docs(author): add strategy-selection reference with empirical contract ladder#1810
Merged
Merged
Conversation
…t ladder Companion deep reference for the SKILL.md strategy gate (#1809): - New `references/strategy-selection.md` with contract-based ladder model, empirical fixes/adapter-year data (837 adapters / 30-day window), Pattern A judgment rules from `api_candidates` verdicts, and reference cases (booking #1680, Twitter GraphQL, xhs signed URL, weread-official). - Cross-link from SKILL.md inline strategy gate to the deep reference, plus one-line empirical hook ("PAGE_FETCH/INTERCEPT 7-8x PUBLIC_API fix rate"). - coverage-matrix.md: Strategy row renamed to 6-enum (PUBLIC_API / COOKIE_API / UI_SELECTOR / DOM_STATE / PAGE_FETCH / INTERCEPT) with fixes/adapter-year on each entry. - site-recon.md: Pattern A note that hit alone is not a `PAGE_FETCH` signal — must check `api_candidates` verdicts (booking #1680 reference).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Step 4 of the Network/API-first design rework (companion to #1809). Adds a deep reference for the strategy gate so authors can justify the rule with empirical evidence, not just the inline SKILL.md prescription.
New
references/strategy-selection.md:analyzeapi_candidates[]verdicts into strategy note evidenceSKILL.mdinline strategy gate gets a one-line empirical hook + cross-linkcoverage-matrix.mdauth/strategy row renamed to 6-enum with fixes/adapter-year on eachsite-recon.mdPattern A annotated: Pattern A ≠ PAGE_FETCH; must checkapi_candidatesverdictsWhy this matters
After #1809, agents have the strategy enum + forced note. But the inline ladder ordering ("PUBLIC_API → COOKIE_API → ...") risks reading as "upper is better", which the step-3 sampling data does not support. This reference makes the contract model and empirical numbers visible, so authors don't over-invest in PAGE_FETCH/INTERCEPT.
Test plan
npm run docs:buildclean