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

Spike Consumer Skill (Inline Arm)

An experiment-harness skill that writes an incident post-mortem while sourcing a guidance skill inline, used to test whether nested skill calls derail the original task.

UtilitiesAdvanced★ 275⑂ 23AI score 6/10Last updated: Sep 23, 2026

What it does

  • Reads an incident data file and produces a post-mortem report through a fixed six-step procedure.
  • At step 3 it invokes a companion guidance skill, spike-guidance-inline, inline (non-forked), absorbs the readability standard, then returns to the main task.
  • The report has five labeled sections (Summary, Impact, Root cause, Resolution, Follow-up actions) and must carry four facts: incident ID, primary error code, peak latency, affected service.
  • Finally it writes <TRIALS_DIR>/<TRIAL_ID>.md and emits a machine-checkable completion token line (CONSUMER_COMPLETE | ...).

Who it's for

  • Engineers studying how nested skill invocation affects task completion in Claude Code
  • Designers of skill/plugin orchestration architectures
  • Anyone wanting a template for A/B harnesses with automatically gradable completion tokens

Example uses

  1. Run the inline arm (this skill) against a forked arm on identical data to compare how often all six steps finish.
  2. Parse the completion token line to auto-score whether all four key facts survived the detour.
  3. Reuse its "call a helper skill, then explicitly return to the main task" wording pattern in your own skills.

· · · 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-inline/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-inline folder from the GitHub repo testdouble/han into my ~/.claude/skills/spike-consumer-inline/.
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 && mkdir -p ~/.claude/skills/spike-consumer-inline && cp han/docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-inline/SKILL.md ~/.claude/skills/spike-consumer-inline/

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

  1. Open a terminal and clone the repo: git clone https://github.com/testdouble/han.git
  2. Create the skill folder: mkdir -p ~/.claude/skills/spike-consumer-inline
  3. Copy the skill file: cp han/docs/plans/han-communication-plugin/artifacts/oi-3-spike/harness-skills/spike-consumer-inline/SKILL.md ~/.claude/skills/spike-consumer-inline/
  4. Install the companion skill spike-guidance-inline from the same harness-skills directory — step 3 depends on it.
  5. Restart Claude Code, then invoke it while passing a TRIAL_ID, an incident data file path, and a TRIALS_DIR.
  6. Verify the completion token on the last line of <TRIALS_DIR>/<TRIAL_ID>.md.
View source on GitHub ↗License: MIT