forecast — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited forecast (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.
Predict likely next developments using two engines:
While intel tells you what happened, forecast tells you what's likely to happen next — internally from development patterns and externally from ecosystem signals.
Success looks like: forward-looking intelligence with ranked scenarios, development momentum analysis, and actionable recommendations that a team can act on before events materialize.
| Situation | Mode |
|---|---|
| "What are we likely to build next?" | Internal |
| "Where is development concentrated?" | Internal |
| "What external shifts should we prepare for?" | External |
| "What's going to happen next?" (general) | Combined — cross-references internal velocity with external ecosystem signals |
| "What's the full picture?" | Combined — produces compound insights (e.g., "heavy investment in a sinking dependency") |
| "What's the market doing?" / "Technology landscape" | External |
| "What happened recently?" | intel |
| "How is our codebase structured?" | archobs |
| "Plan the implementation" | plan |
Default to Combined mode unless the user explicitly scopes to internal-only or external-only. Cross-referencing internal development velocity against external ecosystem signals produces compound insights that neither engine generates alone.
Inputs: Archobs data — cluster velocity, drift, file risks (internal engine); intel data — collected feeds, CUSUM breaks, chain patterns (external engine); mode selection (internal/external/combined). Outputs: Trajectory predictions (internal), ranked scenarios with confidence levels (external), cross-domain synthesis (combined). Consumed by plan (roadmap), architecture (boundary decisions), spec (versioning guidance).
archobs report first to get cluster assignments, file risks, drift data, and commit historypip install -e 'tools/archobs[full]' cd tools/intelligence && npm install && npm run build npm link # from tools/intelligence/ mkdir -p ~/.config/intel ~/.local/share/intel
cp config/feeds.example.yaml ~/.config/intel/config.yaml intel collect --once ./service/install.sh # macOS (launchd) / Linux (systemd) sqlite3 ~/.local/share/intel/intel.db < tools/intelligence/migrations/003-published-at-analysis.sqlintel stats — check events_total > 0 and newest_event is recent.Choose the mode based on the chooser table, then follow the engine-specific workflow:
references/internal-engine.mdreferences/external-engine.mdWhen the user asks "what's going to happen next?" or wants the full picture, run both engines and cross-reference.
#### Cross-reference patterns
| Internal signal | External signal | Synthesis |
|---|---|---|
| High velocity cluster wrapping external dep | Decaying lifecycle for that dep | Urgent: heavy investment in a sinking dependency |
| Emerging cluster using new technology | Accelerating lifecycle for that tech | Aligned: team is riding a growth wave |
| No cluster activity for a technology | Reinforcing loop detected for that tech | Gap: ecosystem is moving and we're not |
| High velocity in an area | Stable lifecycle for related tech | Normal: team building on solid ground |
When context or time is constrained, these are the load-bearing steps:
intel stats must show recent data; stale data produces stale forecasts.intel forecast --summary --with-context for external; archobs show velocity --window 30 --compare --format json for internal.Steps that can be cut under pressure: detailed deepening on high-scoring scenarios, accumulation signal analysis, multi-scale alignment review.
