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.
- Author
- ai-analyst-lab ↗
- Repository
- ai-analyst ↗
- Licence
- MIT
- Last repository change
- 30.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.09.2026, without references to retired models or APIs.
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
| Repository | Score | Licence |
|---|---|---|
| This page · ai-analyst-lab/ai-analyst | 86 | MIT |
| icloudza/algokiller-plugin | 100 | MIT |
| generous-corp/pulp | 89 | MIT |
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…