radarist/structured-analytic-skills / skills/horizon-scanning
horizon-scanning
VerifiedRuns a horizon scan — a systematic early-warning sweep of sources outside an organisation's usual reading for weak signals and emerging issues — and delivers a prioritised horizon-scanning report with impact/likelihood ratings, verified sources and next steps (UK Government Office for Science Futures Toolkit; Amanatidou et al.). Use when asked "what's on the horizon for {domain} over the next ten years?", "what should the strategy team be watching?", "scan for weak signals", "what could blindside us?" or "set up horizon scanning". Not for a dated prediction on one named trend (use `foresight`) or a rated inventory of macro-environment factors (use `steep-pestle-analysis`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.5 KB |
| agents/openai.yaml | config | 357 B |
| evals/evals.json | config | 6.3 KB |
| references/sources-and-report.md | markdown | 3.9 KB |
references/sources-and-report.md
View on GitHub# Horizon scanning — source strategies and report writing
Supplementary detail for steps 2, 3 and 6 of `../SKILL.md`. Drawn from the UK Government Office for Science *Futures Toolkit* horizon-scanning tool (2017; 2024 edition), Amanatidou et al. (2012) and Hiltunen (2008).
## Source strategy (step 2)
- **Look beyond the organisation's normal parameters.** One aim of the scan is to find areas where the organisation needs to know more, so the source list should be judged by how much of it is *new to the readers*, not by authority alone.
- **Source families to cover:** results of other published scans and trend collections ("scan of scans"); directed searches of academic and grey literature (for example the focal topic combined with a horizon year); professional and industry journals; headlines from newspapers and magazines worldwide; blogs and posts by leading commentators and researchers; interviews with subject experts and outsiders; regulatory consultations and dockets; patents and preprints; start-up and venture filings; adjacent industries.
- **Language and geography:** where possible read sources not in English; scientists and commentators from other countries often summarise their national literature in English on social media.
- **Coverage discipline:** track how many entries fall in each STEEP/PESTLE category to avoid over-weighting technology; keep an explicit quota (for example one entry in four) for fringe or unfamiliar sources; rotate source lists between cycles so the scan does not become a monoculture.
- **Read the original.** Look at the original source material rather than a commentator's interpretation, and record the link to it in the entry.
## Entry format (step 3)
One short entry per observation, in a common structure so entries can be compared and clustered:
| Field | Content |
|---|---|
| Observation | What was seen — one or two sentences, in the source's own terms |
| Source | Original link, publisher, date; the scanner's name |
| Category | S / T / E / Env / P (+ L, Ethical where used) |
| Relation to focal area | How it bears on the questions the scan serves |
| Why it may matter | The scanner's hypothesis — the line that turns archiving into scanning |
| Timescale / importance | Initial view, revised at analysis |
Ten scanners producing one entry a week yields roughly sixty entries in six weeks — enough for the first analysis workshop.
## Analysis workshop (step 4)
- Cluster entries into candidate emerging issues; group by themes that emerge from the entries themselves (a "natural agenda") rather than only by category.
- Distinguish for each issue: the observations (weak signals), the issue they may point to, and the interpretations for the organisation (Hiltunen's three dimensions of the future sign).
- Type each issue: established trend, expected development, newly emerging issue, new risk or opportunity, possible future event.
- Position each on an impact (1–5) × likelihood (1–5) matrix. High-impact/high-likelihood issues are vital for planning; high-impact/low-likelihood issues are the ones most often missed and should still be reported.
- A futures wheel on a high-impact issue helps expose its consequences before it is written up.
## Report (step 6)
The horizon-scanning report is a single, clear summary that typically covers:
- the main trends and impacts identified and any recommendations for action;
- the four to eight new drivers of change most warranting action, each characterised for its newness to the organisation (already well understood? by everyone? do current strategies take it into account?);
- changes with potential for high impact that need further research;
- established trends, included for completeness, with any new developments in previously raised issues when the scan is ongoing;
- the drop list, with reasons, as evidence that the filter is working.
When scanning is ongoing, use the report to refine and focus the next cycle's scope and sources.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |