Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lenar-amirov/product-pipeline-public --skill multi-source-signal-synthesisergit clone --depth 1 https://github.com/lenar-amirov/product-pipeline-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lenar-amirov/product-pipeline-public/multi-source-signal-synthesiser)<a href="https://agentmods.dev/skills/lenar-amirov/product-pipeline-public/multi-source-signal-synthesiser"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/multi-source-signal-synthesiser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lenar-amirov/product-pipeline-public/multi-source-signal-synthesiser"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/multi-source-signal-synthesiser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01419 |
| Opus 5 | $0.00037 | $0.00709 |
| Sonnet 5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
multi-source-signal-synthesiser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Source Signal Synthesiser Skill
Purpose
Reconcile user signals from multiple sources — interviews, support tickets, NPS, app reviews, analytics, surveys, synthetic research — into a unified, weighted insight brief that surfaces the underlying need rather than the surface-level request.
Pipeline Context
Primary use: Step 6 (/validate-problems) — when combining:
- Analytics data (from analyst)
- Survey results (from research)
- Interview notes (from PM)
- Synthetic interviews (from step 2)
Also useful at any step where multiple data sources need reconciliation.
Evidence Typing
Every signal must be tagged with evidence type and confidence score:
| Type | Confidence | Source examples |
|---|---|---|
| REAL | 0.6 - 1.0 | Analytics data, survey results, user interviews, A/B test results |
| SYNTHETIC | 0.2 - 0.4 | AI-generated interviews, synthetic personas |
| INFERRED | 0.3 - 0.5 | Logical deductions, cross-referencing patterns |
| AMBIGUOUS | 0.1 - 0.3 | Contradictory signals, unclear data |
Conflict resolution: When REAL contradicts SYNTHETIC, REAL wins. Document the delta — the gap between what synthetic research predicted and what real data showed is itself an insight.
Source Weighting (default — adapt to your context)
- Direct research (interviews, usability tests): weight 5
- Analytics data (funnels, cohorts, events): weight 5
- Support tickets (unprompted pain signals): weight 4
- Survey results (structured quantitative): weight 4
- NPS verbatims: weight 3
- App store reviews: weight 2
- Sales call summaries (filtered through sales lens): weight 2
- Synthetic research (AI-generated): weight 1
- Anecdote or single report: weight 1
Process
- Accept inputs from any combination of source types
- Tag each signal by source, apply weight, and assign evidence type + confidence
- CONVERGENCE: same underlying need appearing across 3+ sources
- Calculate combined confidence: highest individual confidence × (1 + 0.1 × number of confirming sources)
- Cap at 1.0
- DIVERGENCE: contradictory signals suggesting user segmentation
- Don't average away disagreement — it usually means different user segments
- FREQUENCY RANKING: count how many independent sources mention each insight
- "N out of M sources mention this" (inspired by frequency-based evidence ranking)
- Distinguish surface request from underlying need (e.g., "faster export" may mean "I don't trust the data will be there when I need it")
- Produce ranked insights by weighted frequency
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 124 lines · 74 tokens per session scan A 43f99d7029dd
multi-source-signal-synthesiser is a skill published in the GitHub repository lenar-amirov/product-pipeline-public (12 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 1,419 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
support-operations
Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per contact, diagnose long queues or poor…