babamba2babamba2/superclaude-for-sap/skills/project-dashboard/SKILL.md

project-dashboard

Skill69 starsChanged 7 months agoMITView on GitHub

SAP project management dashboard for PMs and the PMO — one editable HTML page per project (summary, KPIs, milestones with Q-gates, WBS with Gantt, SAP actuals, team, history) plus a portfolio page over every project. Templates for new implementation (SAP Activate), S/4 conversion, rollout, AMS release and small projects; module consultant and development consultant tracked separately (WRICEF stages and hand-off queue); actuals read from the connected SAP system (transport requests split into customizing vs workbench, package objects, inactive objects, dumps after go-live). Team members join and leave by date; open items of leavers are flagged and reassigned.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
MUST read workflow.md before Step 1.
line 57

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

SC4SAP Project Dashboard

One editable HTML page per SAP project for the PM and the PMO, and one portfolio page over all projects. The plan comes from a template for the project type; the progress comes from the PM (edit mode) and from the connected SAP system (read-only).

<Purpose>
SAP projects split the work between **module consultants** (requirements, FS, configuration, functional unit test) and **development consultants** (TS, build, unit test). Delays hide in the hand-off between the two and in transports nobody releases. Generic PM tools do not see either. This skill tracks every WRICEF item through its stages with both owners, shows the hand-off queue, reads the system's transports (customizing = configuration work, workbench = development work), and rolls everything into milestones, KPIs and a portfolio — on pages the PMO can edit and send back.
</Purpose>

<Response_Prefix>Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention.</Response_Prefix> <Target_Object>Packages and transports are read on the active profile's system only. Not found → stop and ask per ../../common/multi-profile-artifact-resolution.md § Target object not on the active system.</Target_Object>

<Use_When>

"프로젝트 대시보드", "WBS 관리", "마일스톤 관리", "PMO 보고", "프로젝트 현황", "project dashboard", "SAP project plan", "go-live readiness", "WRICEF 진척", "포트폴리오"
A new SAP project (implementation, S/4 conversion, rollout, AMS release, small project) needs a plan, or an existing one needs status
The PMO wants all projects on one page, or the load of people working on several projects
A team member leaves or joins; WRICEF items change owner </Use_When>

<Do_Not_Use_When>

Business process documentation → /sc4sap:module-to-process
One program's specification → /sc4sap:program-to-spec
Writing ABAP → /sc4sap:create-program </Do_Not_Use_When>

<Session_Trust_Bootstrap> MANDATORY — Step 0. Invoke /sc4sap:trust-session with parent_skill=sc4sap:project-dashboard. Skip silently if .sc4sap/session-trust.log has a line within the last 24h. </Session_Trust_Bootstrap>

<Decisions_Fixed> Settled at design time (2026-10-28) — do not ask again:

Topic	Decision
Readers	PM (edits the plan) and PMO (status across projects)
Output	Per project ONE self-contained HTML page with edit mode; `projects/portfolio-<lang>.html` over all projects; English companion
Storage	Local files are the source (`<artifactBase>/projects/<CODE>/`). Every row, milestone, member and KPI has a stable id so a later sync (SAP Z tables, Notion) can match rows — not built yet
Several projects	Always assume more than one: one folder per project code, portfolio rebuilt after every change, people matched across projects by SAP user (else name)
Team changes	Members leave by an end date (`to`), never by deletion; finished items keep their owner; open items of a member who left are flagged ("needs a new owner") until `reassign`
Two consultant sides	`fnOwner` = module consultant, `devOwner` = development consultant on deliverables and WRICEF items; WRICEF stages req → FS → TS → build → unit test → FUT → SIT → done; hand-off queue = FS done (waiting for development) and unit test done (waiting for FUT)
SAP actuals	Read-only: E070 / E07T (requests since project start; W = configuration, K = development; workstream from the request text, default `[SD] …`), E071 (WRICEF objects → requests), package objects (TADIR, or the ADT package listing on BASIS < 7.50), inactive objects, dumps after go-live. Never business data, never a write
Progress	The PM's values win; SAP evidence only suggests ("evidence ahead")
KPIs	Auto KPIs (schedule, WRICEF, transports, team, hypercare) trended per build; manual KPIs per project type (quality, data, training, cost) entered in the page
Versions	Plan changes (import, add-wricef, reassign, build) = new minor version; `refresh` (actuals) = same version
</Decisions_Fixed>

<Paths>
`<PRJ>` = `<artifactBase>/projects` ([`../../common/multi-profile-artifact-resolution.md`](../../common/multi-profile-artifact-resolution.md)). Per project `<PRJ>/<CODE>/`: `<CODE>-project.json` (model), `<CODE>-project.en.json`, `<CODE>-<lang>.history.json`, `<CODE>-dashboard-v<ver>-<lang>.html`, `_src/`, `_i18n/`, `_answers.json`. Tool: `node "<PLUGIN_ROOT>/scripts/project/build-project-doc.mjs" <cmd> … --dir <PRJ>` (header of that file lists every command).
</Paths>

<Workflow>
MUST read [`workflow.md`](workflow.md) before Step 1. Model fields: [`model-schema.md`](model-schema.md) — read before editing a model file directly.
</Workflow>

<Output_Format>

Project <CODE> · <name> · v<ver> · <type> · go-live <date>
Status <RAG> · progress <actual>% / plan <planned>% · milestones <passed>/<n> · WRICEF <done>/<n>
Hand-offs: to development <n> · to FUT <n> · needs a new owner <n> · KPIs to watch <n>
SAP actuals: <n> requests (configuration <n> / development <n>) · <n> package objects · read <date>
Page: <html> · English: <html> · Portfolio: <PRJ>/portfolio-<lang>.html
Next: edit in the browser → Save → "import <file>", "실적 갱신", "WRICEF 추가", "<사람> 담당 이관"

</Output_Format>

<Not_Yet> Sync to SAP Z tables (DEV only, approval per run) and export to Notion are phase 2 — say so when asked, and keep ids stable. </Not_Yet>

Download now (ZIP)

Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
leosimini/keelokit★ 2same name
laurentvv/agents-kit★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-cbo-objSkill
- analyze-codeSkill
- analyze-symptomSkill
- ask-consultantSkill
- compare-programsSkill
- config-to-documentSkill
- create-objectSkill
- create-programSkill
- ecoSkill
- interface-mapping-specSkill
- mcp-setupSkill
- module-to-processSkill
- package-to-processSkill
- program-to-manualSkill
- program-to-specSkill
- role-matrixSkill
- sap-doctorSkill
- sap-optionSkill
- setupSkill
- smartform-from-pdfSkill
- smartform-previewSkill
- trust-sessionSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free