summarization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited summarization (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Summarization is semantic compression: reduce a source to the smallest useful representation for a reader and task while preserving meaning, provenance, decisions, evidence, and next actions.
What is this skill? Prose condensation and abstraction patterns for AI agents: extracting key findings from long reports, writing executive summaries, creating TLDRs, compressing context for handoffs between agents, progressive summarization, audit report condensation, and the discipline of deciding what to keep and what to cut when space is limited. Use when summarizing session findings, writing wrap reports, condensing research for durable notes, creating executive summaries of audits, compressing context before agent handoffs, or distilling long documents into actionable briefs. Do NOT use for data compression algorithms (use compression), context-window budget management (use context-window), working-set selection (use context-management), prose tone repair (use writing-humanizer), or quality scoring (use evaluation).
Summarization is not shortening. It is the skill of identifying what matters and discarding what doesn't — while preserving the causal chain that makes the remaining content useful.
Extractive summarization (pulling key sentences verbatim), abstractive summarization (rewriting in fewer words while preserving meaning), progressive summarization (Tiago Forte's 3-layer highlight method adapted for agent work), executive summary structure (situation → findings → recommendations → next steps), TLDR generation (one-sentence distillation of a complex document), session wrap condensation (converting 50+ findings into a prioritized summary), research-to-memory compression (distilling task research into memory-file-sized briefs), agent handoff summaries (what the next agent needs to know, nothing else), audit report condensation (from raw findings to scored summary with evidence), and the information-theoretic principle of lossy compression — what you choose to lose defines the quality of the summary.
Every agent in this system produces more text than any human will read. Session logs run to thousands of lines. Research files contain every detail an agent discovered. Audit reports list every finding at every severity level. Without summarization discipline, this output becomes noise — technically complete but practically useless.
The failure mode is not missing information but buried information. A 500-line research file that contains the answer on line 347 is worse than a 50-line summary that puts the answer in the first paragraph. A wrap report that lists 30 findings without priority is worse than one that highlights the 3 critical findings and links to the rest.
Summarization is lossy by definition. The skill is in choosing what to lose. The rules below encode that choice: keep decisions and their rationale, keep blockers and their workarounds, keep numbers and their context — drop process narration, drop tool output, drop hedging.
This skill combines three public traditions:
Not all summaries serve the same purpose. Match the technique to the audience and constraint.
| Level | Name | Length | Keeps | Drops | Use For |
|---|---|---|---|---|---|
| L1 | TLDR | 1-2 sentences | The single most important takeaway | Everything else | chat messages, issue comments, commit subjects |
| L2 | Executive Summary | 3-8 sentences | Situation, key findings, recommendation | Evidence, process, reasoning | Memory files, PR descriptions, wrap reports |
| L3 | Brief | 1-2 paragraphs | Findings + evidence + reasoning | Verbose tool output, narration | Task handoffs, research summaries |
| L4 | Condensed Report | 1-2 pages | Full findings with priority, evidence refs | Raw data, duplicates, process log | Audit reports, board meeting summaries |
Rule: Always specify which level you're writing. "Summarize this" is ambiguous. "Write an L2 executive summary" is actionable.
A summary must preserve the source's truth conditions. It can be shorter, reorganized, and clearer, but it cannot invent new claims, hide uncertainty, convert tentative evidence into certainty, or erase the path back to the source.
Before handing off a summary, check:
| Question | Pass Condition |
|---|---|
| Does every claim appear in or follow directly from the source? | No unsupported claims or imported assumptions |
| Are decisions, blockers, numbers, and action items preserved? | The reader can act without reopening the full source |
| Are evidence paths retained for non-obvious claims? | File paths, URLs, issue links, commit hashes, or line refs remain available |
| Is uncertainty still visible? | Confidence, caveats, and unresolved questions are not flattened |
| Are omissions intentional? | Dropped material is low-value for the declared summary level |
| Are audit findings complete? | Condensed audit summaries preserve exact counts and link to the complete findings |
Always keep:
Always drop:
The executive summary is the most common summary type in this system (memory files, wrap reports, PR descriptions).
Four-part structure:
Example:
Audited the 12 language-related skills for gap coverage. Found 4 clear gaps: microcopy (highest impact — no owner for functional UI text), i18n (linguistics has awareness but no implementation patterns), summarization (critical for agent context handoffs but unowned), and content strategy (the "what to write" layer above copywriting). Recommend creating all 4 as shared skills in the quality/meta/display layers. See gap analysis in conversation context.
Adapted from Tiago Forte's method for agent memory:
For memory files: Always store Layer 3 (the executive summary) with a link to Layer 0 (the raw source) if it still exists. Never store Layer 0 directly in memory — it's too large and decays into noise.
When one agent passes work to another, the summary must answer exactly these questions:
Anything not in these 5 categories is noise for the receiving agent.
Raw audit findings → prioritized summary:
A condensed audit report is not a replacement for the complete findings artifact. It may prioritize, group, and explain, but it must not silently drop findings or present a "top N" subset as the whole audit.
| Anti-Pattern | Why It's Bad | Fix |
|---|---|---|
| "First I did X, then Y, then Z" | Process narration wastes reader time | State the outcome, not the journey |
| Including all findings at equal weight | Reader can't distinguish critical from trivial | Prioritize by severity/impact |
| Summarizing by shortening every section proportionally | Produces a uniformly shallow version | Cut entire low-value sections, keep high-value sections intact |
| "As mentioned above" / "As noted earlier" | Self-referential text that doesn't survive extraction | Make each section standalone |
| Hedging in summaries | "It might be worth considering" wastes the reader's attention | State the recommendation directly |
| Instead of this skill | Use | Why |
|---|---|---|
| Compressing payloads, files, logs, blobs, or storage formats | compression | That work is algorithmic compression, not prose condensation |
| Deciding token budgets, truncation points, or compaction timing | context-window | That work chooses the size constraint; this skill works inside it |
| Deciding which documents, notes, or facts belong in the active context | context-management | That work selects the source material before summarization begins |
| Making prose sound more human, warm, or less AI-patterned | writing-humanizer | That work edits voice and rhythm; this skill preserves and condenses meaning |
| Designing rubrics, assigning scores, or judging quality | evaluation | That work defines the quality standard; summarization may report its result |
After applying this skill, verify:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.