Work Spike — Development skill for Claude Code
Run the spike work items in the active release — investigation only, producing one Findings/Recommendations document per spike.
How to install Work Spike
Installs to ~/.claude/skills/martynjsimpson-workmanagementclaudeplugin-work-spike/SKILL.md
mkdir -p ~/.claude/skills/martynjsimpson-workmanagementclaudeplugin-work-spike && curl -fsSL https://raw.githubusercontent.com/martynjsimpson/workManagementClaudePlugin/HEAD/commands/work-spike.md -o ~/.claude/skills/martynjsimpson-workmanagementclaudeplugin-work-spike/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Work Spike does
description: Run the spike work items in the active release — investigation only, producing one Findings/Recommendations document per spike.
Coordinate a spike session. Spikes produce investigation documents only. No code ships, no version is bumped, no release pipeline is triggered.
Step 0 — Resolve configuration
Follow `${CLAUDE_PLUGIN_ROOT}/skills/work-model/references/config-resolution.md`. Read the manifest at `/project.yml`. Refuse to proceed if it is missing.
Alternatives in Development
- Create Handoff — You are tasked with writing a handoff document to hand off your work to another agent in a new session 10k ★
- Swot Analysis — SWOT analysis with actionable recommendations per quadrant 7.8k ★
- Product Requirements Document — Agent-skill-manager — Product: agent-skill-manager (asm) Version: 1.10.0 (current) → 3.0 (vision) Author: luongnv89 Date: 2026-03-19 185 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Work Plan
Run a planning session — close out a finished release, refine intake into work items, and propose the next rel
Ext Recon
Launch the ext-enumerator agent to run passive+active recon and service/web enumeration against the in-scope t
Team Status
Get comprehensive status report for the current agent team. Shows phase progress, findings, and recommendation
Research Codebase Nt
Document codebase as-is without evaluation or recommendations
Q Link
Map and document the relationship between two investigation targets.
Orch Ledger
Show the active Requirements Ledger — clarified answers, open, done and deferred items, and the verify verdict
Related Agents
Cleanup Analyzer
Use this agent to run static analysis tools and get structured cleanup recommendations. Called by the /cleanup
Gov Reviewer
Independent code reviewer for the governed REVIEW phase. Reviews the active task's diff against its approved p
Spike
Bounded investigation that answers one specific technical unknown so a blocked task can resume. Returns a find