| Rule | When it matters | What to do |
|---|---|---|
| Scores ≠ probabilities | Always | Scenario scores are relative rankings (temperature-sharpened softmax), not calibrated probabilities. Present as "high/medium/low confidence" not as percentage likelihoods |
| Trajectory = evidence | Internal engine | Use "evidence suggests" / "development patterns indicate" framing |
| Adjacency is heuristic | Internal engine | The adjacency table reflects common patterns, not rules. Domain context overrides |
| Freshness check | Before synthesis | Stale data → stale forecasts. Verify recency via intel stats |
| Spurious correlations | Chains with support < 3 or low source diversity | Flag as lower confidence |
| Temporal artifacts | Chains where temporal_pattern = weekday_correlated or weekday_ratio > 0.7 | Likely a calendar cadence, not causal. weekday_ratio is always present for programmatic assessment. Discount unless you can identify a mechanism |
| Decay reveals staleness | decay_weighted_support ≪ support | Co-movement hasn't recurred recently (half-life = 14d) |
| Entropy = predictability | normalized_entropy > 0.8 | Target is bursty and less predictable; widen confidence window |
| CUSUM change points | Change point within last 7 days | History may not hold — always surface these prominently. Highest-priority signal |
| Signal quality | Scenario ranking | Scenarios rank by chain confidence × source diversity × trigger specificity, not just lift. Low-fanout triggers rank higher |
| Base rate noise | trigger_base_rate > 0.5 | Topic spikes most days — chains from it are less informative |
| Target base rate noise | target_base_rate > 0.8 | Target topic is omnipresent — predicting it will spike is trivially true. Pre-filtered when evidence is weak (no 'high' relevance) |
| Evidence relevance | evidence_relevance = low | Likely a classifier false positive (event tagged with 5+ topics). Weight scenario lower. Scenarios where ALL evidence is 'low' are pre-filtered out |
| Classifier over-tagging | High-volume topics (e.g. lang.typescript) | Topic classifier assigns these broadly — evidence titles may not be topically relevant even when marked high. Cross-check titles before citing. Scenarios with high target_base_rate (> 0.8) and no 'high'-relevance evidence are now pre-filtered. Volume inflation: over-tagged topics have inflated volume counts and chain support — discount both when evidence titles look off-topic |
| Co-movement ≠ causation | All chains and scenarios | Chains detect statistical co-occurrence (A spikes, then B spikes), not causal mechanisms. High lift means "more than random" but does not mean A causes B. Always frame as "associated with" or "tends to follow," never "causes" or "leads to." The weekday-ratio filter catches some calendar artifacts, but spurious correlation is an inherent limitation |
| Topic ≠ mechanism | Narrative construction from structural breaks | Enforced by step 5b in the external engine workflow. You MUST name the specific mechanism for each break in one sentence before constructing chains or scenarios. If the mechanism matches the "default" association (e.g., Iran = oil for a commodities break), explicitly search for at least one alternative mechanism. Use break-relative search windows (--since {days_ago + 4}d), not flat --since 7d. When --with-context is used, check break_titles for mechanism clues from around the break date — these surface events the regular titles (biased toward recent/high-score) may miss |
| Source bias | All forecasts | 128 sources skew toward developer communities (HN), vendor blogs (AWS/Azure/GCP), and financial news (Seeking Alpha, Yahoo Finance). Enterprise procurement signals, analyst reports behind paywalls (Gartner, Forrester, IDC), and non-English-language markets are underweighted. Treat coverage gaps as blind spots, not absence of activity |
| Attention ≠ fundamentals | Lifecycle phases, scenarios | "Accelerating" means more coverage and developer activity, not necessarily more revenue, better margins, or enterprise adoption. The system tracks technology momentum (where engineering attention is concentrating), not market fundamentals. Do not use lifecycle phases as investment or procurement signals without supplementary research |
| Accumulation freshness | Accumulation dynamics | Requires published_at in window. Backfill-only topics are excluded |
| HMM vs rule-based | Phase classification | HMM overrides rule-based when confidence is +0.15 higher. phase_probabilities only present when HMM was used |
| Transitive diversity | A→B→C chains | Per-prefix cap of 3 ensures diverse paths. If all top results share the same A→B prefix, lower-ranked cross-domain paths are more interesting |
| Transitive uncertainty | A→B→C chains | combined_lift is a product, min_support is the weakest link — uncertainty compounds. Use normalized_confidence (geometric mean of leg confidences, 0-1) for calibrated comparison |
| Cluster staleness | Internal engine | Low drift.ari_prev means cluster boundaries are shifting. Path-based analysis still valid |
| 120-day retention | All forecasts | System sees patterns within 120-day retention window with a 90d lifecycle timescale. Can detect quarterly trends and seasonal cycles within a single quarter, but cannot detect year-over-year patterns. Good at "what's happening now, what's about to happen, and how does the current quarter compare to the last." For longer-horizon questions, supplement with analyst reports and historical research |
| No fabrication | Always | Only use data returned by tools. Never invent scenarios or probabilities |
| No raw JSON | Output | Always synthesize through the output template |
change_points_summary, sorted by recency. These are the highest-signal items — a recent structural break means a topic's trajectory changed and historical patterns may not hold.evidence_relevance — flag any 'low' relevance titles as potential classifier false positives.target_entropy > 0.8, note the target is burstytrigger_base_rate (> 0.5) as lower-confidence.references/internal-engine.mdreferences/external-engine.mdreferences/velocity-interpretation.mdreferences/feature-adjacency.mdreferences/manual-fallback.mdintelintel journal add — record forecast-informed decisions for cross-session memory. See intel SKILL.md § Decision Journalarchobsplanarchitecture~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.