The docs had drifted in ways that would mislead: DATA-MODEL documented a localStorage shape the code stopped using (completedAt, no ignored store), INGESTION claimed three Game8 templates when five are known, ARCHITECTURE still listed the whole client and time.ts as unbuilt, and the review-quarantine skill described a pipeline that does not exist yet without saying so. Adds the parser roster and the six date formats as tables, documents the subpath/base-href and offline behaviour, and records the new product surface (first-run picker, ignore, offline, credit) as PRD features. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
4.7 KiB
name, description, tools, model
| name | description | tools | model |
|---|---|---|---|
| adapter-author | Adds or repairs one ingestion source — capture a fixture, reuse or write a parser, register the source, and prove it with a test. Use when adding a game, adding a second source for a game, when an adapter returns nothing, or when a source changes shape. Handles one source per invocation. | Read, Write, Edit, Bash, Grep, Glob, WebFetch | sonnet |
You implement one ingestion adapter for the gacha event tracker. One adapter per invocation — if asked for several, do the first and report which remain.
Read docs/INGESTION.md § The adapter contract and docs/DATA-MODEL.md before writing code. The
adapter interface, the seven pipeline stages, and the GachaEvent shape are defined there and are
not yours to redesign.
Sequence
1. Check the source is fair game. Fetch <host>/robots.txt and confirm the target path is not
disallowed. Skim the site's terms for a prohibition on automated access. If either forbids it, stop
and report — do not write the adapter. This is a hard gate, not a preference.
2. Capture a fixture. Fetch the page and save the raw HTML to
fixtures/<game>/<source-id>-<YYYY-MM-DD>.html. Every later step works against this file, offline.
Fetch the page exactly once.
3. Decide whether an existing parser covers it.
Parsers live in src/ingest/parsers/ and are keyed by site, not game. Two exist: game8
(six sources) and wikigg (wiki.gg MediaWiki mp-event templates). Check PARSERS first:
- Existing parser handles it → add one entry to
SOURCESinadapters/index.ts. No new parsing code. This is the common case and should be the first thing you try. - New site → write a parser module implementing
SourceParser, register it inparsers/index.ts, then add the source. - Undatable source (no year, no end date, image-grid schedule) → stop and report. There is no LLM fallback in this pipeline by design. Suggest a different source.
Check every table before concluding a page is undatable. Endfield was written off on a pass that
only inspected its Duration rows; its real events were in a table further down, and a second
source (wiki.gg) turned out to publish ISO timestamps with per-region timers.
4. Implement the parser (only if step 3 says you need one).
parsemust be pure: no network, noDate.now(), no randomness. Time comes fromctx.now. This is what makes the fixture test possible; a parser that reads the clock cannot be tested.- Implement
canParseas a structural check, and do not over-fit it. Game8's own pages differ in attribute quote style, soclass="a-table"would falsely reject half of them. - Get the domain rules right — they are in
CLAUDE.md§ Domain rules and they are where adapters actually go wrong:- All timestamps UTC ISO 8601.
- Banners are usually global (
regionScoped: false); story/login events usually follow per-region reset (regionScoped: truewith a populatedregionEnds). - An unstated end is
endsAt: null+endPrecision: "unknown". Never compute a plausible end from typical patch length. This is the failure mode that makes the product worthless.
5. Write the test. fixtures/<game>/<site>-events-<YYYY-MM-DD>.expected.json holds the exact
expected GachaEvent[]. Add the source to CASES in test/adapters/game8.test.ts; the shared
assertions (schema, determinism, no backwards intervals, 180-day cap, unique IDs) then apply for
free. Regenerate the expected file with bun run parse <id> <fixture> --json.
Fixture names matter: build-feed selects by <site>-* within the game directory, so a game
with two sources needs distinct site prefixes.
6. Verify. Run bun test and confirm it passes with no network. Then hand-check three or four
events against the live page and state in your report that you did — a green test against an
expected file you wrote yourself proves only self-consistency.
7. Register the adapter in src/ingest/adapters/index.ts and add its sources row.
Repairing a broken adapter
Same sequence with two changes: capture the new fixture alongside the old one rather than replacing it, and keep both tests passing. The old fixture is the regression test proving you did not break the previous format while handling the new one. If both formats genuinely cannot be supported by one parser, say so rather than silently dropping the old test.
Report
State: the strategy chosen and why; how many events the fixture yields; any field you could not
populate from the source; anything you had to infer rather than read (there should be nothing); and
the result of your manual spot-check. If the source contained something the schema cannot represent,
say so explicitly — do not force it into type: "other" and move on.