Skip to content
mif-docs

Skill reference: exec-summary

Skill reference: exec-summary

Section titled “Skill reference: exec-summary”

The exec-summary skill authors one document genre: a decision-oriented executive summary — BLUF, Key Findings, Recommendation, Risks & Caveats — a 1-2 page standalone brief for decision-makers who will act without reading a full report. This reference describes what that document type is, how the skill produces one, when it earns its place, and the provenance behind it.

PropertyValue
AuthorsA decision-oriented executive summary
Purpose groupBusiness communication
MIF conceptTypesemantic
Target MIF level3
Primary sourceThe BLUF (Bottom Line Up Front) writing convention

What this document type is

Section titled “What this document type is”

An executive summary is a short, standalone brief for decision-makers — executives, sponsors, board members — who need the conclusion and the single recommended action and will not read past page two. Its defining trait is the BLUF (Bottom Line Up Front) — the answer and the recommended action stated before any context, in a heading that must literally contain “BLUF” so automated checks can locate it. The document states conclusions and their business consequence; it does not narrate method, explore alternatives, or expose intermediate analysis. Length is a hard ceiling of 1-2 pages in standalone mode: if it grows, the skill cuts rather than continues.

This is distinct from a team-facing technical evaluation with a mandatory comparison table (an engineering report), from a narrative alignment doc read by engineers before building (a google-design-doc), and from the fuller study or report the summary would introduce, which the skill never generates itself.

How the skill produces one

Section titled “How the skill produces one”

exec-summary is a genre skill: it carries the BLUF pattern as durable instructions plus exemplars, and writes the artifact over a MIF floor so the result is at once a human-readable brief and a machine-conformant unit.

  • Pattern, made operational. The skill encodes four required sections — BLUF, Key Findings (3-5 bullets, each with its “so what” and a source citation), Recommendation (What/Why/How/Risk), and Risks & Caveats (1-3 failure conditions plus confidence basis) — and enforces active voice, at least one quantified finding, and inline numeric citation markers resolving to a compact footnote list rather than a bibliography.
  • A composable, additive overlay. Standalone is the default. When requested, the skill can instead render the genre as the leadership-summary section of a larger report — the management summary introducing a market-research study, or the PTES Executive/Leadership Summary (with Posture, Risk Profile, and Roadmap) introducing a pentest report — emitting only that section, sized for embedding, never the fuller report’s body.
  • Exemplars set the bar. Like every genre in the suite it ships good-l1.md (the MIF Level-1 floor), good.md (the Level-3 target), bad.md (a counter-example that buries the recommendation behind background and method instead of leading with BLUF), and evals/evals.json. The check-exemplars gate proves good-l1.md validates at L1 and good.md at Level 3.
  • MIF projection. The document is authored with MIF frontmatter (via the shared mif-frontmatter substrate) and a conceptType of semantic, reflecting that the doc is declarative decision-and-rationale knowledge, not a time-bound event or a step sequence. mif-validate proves the Markdown ↔ JSON-LD round-trip is lossless before the document is considered done.

When it is beneficial

Section titled “When it is beneficial”

Reach for exec-summary when the deliverable is a short brief for decision-makers who will act without reading a full report, and the center of gravity is a single recommendation with its business consequence stated before any context. It shines whenever a decision needs to move fast on a one-to-two-page read, whether standalone or embedded as the leadership-summary section of a fuller report.

Do not use it for the fuller study or report this summary would introduce — that is feature-spec or a requirements/architecture genre depending on what is being scoped, since this genre only produces the leadership-summary section and never the full body. Do not use it for a team-facing technical evaluation with a comparison table — that is engineering. Do not use it for a narrative alignment doc read by engineers before building — that is google-design-doc.

Example

Section titled “Example”

An executive summary titled “Executive Summary: Data Warehouse Consolidation” opens with the BLUF: approve consolidating three regional data-warehouse platforms (Snowflake, BigQuery, Redshift) onto a single Snowflake instance within 90 days, since running three in parallel costs $2.4M/year against $600K/year consolidated. Key Findings cite the duplicate storage and compute spend, the query-latency parity Snowflake already meets, the 6-engineer-week estimate from a completed EU-region pilot, and the 90-day contract-renewal window. The Recommendation states What (retire BigQuery and Redshift), Why (eliminate $1.8M/year in duplicate spend), How (reuse the EU pilot’s runbook before renewal), and Risk (a missed renewal deadline forces another year of triple-platform spend). Risks & Caveats name the single-pilot basis for the effort estimate, the renewal-deadline dependency, and the load-dependent latency assumption, and two footnotes resolve the inline citation markers.

Provenance & citations

Section titled “Provenance & citations”