Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate weekly executive status updates from Jira/Linear data exports. Produces a structured "highlights / blockers / risks / asks / what's next" briefing in markdown, Confluence, Notion, Linear, JSON, or Mermaid.
.claude/skills/borghei-status-update-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 227% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 170% | 0% |
Weekly status updates eat 30-90 minutes of every PM's Friday afternoon and they almost always say the same thing in subtly different ways. This skill standardizes the artifact: pull tickets from Jira or Linear (or any JSON dump), and emit a structured update with five named sections -- Highlights, Blockers, Risks, Asks, What's Next -- plus a traffic-light status (Red / Yellow / Green) for the period. The structure follows SBNR (Status / Blockers / Next / Risks) and a condensed Amazon 6-pager narrative for Highlights; the stoplight verdict follows classic R/Y/G reporting.
references/status-structure-and-workflow.md).status_generator.py emits all six SHARED_OUTPUT_SCHEMA formats: markdown, confluence, notion, linear, json, mermaid.When NOT to use: real-time incident response (use delivery-manager/ incident skills), deep retrospectives (use sprint-retrospective/), or one-to-one stakeholder reporting needing custom framing (use roadmap-communication/).
Before generating the update, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
| Tool | Purpose | Command | |------|---------|---------| | status_generator.py | Generate a structured weekly status update | python scripts/status_generator.py --input data.json --format markdown | | status_generator.py --demo | Inspect demo input and output formats | python scripts/status_generator.py --demo --format markdown |
The traffic-light status is a human judgment, not a calculation — set it and document the rationale. See references/tool-and-troubleshooting.md for flags and the input JSON shape.
Load the reference that matches the task — keep this file lean and pull detail on demand:
status_generator.py flags, input JSON shape, Mermaid output, troubleshooting table, and success criteria. Read when running the tool or diagnosing a problem.In Scope:
Out of Scope:
linear-expert//jira-expert/ skills to export the JSON first)../scrum-master/)delivery-manager/)sprint-retrospective/)roadmap-communication/)Important Caveats:
| Integration | Direction | Description | |-------------|-----------|-------------| | ../jira-expert/ | Receives from | Jira JQL exports or MCP pulls feed the input JSON | | linear-expert/ | Receives from | Linear GraphQL exports feed the input JSON | | ../senior-pm/ | Feeds into | Weekly updates aggregate into monthly portfolio reports; risks lift into the portfolio risk register | | ../scrum-master/ | Pairs with | Sprint health scores supply the Highlights/Risks context | | roadmap-communication/ | Pairs with | Weekly status feeds the executive-variant roadmap narrative | | sprint-retrospective/ | Feeds into | Four weeks of status archives become retrospective input | | ../program-manager/ | Feeds into | Cross-team status aggregation rolls up multiple team updates | | ../delivery-manager/ | Pairs with | Release windows and incident references show up in Highlights and Risks |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | fail→fail | 10,019 | 14,339 | +43% | 1 | 1 | 0% | 1,939 | 4,241 | +119% | 0 | 0 | — |
case-01 | pass→pass | 7,483 | 3,288 | -56% | 1 | 1 | 0% | 1,240 | 2,200 | +77% | 0 | 0 | — |
case-02 | pass→pass | 7,922 | 2,243 | -72% | 1 | 1 | 0% | 1,202 | 1,927 | +60% | 0 | 0 | — |
case-03 | fail→pass | 9,263 | 8,615 | -7% | 1 | 1 | 0% | 1,449 | 2,988 | +106% | 0 | 0 | — |
case-04 | fail→fail | 12,383 | 14,170 | +14% | 1 | 1 | 0% | 1,803 | 3,659 | +103% | 0 | 0 | — |
case-05 | pass→pass | 8,261 | 6,271 | -24% | 1 | 1 | 0% | 1,348 | 2,533 | +88% | 0 | 0 | — |
case-06 | fail→pass | 10,009 | 18,789 | +88% | 1 | 1 | 0% | 1,407 | 4,605 | +227% | 0 | 0 | — |
case-07 | fail→pass | 11,212 | 2,848 | -75% | 1 | 1 | 0% | 1,692 | 2,095 | +24% | 0 | 0 | — |
case-08 | fail→pass | 8,859 | 4,112 | -54% | 1 | 1 | 0% | 1,383 | 2,339 | +69% | 0 | 0 | — |
case-09 | fail→pass | 6,061 | 4,855 | -20% | 1 | 1 | 0% | 877 | 2,367 | +170% | 0 | 0 | — |
case-10 | fail→pass | 8,786 | 2,645 | -70% | 1 | 1 | 0% | 1,420 | 2,073 | +46% | 0 | 0 | — |
case-11 | fail→pass | 14,691 | 11,074 | -25% | 1 | 1 | 0% | 2,373 | 3,249 | +37% | 0 | 0 | — |
case-12 | fail→fail | 9,479 | 8,753 | -8% | 1 | 1 | 0% | 1,431 | 2,743 | +92% | 0 | 0 | — |
case-13 | fail→pass | 3,275 | 13,941 | +326% | 1 | 1 | 0% | 460 | 3,591 | +681% | 0 | 0 | — |
case-14 | pass→pass | 6,970 | 2,701 | -61% | 1 | 1 | 0% | 1,148 | 2,071 | +80% | 0 | 0 | — |
case-15 | pass→pass | 9,805 | 11,172 | +14% | 1 | 1 | 0% | 1,374 | 3,352 | +144% | 0 | 0 | — |
case-16 | pass→pass | 8,671 | 1,999 | -77% | 1 | 1 | 0% | 1,317 | 1,904 | +45% | 0 | 0 | — |
case-22 | fail→fail | 15,826 | 14,194 | -10% | 1 | 1 | 0% | 2,268 | 3,562 | +57% | 0 | 0 | — |
case-17 | fail→pass | 2,185 | 2,151 | -2% | 1 | 1 | 0% | 266 | 1,956 | +635% | 0 | 0 | — |
case-18 | pass→pass | 7,895 | 4,401 | -44% | 1 | 1 | 0% | 1,193 | 2,308 | +93% | 0 | 0 | — |
case-19 | pass→pass | 9,158 | 8,372 | -9% | 1 | 1 | 0% | 1,478 | 2,790 | +89% | 0 | 0 | — |
case-20 | fail→fail | 6,168 | 12,176 | +97% | 1 | 1 | 0% | 988 | 3,571 | +261% | 0 | 0 | — |
case-21 | fail→fail | 18,051 | 17,595 | -3% | 1 | 1 | 0% | 2,653 | 4,408 | +66% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +39 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.