process-extraction

A method for turning a completed, successful multi-step workflow into a reusable skill. It first records the concrete process and then extracts the parts that apply more generally.

In plain words
What is it for?
Use it after finishing a complex repeatable task, when the same sequence keeps recurring, or during a retrospective to document and package the workflow.
Why use it?
It prevents useful know-how from remaining trapped in one project or conversation and makes repeated work easier to standardize.

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/dojogenesis/mcp/process-extraction
Any agent
npx skills add DojoGenesis/mcp --skill process-extraction
Clone the repo
git clone --depth 1 https://github.com/DojoGenesis/mcp

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,136 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 $0.00069 $0.02136
Opus 5 $0.00034 $0.01068
Sonnet 5 $0.00014 $0.00427
Haiku 4.5 $0.00007 $0.00214

Measured yesterday against content hash 4d11553e4836, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-extraction 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 yesterday.

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.

internal/skills/bundled/skill-forge/process-extraction/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process Extraction

I. Philosophy: From One-Off Process to Institutional Knowledge

Every time someone completes a complex task successfully, they generate implicit knowledge -- a sequence of decisions, actions, and course corrections that led to a good outcome. This implicit knowledge is valuable, but it's also fragile: it lives in a single conversation, a single mind, a single moment. Without capture, it evaporates.

Process extraction is the discipline of making implicit knowledge explicit. The key insight is that you must document the specific process before abstracting the general pattern. The specific is the anchor. Without it, generalization drifts into theory.

The process example is the proof. The skill is the tool. You cannot build a reliable tool without first understanding -- in concrete detail -- what the tool must do.

II. When to Use This Skill

  • After completing a complex, multi-step task that produced a good outcome and is likely to be repeated
  • When you find yourself repeating the same sequence of actions across different projects or contexts
  • During a retrospective when a successful workflow is identified for standardization
  • When onboarding someone to a complex process that needs to be reproducible
  • When a conversation transcript contains a valuable workflow that should be preserved
  • When institutional knowledge exists only in one person's head and needs to be formalized
  • After a debugging session that revealed a systematic diagnostic approach

When NOT to use: If the process was unsuccessful, capture it as a retrospective lesson, not a skill. If the process is trivial (1-2 steps), it doesn't warrant a skill.

III. The Extraction Workflow

Step 1: Document the Specific Process

Goal: Create a detailed record of what actually happened, not what should have happened.

Actions:

  1. Identify the source: conversation transcript, memory, or user description
  2. Create a process example document with these sections:
    • Context: When and why the process was used
    • Input: What the process started with
    • Output: What the process produced
    • Steps Taken: Every significant action, in order, with goals and outcomes
    • Key Decisions: What was decided, why, and what alternatives were considered
    • What Worked: Success factors and why they mattered
    • What Was Hard: Challenges encountered and how they were resolved
    • Reusable Pattern: The generalizable principle (the kernel of the future skill)

Read the full file on GitHub · 196 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. yesterday First seen · 196 lines · 69 tokens per session scan A 4d11553e4836

Subscribe to this mod's changes

process-extraction is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,136 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 2026-08-31.

Related

Other skills, from other repositories

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

drt-analyze

Analyze DRT cluster health for a given time range. Reconstructs the operations timeline, checks CockroachDB metrics (availability, latency, storage, changefeeds, jobs, goroutines, admission control, LSM, KV prober) and logs for anomalies, correlates findings with disruptive operations to distinguish expected…

cockroachdb/cockroach · 149 tokens

redux-to-swr

Migrate React components from Redux + Saga to SWR hooks. Use when converting data fetching from Redux store (reducers, sagas, selectors, connect HOC) to SWR-based hooks in CockroachDB DB Console or cluster-ui.

cockroachdb/cockroach · 53 tokens

mma-investigator

Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.

cockroachdb/cockroach · 47 tokens

file-crdb-issue

Use when filing, creating, or reporting GitHub issues for CockroachDB. Use when asked to open a bug report, feature request, investigation issue, or performance inquiry. Also use when the user mentions wanting to track a problem, report a regression, or document unexpected behavior in CockroachDB.

cockroachdb/cockroach · 66 tokens

engflow-artifacts

Use when downloading test logs, artifacts, or outputs.zip from EngFlow build invocations. Use when investigating CockroachDB CI test failures hosted on mesolite.cluster.engflow.com.

cockroachdb/cockroach · 41 tokens