Run any Skill in Manus with one click

candidate-staging-sync

Stars1

Forks0

UpdatedMarch 24, 2026 at 21:18

Backfill or refresh staged candidate facts and timeline artifacts from live app rows plus district packets. Use when: expanding candidate-facts/timelines coverage to match public/data, resyncing after district-candidate edits, or restoring provenance on staged candidate files.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

aarshps

aarshps/hora-prathinidhi

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	candidate-staging-sync
description	Backfill or refresh staged candidate facts and timeline artifacts from live app rows plus district packets. Use when: expanding candidate-facts/timelines coverage to match public/data, resyncing after district-candidate edits, or restoring provenance on staged candidate files.

Candidate Staging Sync

When to Use

After editing research/constituency-live-fields/*.json
When research/candidate-facts/ or research/candidate-timelines/ drift from live thin rows
When staged files need packet provenance or full live-row coverage

Canonical Agents

facts-agent
timeline-agent
ingestion-validator-agent

What It Does

Syncs one staged facts file and one staged timeline file for every structured seat candidate
Syncs one structured research/constituency-live-fields/<district>.json file per district
Seeds missing staged files from the live row plus district coverage packet sources
Preserves hand-curated staged files, but adds packet provenance to them
Allows extra research-only candidate files to exist beyond the live app layer

Procedure

Confirm the district publish packets exist for any touched district
Update the staged research source first; if public rows drift, treat them as generated outputs
Trigger facts/timeline subagents for touched candidates only
Trigger ingestion-validator subagent and write results to research/swarm/control/validation-state.json
Spot-check one synced facts file and one timeline file in the affected district

Provenance Model

Live-app-linked staged files carry both provenance.research.liveAppLinked: true and provenance.app
Research-only staged files carry provenance.research.liveAppLinked: false
All staged files must keep district packet refs for coverage, review, and verification

Guardrails

Do not hand-edit public/data/ as the normal starting point for staging sync work
Do not let automated stage updates overwrite curated manual refs/events without explicit review decision
When correcting a seat, also rewrite Current best-known live field prose so removed names do not linger; the parser will otherwise resurrect stale candidates from packet text
Do not treat an empty staged timeline as publishable app timeline content
Do not use sync as a substitute for constituency-level verification when the live row itself is wrong
If constituency numbering in packets differs from app numbering, fix the packet or add a resolver rule before trusting the output

Handoff

If sync changes the repo workflow or provenance shape, update docs/INGESTION_OPERATING_MODEL.md, research/README.md, AGENTS.md, README.md, and handoff docs in the same session

More from this repository

same repository

data-validation

aarshps/hora-prathinidhi

Validate integrity of all public/data JSON files. Use when: after editing candidates, constituencies, or districts JSON; before committing data changes; checking coverage completeness; debugging data mismatches.

2026-04-251

public-candidate-sync

aarshps/hora-prathinidhi

Refresh public district candidate rows from structured live-field research plus staged facts/timelines. Use when: surfacing all candidates per constituency in the app, resyncing public/data after research candidate changes, or restoring legacy candidate route aliases.

2026-04-251

session-wrap-up

aarshps/hora-prathinidhi

Wrap up a meaningful repo work session. Use when: folding durable learnings into repo-local skills, syncing AGENTS/README/handoff docs, or preparing the final close-out commit and push.

2026-04-241

issue-watch-closeout

aarshps/hora-prathinidhi

Drive recurring GitHub issue work from shipped slices to final closeout or reusable closed-issue audits.

2026-04-241

constituency-outcome-slice

aarshps/hora-prathinidhi

Work one bounded constituency possible-outcome slice. Use when: creating or reviewing seat-local outcome packets under the new 1 primary + 3 reviewer workflow.

2026-04-081

ui-conventions

aarshps/hora-prathinidhi

UI rules for the Kerala elections app. Use when: modifying components, adding status indicators, changing how candidates or constituencies display, or touching motion.

2026-04-071

name	candidate-staging-sync
description	Backfill or refresh staged candidate facts and timeline artifacts from live app rows plus district packets. Use when: expanding candidate-facts/timelines coverage to match public/data, resyncing after district-candidate edits, or restoring provenance on staged candidate files.

Candidate Staging Sync

When to Use

After editing research/constituency-live-fields/*.json
When research/candidate-facts/ or research/candidate-timelines/ drift from live thin rows
When staged files need packet provenance or full live-row coverage

Canonical Agents

facts-agent
timeline-agent
ingestion-validator-agent

What It Does

Syncs one staged facts file and one staged timeline file for every structured seat candidate
Syncs one structured research/constituency-live-fields/<district>.json file per district
Seeds missing staged files from the live row plus district coverage packet sources
Preserves hand-curated staged files, but adds packet provenance to them
Allows extra research-only candidate files to exist beyond the live app layer

Procedure

Confirm the district publish packets exist for any touched district
Update the staged research source first; if public rows drift, treat them as generated outputs
Trigger facts/timeline subagents for touched candidates only
Trigger ingestion-validator subagent and write results to research/swarm/control/validation-state.json
Spot-check one synced facts file and one timeline file in the affected district

Provenance Model

Live-app-linked staged files carry both provenance.research.liveAppLinked: true and provenance.app
Research-only staged files carry provenance.research.liveAppLinked: false
All staged files must keep district packet refs for coverage, review, and verification

Guardrails

Do not hand-edit public/data/ as the normal starting point for staging sync work
Do not let automated stage updates overwrite curated manual refs/events without explicit review decision
When correcting a seat, also rewrite Current best-known live field prose so removed names do not linger; the parser will otherwise resurrect stale candidates from packet text
Do not treat an empty staged timeline as publishable app timeline content
Do not use sync as a substitute for constituency-level verification when the live row itself is wrong
If constituency numbering in packets differs from app numbering, fix the packet or add a resolver rule before trusting the output

Handoff

If sync changes the repo workflow or provenance shape, update docs/INGESTION_OPERATING_MODEL.md, research/README.md, AGENTS.md, README.md, and handoff docs in the same session