposes unclear instructions and bad behavior before the skill is released.

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/jackfranklin/dotfiles/skill-workshop
Any agent
npx skills add jackfranklin/dotfiles --skill skill-workshop
Clone the repo
git clone --depth 1 https://github.com/jackfranklin/dotfiles

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 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 $0.00057 $0.01136
Opus 5 $0.00028 $0.00568
Sonnet 5 $0.00011 $0.00227
Haiku 4.5 $0.00006 $0.00114

Measured 3d ago against content hash a8704d7582d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-workshop 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 3d 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.

claude/skills/skill-workshop/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Workshop

An iterative loop for improving a SKILL.md using two distinct subagent phases: consensus (do proposed changes make sense in theory?) and simulation (does the skill produce good output in practice?). Repeat until the skill is behaving well.

Phase 0 — Orient

  1. Locate and read the target SKILL.md in full. Skills are typically found in a skills/<name>/SKILL.md directory — check the current project or any known skills directory in the environment. Read it before asking anything. If the file cannot be found, tell the user clearly, list the skills you can find, and offer three recovery paths: wrong name, create a new skill from scratch, or non-standard path. Do not proceed without a file to work from.
  2. Ask the user: "What problem are you trying to fix, or what behaviour do you want to test? Even a vague sense of something feeling off is useful." If they already have a clear problem description, proceed directly.
  3. If the user can't articulate a problem — or after one follow-up still can't — skip straight to Phase 2 (simulation) to discover issues empirically. Don't loop on clarification.

Phase 1 — Proposal + Consensus

Use this phase when you have one or more proposed changes to evaluate before applying them.

  1. Present your proposed changes clearly — show before/after diffs or describe the change in plain language.
  2. Spawn 4 subagents in parallel, each given:
    • The full current SKILL.md
    • The proposed change(s)
    • This prompt: "Evaluate this proposal critically. Does it solve the stated problem? Is the wording clear and well-calibrated? Anything that should be added, removed, or tightened? Be direct and opinionated. Under 200 words."
  3. Synthesize the responses. Look for:
    • Unanimous agreement → apply with confidence
    • Recurring criticisms → fold them in before applying
    • One-off objections → use your judgment; note them to the user
  4. Apply the changes, then proceed to Phase 2 to verify in practice. Do not commit yet — only commit at the stopping condition.

Read the full file on GitHub · 78 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. 3d ago First seen · 78 lines · 57 tokens per session scan A a8704d7582d2

Subscribe to this mod's changes

skill-workshop is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 1,136 once invoked, about $0.0003 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 2026-08-30.

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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