topic-brainstormer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited topic-brainstormer (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.
Generate blog topic ideas that align with a content identity built around solving frustrating technical problems. Three phases: ASSESS, DECIDE, GENERATE. Every topic must pass the three-question content quality filter before presentation.
| Signal | Load | Content |
|---|---|---|
| Filtering topics: three-question test, category examples | references/content-filter.md | Full quality filter with green/red/yellow topic categories, salvage patterns |
| Scoring: impact, vex, resolution matrix | references/priority-scoring.md | Rubrics per dimension, score ranges, calibration, worked examples |
| Mining: problem sources, gap analysis, expansion | references/topic-sources.md | Mining prompts, signal strength, gap types, expansion strategies |
Gather context about existing content and available sources.
Gate: Content landscape documented, at least 2 sources identified with material.
Generate candidates and filter through the content quality test.
Failure modes to catch:
Gate: At least 3 candidates pass. Fewer than 3 -- return to Step 1 with different sources.
Score, prioritize, and present the filtered list.
Scoring: Priority = Impact(1-5) x Vex(1-5) x Resolution(1-5). Thresholds: 60-125 HIGH, 30-59 MEDIUM, 15-29 LOW, 1-14 SKIP.
Titles: Replace vague categories with failure-mode titles. Bad: "Kubernetes Networking Issues". Good: "Pod-to-Pod Traffic Works But Service Discovery Fails".
Output format: Grouped by priority tier. Each topic: title, vex, joy, content cluster fit, word estimate, score breakdown. End with recommendations: top pick, quick win, deep dive.
Tie-breaking: prefer topics that fill an existing gap, complement recent posts, use already-covered technologies, have clearer narrative structure.
Gate: All topics scored, prioritized, presented with recommendations.
When the task asks for angles on a single topic (not fresh candidates), apply these six lenses instead of the content quality filter:
| Lens | Question |
|---|---|
| Perspective shift | Whose view changes the story? |
| Ladder of abstraction | One rung up (the trend) or down (the single case)? |
| News values | Which value carries it: conflict, proximity, novelty, impact, human interest? |
| Data angle | What does the dataset say that the narrative misses? |
| Contrarian | What if the consensus framing is wrong? |
| Timeliness peg | Why now? What event or deadline makes this urgent? |
Rules: one lens per kept angle (distinctness is structural). Each kept angle must pass the "so what?" gate -- one sentence naming a concrete reader payoff. Log refused angles with reason.
| Error | Cause | Solution |
|---|---|---|
| No existing posts | Content directory empty | Focus on problem mining; ask about recent debugging sessions |
| All candidates fail filter | Sources lack frustration signals | Ask probing questions: "What broke recently?" Shift sources. |
| Topic too broad | Category, not a specific problem | Break into failure modes: "[A] works but [B] fails" |
| Resolution unclear | Ongoing issue, no fix yet | Defer until resolved; or assess if "understanding the workaround" suffices |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.