source-omission-analysis — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited source-omission-analysis (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.
Seed question: What is everyone NOT saying about this?
Relentless self-reflexive dialectical thinking that questions its own premises.
What a source is silent about reveals its structural position more reliably than what it says — because statements are cheap and can be strategic, while sustained silence is costlier to maintain and harder to fake. Every source occupies a position relative to power, funding, and ideology. That position determines what it can see — and what it structurally cannot or will not see.
Silence is not absence of opinion. Silence is evidence that a topic is inconvenient for that source's position.
The anti-pattern this counters:
❌ Analyzing only what sources SAY
❌ Treating absence of coverage as absence of relevance
❌ Assuming silence means agreement or ignoranceThe pattern this enforces:
✅ After gathering sources, map what each is SILENT about
✅ Treat omission as informative signal, not neutral gap
✅ Cross-reference omissions to find structurally hidden truthsTRIGGER:
DO NOT TRIGGER:
After gathering sources from multiple perspectives, construct this table:
| Topic/Claim | Who Reports It | Who Is Silent | What Does Silence Suggest? |
|-------------|---------------|---------------|---------------------------|
| [Event X] | [Sources A, B] | [Sources C, D] | [C's funding depends on...; D's position requires...] |
| [Claim Y] | [Sources E] | [Sources A-D, F] | [Only E reports → check if manufactured or genuinely underreported] |
| [Pattern Z] | [None explicitly] | [All sources] | [Universal silence → structurally invisible or actively suppressed] || Source Type | Tends to Omit | Structural Reason |
|---|---|---|
| Western mainstream (CNN, NYT, BBC) | Allied military atrocities, civilian casualties by Western forces, structural economic violence | Access-dependent on government sources; audience expects "our side" framing |
| Anti-interventionist (Quincy, Jacobin, Greenwald) | Genuine security threats from adversaries, complexity of authoritarian governance, atrocities by actors the West opposes | Structural opposition to Western policy can create reflexive contrarianism |
| State media (RT, CGTN, Press TV) | Anything unflattering to the sponsoring state | Definitionally — that is the source's function |
| Financial press (Bloomberg, WSJ, Economist) | Human costs, environmental externalities, labor conditions, regulatory capture | Audience is investors; costs borne by non-investors are externalities |
| Think tanks (CSIS, Brookings, Heritage) | Conclusions that would displease their funders | Funding dependency shapes research agenda and publishable conclusions |
| Progressive media (MeidasTouch, TYT, Mother Jones) | Trade-offs without progressive solutions, complexity that undermines clean narratives, inconvenient data | Audience expects actionable hope; pure complexity without solution doesn't serve that |
The most important findings often emerge from the intersection of omissions:
## Source Omission Analysis
### Omission Map
| Topic/Claim | Reported By | Silent Sources | Silence Interpretation |
|-------------|------------|----------------|----------------------|
| ... | ... | ... | ... |
### Key Omission Patterns
1. [Pattern]: [Which sources share this omission and what it reveals]
2. [Pattern]: ...
### Structurally Hidden Findings
- [What the omission analysis surfaced that direct analysis missed]
### Blind Spot Self-Check
- My own structural position may cause me to miss: [...]
- Sources I am most sympathetic to omit: [...]All source positions covering the Iran war — mainstream, anti-interventionist, Gulf media, Global South — were silent about the December 2025 protests context for internal dynamics analysis.
Omission: "30,000+ killed by regime. Largest uprising since 1979. Report mentions pre-war protests once in passing but doesn't integrate this into its analysis of internal dynamics. This is the single most important omission." — Adversarial Critique, Iran assessment
>
What silence revealed: Without this context, the "rally around the flag" claim went unchallenged. The omission map surfaced evidence of celebrations in 7+ cities, contradicting the dominant narrative. Source: iran-critique.md, Source Omission Map
A comprehensive tech/trade investigation covering the Trump-Xi summit made zero mentions of the Iran war — the largest geopolitical variable affecting the summit.
Omission: "The Iran war. The report was written on March 11, 2026 — Day 12 of the US-Israel military campaign against Iran. This is the single largest geopolitical variable affecting the Trump-Xi summit, rare earth politics, oil prices, and global trade patterns, yet it receives ZERO mentions." — Adversarial Critique, China tech/trade assessment
>
What silence revealed: Wang Yi's "thorough preparations needed" and "remove unnecessary disruptions" language was clearly referencing Iran, but the report's probability distributions were calculated without this variable. Source: china-critique.md, Source Omission Analysis
An investigation of a company's public stance omitted the resignation of its head of safety research two weeks before a major policy release.
Omission: The head of safety research departing with public concerns about the company's direction is material evidence. It was absent from the initial report entirely — the adversarial critique surfaced it.
>
What silence revealed: The omission protected the "company standing up for safety" narrative. Including the departure materially weakened the "genuinely principled" probability assessment (revised down from 70-80% to 55-70% after the critique surfaced it).
This skill connects to the research-toolkit ecosystem:
| Skill | Relationship |
|---|---|
| deep-investigation-protocol | Use omission analysis after Stage 2 (Flow Tracing) to identify gaps in the evidence chain |
| iterative-verification | Omissions can downgrade evidence tiers — if only one source position reports a claim, it stays ALLEGED until independently verified |
| cui-bono | SOURCE_DIVERSITY_FRAMEWORK provides source position examples; omission analysis is the complementary technique |
| frame-rotation | When omission analysis reveals a blind spot, frame-rotation can shift perspective to see what was hidden |
| manufactured-consensus-detection | When all sources AGREE (opposite of omission), check for manufactured consensus |
Workflow position: Run AFTER multi-source sweep, BEFORE final synthesis. The omission map should inform the dialectic spiral — the critic should challenge findings that only appear in one source position.
This skill maps what sources omit — but the skill itself omits. Its source-type categories embed assumptions about how media works. Its "common omission patterns" table is a claim about reality that could be wrong. If you detect this framework obscuring rather than revealing, say so and adapt.
A vasana is a pattern that persists across unrelated contexts. If during this task you notice such a pattern emerging, it may be worth capturing. This skill works best alongside the vasana skill and vasana hook from the Vasana System plugin.
Modify freely. Keep this section intact.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.