Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Spike Consumer (Forked Arm)

An experimental harness skill that builds a six-step incident post-mortem to measure agent behavior across a context fork.

UtilitiesAdvanced★ 258⑂ 22AI score 6/10Last updated: Sep 1, 2026

What it does

  • Reads an incident data file and extracts four mandatory facts: incident ID, primary error code, peak latency, affected service.
  • Mid-workflow, invokes the paired guidance skill spike-guidance-forked to source a shared readability standard.
  • Drafts a post-mortem with five labeled sections (Summary, Impact, Root cause, Resolution, Follow-up actions), writes it to <TRIALS_DIR>/<TRIAL_ID>.md, and appends an exact completion token.
  • Its real purpose is instrumentation: checking whether the agent resumes and finishes the original task after a sub-skill (context fork) call.

Who it's for

  • Engineers experimenting with Claude Code's Skill invocation and context-fork behavior.
  • Researchers reproducing "agent stops after the sub-skill" failure modes.
  • Not suitable if you simply want a general-purpose post-mortem writer.

Examples

  1. Run with TRIAL_ID=oi3-007 plus an incident log path and verify the artifact ends with a well-formed CONSUMER_COMPLETE | ... line.
  2. Compare six-step completion rates between the forked and inline arms on identical data.
  3. Script a grader that confirms all four facts appear across the five report sections.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/testdouble/han/HEAD/docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-forked/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-forked folder from the GitHub repo testdouble/han into my ~/.claude/skills/spike-consumer-forked/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/testdouble/han.git && cp -r han/docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-forked ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/testdouble/han.git
  3. Go to the harness folder: cd han/docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills
  4. Copy this skill and its companion: cp -r spike-consumer-forked spike-guidance-forked ~/.claude/skills/
  5. Restart Claude Code and confirm registration with /skills.
  6. When invoking, always supply TRIAL_ID, the incident data file path, and TRIALS_DIR; without them the skill cannot run correctly.
View source on GitHub ↗License: MIT