explain-work
/explain-work
Explain research, analysis, technical design, or implemented work in terms of stakeholder need, mechanism, tradeoffs, evidence, and project fit. Use for a quick rundown, design walkthrough, stakeholder explanation, or an optional teaching conversation; it does not automatically create a specification or course.
- Author
- gcgloven ↗
- Repository
- multiagent-engineer-practices ↗
- Licence
- MIT
- Last repository change
- 11.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Explain research, analysis, technical design, or implemented work in terms of stakeholder need, mechanism, tradeoffs, evidence, and project fit. Use for a quick rundown, design walkthrough, stakeholder explanation, or an optional teaching conversation; it does not automatically create a specification or course.
Original author description
Explain research, analysis, technical design, or implemented work in terms of stakeholder need, mechanism, tradeoffs, evidence, and project fit. Use for a quick rundown, design walkthrough, stakeholder explanation, or an optional teaching conversation; it does not automatically create a specification or course.
How it works
- Choose the explanation the reader needs
- Establish what the artifacts support
- Connect purpose, mechanism, and fit
- Explain interactively when useful
- Finish at the requested depth
SKILL.md preview
--- name: explain-work description: Explain research, analysis, technical design, or implemented work in terms of stakeholder need, mechanism, tradeoffs, evidence, and project fit. Use for a quick rundown, design walkthrough, stakeholder explanation, or an optional teaching conversation; it does not automatically create a specification or course. --- # Explain the work and its purpose ## Choose the explanation the reader needs Identify what the reader wants to understand or decide and what they already know. Use the request and available context; ask a focused question only when a missing distinction would materially change the explanation. A quick rundown should remain quick. When the reader says an explanation did not land, change the framing or example rather than repeating the same terms at greater length. Select the relevant parts of this method. Explaining a small change need not cover the project's entire strategy. A product-fit discussion may need stakeholder and evidence detail, while a technical walkthrough may need an interface example. For deeper walkthroughs or contrasting audience needs, use [explanation patterns](references/explanation-patterns.md). ## Establish what the artifacts support Inspect the source needed for the requested explanation: task, paper, data/result, design, code/diff, test output, or product brief. Preserve the candidate or source identity where it matters. If a document says what should happen and the code shows what currently happens, explain the difference. Distinguish proposed, implemented, inspected, tested, measured, and verified claims. Tests of local behavior do not establish adoption, production readiness, or business benefit. Cite the decisive source or artifact near the claim and identify material missing evidence. If implementation evidence is unavailable, explain the proposed design as a proposal; do not reconstruct a fictional implementation. ## Connect purpose, mechanism, and fit Start with the useful outcome and the stakeholder situation it addresses. Follow one concrete case through the relevant behavior: input or trigger, important decisions or transformations, output, and consequence for the person or system using it. Define unfamiliar terms on first use and preserve established project vocabulary without imposing a new glossary. Explain why the design takes this shape, including the tradeoff that matters for the reader. Separate recorded rationale from your interpretation. Include a failure condition, limitation, or counterexample when it changes how the result should be understood. Use a diagram, comparison, or worked example when it makes the mechanism clearer; do not add decoration or unrelated architecture detail. Connect the work to an existing project outcome or decision only where that link is supported. Make the chain visible: capability changes behavior; changed behavior may improve an outcome; evidence is needed for each claimed improvement. Identify dependencies or operating assumptions. Do not turn a plausible benefit into established product fit, or treat every research result as a feature recommendation. ## Explain interactively when useful For teaching, explain one coherent idea, work through an example, then offer a small application or invite the reader to explain it back. Feedback should target the specific misconception. Participation is optional; do not quiz the user before answering a simple question or claim that understanding has been demonstrated without a response. Follow-up questions can deepen or redirect the explanation without starting a course or mandatory loop. ## Finish at the requested depth Return an explanation the reader can use, with material uncertainty and the next decision only if one is needed. A short response, conversation, or annotated artifact may be enough. Create persistent notes or a formal deliverable only when the request or agreed workflow calls for it. This skill does not initiate implementation, dispatch agents, approve technical work, or add gates, terminology, or retry counters.
Files in this package (2)
- SKILL.md 4 KB
- references/explanation-patterns.md 4 KB
Versions
The database has no other skills named explain-work.
Database snapshot: 13.11.2026 · package version c73ea85dd086 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 85atlas-explain
Explains a piece of the work to a person who was not there: a mechanism in plain words for someone who does not code, a decision with its options and its cost, a set of measurements with what they do and do not prove. Use for "atlas explain", "explain this simply", "why did we… - 100explain-branch-changes
Explain the current git branch's changes in plain product language for a non-technical audience — no file paths, no code references, no jargon. Reads the branch diff, commits, and available docs, then produces a short human briefing about what changed and why it matters. Use… - 90explain-plainly
Default to explaining technical work in plain language for a non-technical audience, using an existing project glossary only when a persistent document is already in scope. Use whenever an explanation is aimed at someone outside the technical team, or whenever jargon would… - 90stakeholder-alignment
Translates between technical data teams and business stakeholders. Use when preparing stakeholder updates, translating technical data work for executives, shaping vague business requests into buildable specs, navigating competing priorities across data consumers, or when someone… - 100stakeholder-summary
Produces a plain-language stakeholder summary from an existing feature specification, for sharing with non-technical stakeholders before implementation kicks off. Use when the user wants to draft a stakeholder summary, executive summary, or business summary of a feature spec or… - 100technical-analyst
Technical analysis translator for Product Managers. Use when the user needs to analyze a system, codebase, API, or technical concept in PM-friendly terms. Trigger with "understand system", "explain code", "technical analysis", "how does X work", or "what does this service do".