improve-pipeline
Improve Pipeline
Use this skill when real-world usage of the pipeline reveals a weakness in the pipeline itself. The triggering incident may happen in another repository, but the improvement target is always chrislacey89/skills: the skills, docs, checklists, and workflow guidance that shape future agentic development.
This is not automatic self-modification. Default output is a GitHub issue in chrislacey89/skills. The issue should explain what happened, why it is a pipeline problem rather than only a project problem, what change is recommended, what repo-wide effects the change could have, and which files in chrislacey89/skills would need to change if the recommendation is approved.
If the user asks for implementation after reviewing the proposal, implementation can follow as a separate step. Do not skip the proposal.
One question per turn. If key facts are missing, ask one question at a time and wait for the user's answer before asking the next. Never turn incident intake or review into a questionnaire.
Prefer single-select. Use single-select multiple choice when the user is choosing one direction, one priority, or one next step.
Use multi-select rarely. Reserve it for compatible sets — goals, constraints, non-goals, success criteria — that can all coexist. If prioritization matters, follow up asking which selected item is primary.
Use the platform's question tool when available. In Claude Code, use
AskUserQuestion; in Codex,request_user_input; in Gemini,ask_user. Otherwise, present numbered options in chat and wait for the user's reply before proceeding.
Invocation Position
This is an optional meta-skill, not a default pipeline stage.
More from chrislacey89/skills
pre-merge
Primary pipeline review step after verified implementation. Use to create a PR with lineage and run architectural review before merge. Not for QA intake, planning, or implementation work.
22execute
Primary pipeline execution step after /prd-to-issues or for clearly scoped implementation work. Use to build, verify, and commit a concrete slice, delegating to /tdd for backend work and behavior-heavy frontend logic when red-green-refactor will reduce risk. Not for shaping or pre-merge review.
21write-a-prd
Primary pipeline shaping step after /research and before /prd-to-issues. Use when the problem is understood well enough to turn into a bounded PRD issue. May invoke /design-an-interface or /api-design-review when interface or contract uncertainty remains. Not for discovery, decomposition, or implementation-ready work.
14research
Primary pipeline step after /shape and before /write-a-prd. Use to verify current docs, versions, repo patterns, and key unknowns before shaping. Invokes /api-design-review when API contract risk is high. Not for underdefined problems or implementation-ready work.
13prd-to-issues
Primary pipeline decomposition step after /write-a-prd. Use when a shaped PRD is ready to become implementation-ready slices with boundary maps and dependency order. Not for unresolved scope, appetite, or solution direction.
13setup-ralph-loop
Infrastructure skill for setting up Ralph loop scripts for Claude-driven AFK execution. Use when a repo wants a HITL-to-AFK runner around /execute with bounded iterations, GitHub-native durable state, and explicit feedback loops. Not a normal feature-delivery stage; it prepares the repo for safer autonomous execution.
12