agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/analyze-temporal-trajectory/SKILL.md

analyze-temporal-trajectory

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Analyze an ordered temporal trajectory, including persistence/narrowing/widening tests, regime changes, inflection points, and optional extrapolation with uncertainty. Entity type, window, and forecast mode are parameters.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If forecast mode is enabled, extrapolate with confidence bands and explicit caveats.

    line 25
  2. Very specific:

    If the trajectory suggests an abrupt regime change rather than smooth variation, consider detect-breakpoint as the next tactic.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

analyze-temporal-trajectory

Purpose

Analyze an ordered temporal trajectory for persistence, narrowing or widening, regime changes, inflection points, and optional uncertain extrapolation.

Input contract

required: [time_indexed_records, entity_type, metric, window]
optional: [forecast_mode, uncertainty_model, grouping_keys, event_markers]
constraints: [records are ordered by time; metric direction is explicit; extrapolation is optional and must carry uncertainty]

Procedure

  1. Normalize records by entity, metric, and time index and identify the observed frontier.
  2. Fit the caller-selected trajectory representation and inspect residuals and regime changes.
  3. Detect inflection points, persistence, narrowing, widening, or stable segments.
  4. If forecast mode is enabled, extrapolate with confidence bands and explicit caveats.
  5. Return trajectory data, regime annotations, and uncertainty.

If the trajectory suggests an abrupt regime change rather than smooth variation, consider detect-breakpoint as the next tactic.

Output contract

produces: [trajectory_series, fitted_model, inflection_points, regime_labels, forecast, uncertainty_notes]
delta_fields: [findings, evidence_updates, decisions, uncertainties]

Quality gates

  • Preserve source minimum yield where the progress-curve mode applies: 2 progress curves, 3 years of history, 1 inflection point, and 2 headroom estimates.
  • Retain filing time series, lifecycle/S-curve fitting, historical SOTA curve fitting, milestone projection with confidence intervals, and 2/5/10-year persistence-window comparisons when those modes are requested.
  • Forecasts must state model, time window, confidence band, and uncertainty; do not turn a trend into a causal claim.

Parameterization

The caller must provide the entity schema, time window, metric and direction, grouping keys, frontier rule, model/forecast mode, uncertainty method, and event markers. For persistence testing provide the requested windows; for filing or SOTA analysis provide dates and comparable score records.

Failure and counterexamples

Reject unsorted or incomparable records, forecasts without uncertainty, or regime labels unsupported by the observed series. Do not infer a future milestone when the metric definition changes across time.

Provenance map

  • resolved: knowledge-acquisition/trend-analysis
  • resolved: knowledge-acquisition/progress-curve-fitting
  • resolved: knowledge-acquisition/progress-curve-fitting
  • resolved: knowledge-acquisition/progress-curve-construction
  • resolved: experiment-execution/timeline-projection
  • intermediate: Pass3/analyze-filing-trend
  • intermediate: Pass3/fit-research-progress-curve
  • intermediate: Pass3/project-research-timeline
  • resolved: deep-insight/temporal-sensitivity-testing

Verbatim source criteria excerpts

  • progress-curve-construction lines 66-69: Progress curves constructed 2; years of history covered 3; inflection points identified 1; headroom estimates produced 2.
  • progress-curve-construction lines 50 and 60: Annotated inflection points with causal attribution; headroom estimates with confidence intervals.

Preserved source criteria ledger

sourcephysical linekindsource criterion
knowledge-acquisition/progress-curve-construction46numericMinimum yield: 2 progress curves, 3 years history, 1 inflection point, 2 headroom estimates.
deep-insight/temporal-sensitivity-testing12structuralTest persistence across the caller-supplied time windows and classify narrowing, widening, or stable.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free