Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vigneshbarani24/sap-superpowers --skill fit-gap-analysisgit clone --depth 1 https://github.com/vigneshbarani24/sap-superpowersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/fit-gap-analysis)<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/fit-gap-analysis"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/fit-gap-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/fit-gap-analysis"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/fit-gap-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.03406 |
| Opus 5 | $0.00022 | $0.01703 |
| Sonnet 5 | $0.00009 | $0.00681 |
| Haiku 4.5 | $0.00004 | $0.00341 |
Grade A, and why
fit-gap-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Fit-Gap Analysis
This skill enforces evidence-based classification of every business requirement against SAP standard capability so that no gap is accepted without a resolution strategy, no fit is assumed without proof, and no custom development is committed without assessing clean core impact.
Iron Laws
- NEVER CLASSIFY AS FIT WITHOUT PROVING STANDARD COVERS IT. "SAP probably handles this" is not a Fit classification. A Fit requires a named standard transaction, configuration path, or Best Practice process that demonstrably covers the requirement without modification.
- NEVER ACCEPT A GAP WITHOUT A RESOLUTION STRATEGY. Every gap — whether configuration, development, process, or partial — must carry an explicit resolution: configure, extend (BAdI/BTP), workaround, or accept. An unresolved gap is a project risk, not a classification.
- ALWAYS ASSESS CLEAN CORE IMPACT. Every Gap-Dev classification must be evaluated against SAP's clean core principles. Custom code inside the core (Z-programs, modifications) must be challenged. Side-by-side BTP extensions are preferred.
- NEVER ESTIMATE GAP EFFORT WITHOUT A TECHNICAL APPROACH. A gap effort estimate without a named technical approach (configuration path, BAdI, BTP service, interface) is a guess. Do not produce numbers without first defining how the gap will be resolved.
- INVOLVE THE PROCESS OWNER IN EVERY CLASSIFICATION. Business requirements classified without process owner confirmation are consultant assumptions. Classifications must be reviewed and signed off by the accountable business stakeholder before the matrix is baselined.
Rationalization Table
| Agent Will Try To... | Why It Seems Reasonable | Why It Fails | Counter |
|---|---|---|---|
| Classify as Fit based on module familiarity | "We've done SD before — standard order-to-cash covers this" | Requirements vary by client. Client-specific pricing rules, approval workflows, or output formats routinely break assumed Fits. | Iron Law 1: Name the transaction or config path. If you cannot, it is not a Fit. |
| Leave a gap without resolution strategy | "We'll decide how to resolve it in Realize" | Unresolved gaps accumulate. By Realize, the backlog is so large that the resolution strategy defaults to custom development without proper evaluation. | Iron Law 2: Every gap row must have a resolution column populated at classification time. |
| Skip clean core assessment for Gap-Dev | "The client wants the custom report — just estimate it" | Custom code inside the core creates technical debt, blocks upgrades, and violates SAP's cloud roadmap. A side-by-side BTP extension may achieve the same result with zero core impact. | Iron Law 3: Every Gap-Dev must include a clean core impact rating (None / Low / Medium / High) and a justification. |
| Estimate effort before technical approach is defined | "The functional consultant can size it at a high level" | Without a technical approach, effort estimates have no basis. A BAdI-based extension might take 3 days; a full RAP object might take 15. The approach drives the number. | Iron Law 4: Technical approach column must be populated before the effort column. |
| Use only IT stakeholders for classification | "The business is too busy for workshops" | IT stakeholders may not know the actual business requirement. Process owners routinely override IT classifications in UAT. Surface the disagreement now. | Iron Law 5: Document the process owner who confirmed each classification. If unavailable, flag it as provisional. |
| Classify every variance as a gap | "If it requires configuration, it must be a gap" | Standard SAP configuration is not a gap — it is the mechanism for delivering Fit. Misclassifying configuration as a gap inflates gap counts and creates false urgency for custom development. | Classification rules: Gap-Config = achievable via standard configuration. Only Gap-Dev and Gap-Process represent true divergence from standard. |
| Ignore partial fits | "It's mostly covered — call it a Fit" | Partial fits carry hidden scope. The uncovered portion becomes a late-stage gap that is more expensive to resolve once design is locked. | Classification rules: Partial fit = its own category. Document what is covered and what is not. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 255 lines · 44 tokens per session scan A 01c20e6b7f80
fit-gap-analysis is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 3,406 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sap-expert
Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
add-telegram
Add Telegram channel integration via Chat SDK.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-gchat
Add Google Chat channel integration via Chat SDK.