jira-access-preflightlisted
Install: claude install-skill atretyak1985/swarmery
# Purpose
Make "can this run actually reach Jira" the first unconditional check of any jira-pack flow,
before `jira-tasks` reads anything or `/jira-fix` writes anything. If access is broken, the run
must stop with a report that explains exactly what's missing and how to fix it -- never
proceed on a partial or guessed capability set, and never let a write tool fire when a read
tool already failed.
# Why the tool prefix can't be hardcoded
At least two channels can expose the same Atlassian MCP tools, under **different** prefixes,
with **identical** tool names:
- an officially-installed Atlassian MCP plugin, e.g. tools registered under a
`mcp__plugin_atlassian_atlassian__*`-shaped prefix
- a claude.ai connector for Atlassian/Rovo, e.g. tools registered under a
`mcp__claude_ai_Atlassian_Rovo__*`-shaped prefix
Those two are **illustrative examples of the shape**, not the two values this skill expects --
a host may register either one, both at once, neither, or a differently-named channel entirely,
and which channel (if any) is live changes between sessions and between machines. A skill that
hardcodes one prefix will report "no access" against a perfectly reachable Jira the moment the
*other* channel is the one that's live -- exactly the bug `plugins/core/skills/jira-tasks/SKILL.md`
carried in its own narrower read-only tool-loading example until Phase 8 de-hardcoded it to the
same by-name resolution this skill uses. This skill never assumes a specific prefix is present;
i