aufrank/querying-jira-programmatically
skills/querying-jira-programmatically/SKILL.md
Run Jira MCP searches (Rovo or JQL) via mcpc-backed Python wrappers with cached tool schemas and file-backed outputs. Use when Codex needs deterministic Jira queries using @jira and mcpc (no direct HTTP).
tools
Updated Apr 3, 2026
$ install --global
skillsauthnpx skillsauth add aufrank/agent-skills querying-jira-programmaticallyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 3:20 PM1.8s1 file scanned
SKILL.md
- name:
- querying-jira-programmatically
- description:
- >
- version:
- 0.1.0
Querying Jira Programmatically
Overview
- Code Mode skill for querying Jira through MCP: Rovo
searchandsearchJiraIssuesUsingJql, with generic tool caller and cached schemas. - Uses mcpc wrappers (supports MCPC_BIN/POWERSHELL_EXE for WSL Windows keyring) and writes outputs to disk (
results/+.mcpc-skill-caches/). - Scope: queries/read-only; no edits/transitions by default.
Quick Start (examples)
- Rovo search:
python <CODEX_HOME>/skills/querying-jira-programmatically/scripts/jira_search.py --query "incident backlog" - JQL search:
python <CODEX_HOME>/skills/querying-jira-programmatically/scripts/jira_search_jql.py --jql "project = ABC ORDER BY updated DESC" --max-results 25 - Any tool (cached schemas):
python <CODEX_HOME>/skills/querying-jira-programmatically/scripts/jira_call_tool.py --tool search --arg query:="AI" --refresh-cache - WSL bridge: prefix with
MCPC_BIN="<TOOL_HOME>"(optionalPOWERSHELL_EXE).
Prereqs & Auth
- Tools:
mcpcon PATH; Python 3.11+. - Manual login only:
mcpc https://mcp.atlassian.com/v1/mcp login --profile <name>(defaultdefault). - Session defaults:
@jirasession, serverhttps://mcp.atlassian.com/v1/mcp, profile fromMCP_PROFILEordefault. - WSL tip: reuse Windows keyring by exporting
MCPC_BIN="<TOOL_HOME>"; setPOWERSHELL_EXEfor a specific PowerShell if needed.
Trust / Permissions
- Always: Read caches/references; inspect templates; view cached schemas on disk.
- Ask: Any mcpc call (network); any tool call that mutates Jira (edits, transitions, create, comments); packaging.
- Never: Direct HTTP or credential exposure; destructive actions without explicit user direction.
Canonical Loop
- Clarify query (Rovo vs JQL). Optionally fill
templates/plan.search.jsonortemplates/plan.jql.json. - Ensure auth (scripts run tools-list preflight; if missing, user must login).
- Use scripted wrappers:
jira_search.py(Rovo),jira_search_jql.py(JQL), orjira_call_tool.py(any tool). - Inspect outputs under
results/and cached schemas under.mcpc-skill-caches/querying-jira-programmatically/mcp_tools/. Reuse files instead of re-running. - Keep payloads out of chat; reference file paths.
Scripts (execute, don't call tools directly)
- scripts/jira_search.py: Rovo search via
search.
Flags:--query(required),--content-type jira|confluence|all(default jira),--output(defaultresults/jira.search.json),--session/@jira,--profile,--server. Writes payload; prints count + key/url summary when possible. - scripts/jira_search_jql.py: JQL search via
searchJiraIssuesUsingJql.
Flags:--jql(required),--cloud-id(default cached for this Jira instance),--max-results(default 50),--pages(follow nextPageToken),--output(defaultresults/jira.jql.json), optional--raw-output,--no-output,--timestamp-output,--session/@jira,--profile,--server. Parsescontent[0].textJSON string when present; writes parsed payload (overwrites by default) and pretty-prints key/summary/status. - scripts/jira_call_tool.py: Generic mcpc caller with cached
mcp_tools/tools-list.jsonandmcp_tools/<tool>.jsonunder.mcpc-skill-caches/....
Flags:--tool <name>(required), repeatable--arg key:=value,--output(defaultresults/<tool>.json),--timestamp-output,--refresh-cache,--session/@jira,--profile,--server. Warns if tool missing from cached list; always writes output JSON. - scripts/jira_common.py: Shared auth preflight (
tools-list), MCPC_BIN/PowerShell resolution, cache/results root detection, file writers. - scripts/jira_team_workload.py: Group issues by assignee for a project/team (membersOf).
Flags:--projector--jql(one required),--team,--cloud-id(default set),--max-results,--output,--summary-output, optional--raw-output,--no-output,--no-summary,--timestamp-output. - scripts/jira_unassigned.py: Find open unassigned issues.
Flags:--projector--jql,--include-done,--cloud-id,--max-results,--output, optional--raw-output,--no-output,--timestamp-output. - scripts/jira_backfill_analysis.py: Fetch “backfill/backlog” items (label or text match) and summarize patterns by status/type/priority.
Flags:--projector--jql,--label(else text~"backfill"),--include-done,--cloud-id,--max-results,--output,--summary-output, optional--raw-output,--no-output,--no-summary,--timestamp-output.
Templates
templates/plan.search.json: Rovo search plan scaffold (query, content_type, expected outputs).templates/plan.jql.json: JQL search plan scaffold (jql, expected outputs).
References
references/usage.md: Quick commands, MCPC_BIN tip, cache locations.- Runtime caches:
.mcpc-skill-caches/querying-jira-programmatically/mcp_tools/(tools-list + per-tool schemas). Should be gitignored; regenerate anytime.
Outputs & Restart
- Outputs land in
results/; caches in.mcpc-skill-caches/querying-jira-programmatically/mcp_tools/. - To resume, reuse existing
results/*.jsoninstead of re-calling MCP when possible.
Packaging
- Validate + package when done:
python <REPO_ROOT>/skills/creating-mcp-code-mode-skills/scripts/package_skill.py <REPO_ROOT>/skills/querying-jira-programmatically dist
Related Skills
aufrank/running-dag-pipelines
tools
VerifiedTrustedCommunity
Build and execute modular DAG workflows for long-context processing using slice/map/reduce/recurse/compact/filter operators. Use for one-shot batch jobs, standalone map-reduce pipelines, or when the context-dag plugin is not installed. Trigger when input exceeds the model's context window, when reproducible logged pipelines are needed, or when multi-level recursive processing is required. If context-dag is installed, the plugin's bundled dag_runner.py provides the same capability with persistent artifact storage.
SKILL.mdUpdated May 7, 2026
aufrank/austin-frank-voice
documentation
VerifiedTrustedCommunity
Write in Austin Frank's voice and style. Use this skill whenever generating text that should sound like Austin — strategy docs, charters, proposals, business cases, vision documents, staffing requests, stakeholder updates, cover letters, mission statements, org design documents, or any professional prose where the user wants Austin's distinctive voice. Also use when the user asks to review, edit, or improve a draft for voice consistency, or when they reference "my style", "my voice", "write like me", or "Austin's style".
SKILL.mdUpdated May 7, 2026
aufrank/working-with-notion-programmatically
tools
VerifiedTrustedCommunity
Use mcpc to interact with the Notion MCP server: connect sessions, search workspace content, fetch pages/databases, and run helper scripts for common Notion actions.
SKILL.mdUpdated Apr 3, 2026
aufrank/workflow-or-agent-decider
tools
VerifiedTrustedCommunity
Decide between a scripted workflow and an autonomous agent harness, then scaffold the chosen path. Use when scoping new agentic systems or tool integrations.
SKILL.mdUpdated Apr 3, 2026