productivity by sundial-org
jira sundial-org/jira
Manage Jira issues, boards, sprints, and projects via the jira-cli. Search, create, update, and transition issues directly from the command line.
What it changes View full report → Passed 18 of 21 test cases with the skill, and 8 of 21 without it.
Without skill 36%
With skill 86%
Checks it passed that the model alone missed and 15 more in the full report
12 fixed7 passed either way2 still failing1 broke
Pass-rate lift +50 pp
Tokens -14%
Agent turns 0%
Response time -52% Model gemini-3.6-flashMeasured 8/19/2026 v1 19 of 22 cases passed with skill · 21 comparable
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/sundial-org-jira/SKILL.md https://app.decimal.ai/s/sundial-org-jira/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add sundial-org-jira, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/sundial-org-jira/ and pins it in .decimal/skills.lock
$ decimalai skills add sundial-org-jiraCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/sundial-org-jira/SKILL.md https://app.decimal.ai/s/sundial-org-jira/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Change the workflow status of issue SEC-12 to 'In Progress'.
What was checked, without and with the skill Checked Without skill With skill Requests user confirmation prior to transitioning the issue Uses the command jira issue move SEC-12 "In Progress"
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 50 lines single file
jira
Use jira to manage Jira issues, sprints, and boards. Requires API token setup.
Setup (once)
Generate an API token: https://id.atlassian.com/manage-profile/security/api-tokens
Export it: export JIRA_API_TOKEN="your-token" (add to ~/.zshrc for persistence)
Initialize: jira init --server https://your-org.atlassian.net --login [email protected] --installation cloud
Common commands
Issues
List issues: jira issue list -p PROJECT
View issue: jira issue view PROJ-123
Create issue: jira issue create -p PROJECT -t "Task" -s "Summary" -b "Description"
Edit issue: jira issue edit PROJ-123 -s "New summary"
Assign issue: jira issue assign PROJ-123 "[email protected] "
Transition issue: jira issue move PROJ-123 "In Progress"
Comment: jira issue comment add PROJ-123 "My comment"
Search (JQL): jira issue list -q "project = MKT AND status = 'To Do'"
Sprints
List sprints: jira sprint list -p PROJECT
View active sprint: jira sprint list -p PROJECT --state active
Sprint issues: jira sprint list -p PROJECT --state active --plain
Boards
List boards: jira board list -p PROJECT
Epics
List epics: jira epic list -p PROJECT
View epic: jira epic view PROJ-100
Projects
List projects: jira project list
Output formats
--plain — Tab-separated, no colors (best for scripting)--columns key,summary,status — Select columns
Track record Benchmark 18 / 21
test cases passed, vs 8 / 21 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported Imported 8/3/2026Version v1