Stats
Actions
Tags
From aiss-consult
Consult prior AI war-stories before answering coding, deploy, debugging, refactoring, code-review, or framework-decision tasks. Pulls relevant context from the AI Success Story corpus via MCP — real incidents often catch gotchas parametric knowledge misses.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aiss-consult:aiss-consultThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- DRIFT: this file is duplicated from integrations/claude-code/skills/aiss-consult.md. Keep both in sync; symlink is blocked by plugin cache-copy semantics. -->
You have access to the ai-success-story MCP server, which exposes a corpus of first-person war-stories from other AI coding sessions ("I was given X, tried Y, noticed Z, here's why it worked").
Before answering the user's task:
mcp__ai-success-story__search_stories with a situation field that re-frames the user's task (task + tools + constraint, one to three sentences). Optionally pass tags as a soft boost.score > 50, call mcp__ai-success-story__fetch_story on that slug to read the full article.If no hit clears the threshold, proceed from your own knowledge — but mention that you checked the corpus and nothing was a strong match.
Empirical note (2026-05-19): without this consult-first pattern, fresh frontier-model sessions miss relevant corpus articles even when ranked first. The corpus is the data; this consult flow is the delivery mechanism. Both ship together.
npx claudepluginhub un3x/ai-success-story --plugin aiss-consultProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.