Skip to content
Skills Library
Data & analytics · Analysis

trace-analysis

/trace-analysis

Trace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.

Repository
ai-analyst ↗
Licence
MIT
Last repository change
30.09.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 30.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Trace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.

Original author description

Trace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.

How it works

SKILL.md has no level-two headings · 26 lines, 185 words

SKILL.md preview
---
name: trace-analysis
description: Trace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.
---

# Trace one analysis

First invoke the `trace` skill so the machine-readable provenance record,
lightweight receipt, and shareable HTML exist. Then review the claim through
these records:

1. The output states the claim.
2. The receipt identifies the source, data snapshot, query, and artifacts.
3. The trace records how the run unfolded.
4. Logs record specific system and query events.
5. The query and result provide execution evidence.

Use `helpers.evals.trace.inspect_receipt` on
`working/trace_receipt_<analysis_id>.json` to identify missing fields and
initial query risks. Then inspect the analytical details that code cannot infer
from syntax alone: population, filters, time window, timezone, exclusions,
grain, join cardinality, missingness, referential integrity, freshness,
reconciliation, and whether the claim stays within the evidence.

For a query with a join and aggregate, test the grain directly. Compare the candidate total with a defensible reference query when one exists. A query that runs successfully may still answer the wrong question.

Save the written review beside the analysis. Report the review path and the
HTML trace path together. Report missing evidence as missing. A complete
receipt makes an analysis inspectable. It does not make the analysis correct.

Versions

RepositoryScoreLicence
This page · ai-analyst-lab/ai-analyst86MIT
icloudza/algokiller-plugin100MIT
generous-corp/pulp89MIT

Database snapshot: 13.11.2026 · package version eb32a246259f (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 96speclink-trace
    Use when someone asks how a capability came to be or why it works this way — walks its provenance chain across archived changes, source discussions, evidence and live code.
  • 96speclink-trace
    Use when someone asks how a capability came to be or why it works this way — walks its provenance chain across archived changes, source discussions, evidence and live code.
  • 100trace
    Evidence-driven tracing and execution tracking. Use for "trace this", "execution trace", and "track progress".
  • 90s4h-investigation-source-trace
    Traces a claim back to its origin: who first made it, what evidence it rested on, and how it has been distorted in transmission. Use when you've heard something and want to know where it actually came from — 'where does this claim come from', 'who first said this', 'I've heard…
  • 100data-analysis
    Answers product questions with data, decision first — decision, question, population boundary (what the source excludes), source authority, read-only query through the query API, sanity checks, claim level, interpretation with a source label. Metrics mode looks up a metric in…
  • 100readonly-db-query
    Run a safe, read-only query against a specific Postgres database (usually production) to pull a stat or verify data. The script refuses to run unless the connection points at the expected host, never prints the connection string, and reads timestamps as text to avoid time-zone…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.