docs(skills): latency-forensics skill + ledger/model/flag/finish capture (last-few-days skillify) - #578
Merged
Merged
Conversation
… skill + ledger/model/flag/finish fixes Skillify backlog (5 HIGH items, from the wf_ed9a8ad2 discovery workflow, gap-checked): 1. NEW skill .claude/skills/worldos-latency-forensics — SDK duration_api_ms measurement method (true tool-exec ~1-4%, beats are generation-bound), quality-cost lever taxonomy (neutral: alwaysLoad/streaming/scene_context/prose-trim; trading: effort), REFUTED hypotheses (Haiku-helper, --tools, --fast). 2. worldos-dev SKILL.md: re-add the ⚠ Support-VM-lane callout (heavy sweeps, not local); ledger drift fix (canonical is scores_db.py -> scores_ledger.md, SCORECARD legacy); palette now 9-tool with finish() (finish=satisfied/gave_up=false vs give_up=blocked, #574); + DISCIPLINE: 'QA must exercise the flag' (run_duo ignored CLAWDND_LEAN_BEATS -> confounded A/Bs) and 'DM latency is reasoning not the GUI/harness'. 3. docs/MODEL-TIERING-STRATEGY.md: supersede the stale proposal with the MEASURED state (generation-bound; effort is the lever; ONE model/campaign, never switch mid-campaign=cache; Opus story 4.4-4.5 vs Sonnet 4.2). Model choice left OPEN (owner's call; models are options, not bolted-on); Haiku-helper REFUTED. 4. Ledger-drift banner on qa/SCORECARD.md (LEGACY -> scores_db.py) + qa/SCORING.md + qa/QA_TOOLS.md refs. Doc-only. The 5th HIGH item (verify-subagent-factual-claims) lands in the user-global verification-before-completion skill, separately.
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (6)
📝 WalkthroughWalkthroughThis PR consolidates WorldOS QA operational discipline, scoring infrastructure, and measured DM performance strategy across six documentation files. It redirects the scoring source-of-truth from legacy narrative to SQLite-backed ledger, introduces latency measurement methodology, updates model-tiering strategy based on measured findings, and refines the GUI playtester harness semantics for satisfaction-based gating. ChangesQA Operations & Scoring Infrastructure
DM Latency Forensics & Model Strategy
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Comment |
100yenadmin
added a commit
that referenced
this pull request
Jun 2, 2026
…rule (#13/#6) + REGRESSION-FORENSICS cross-link (#9) (#584) Adversarial re-review (post-VM-sweep, 3h later) graduated 3 backlog items to HIGH on new evidence: - #13 (LOW→HIGH): the scorer's DERIVED sat = 8-friction (crit=1⇒6) STRUCTURALLY can't clear G3 (≥7); the 2026-06-02 VM sweep had gave_up=false on all 5 but 4/5 DERIVED 5-6 → the low sat is a self-report-COVERAGE artifact, not a quality failure. Added the reading rule to worldos-dev (verify satisfaction_source; derived G3-miss = inconclusive) + soft caveat (finish() fires in the minority; 'self-reported' can be the Satisfaction:N/10 verdict line, not only finish()). - #6 (finish-it): new WorldOS-GUI-RUNBOOK 'Reading the sweep — honest satisfaction' section (finish vs give_up; budget=story-beats; spinner=progress; every persona MUST finish(satisfaction); PARTIAL≠product-RED). - #9 (MED→HIGH): cross-link qa/REGRESSION-FORENSICS.md from QA_TOOLS Evidence-Reading-Order (the 4.x-vs-2.x 'regression' is a surface+rubric artifact; was orphaned, no nav path). - Also fixed the residual SCORECARD ledger-drift in the GUI-RUNBOOK gate-sweep line. Doc-only. The 5 prior HIGH items (PR #578) were adversarially re-verified against a40beaf + the VM sweep: all sound, no contradictions (#579-582 were additive render/ + server.py SSE, no protected files touched). Co-authored-by: Eva <arncalso@gmail.com>
This was referenced Jun 3, 2026
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.
Captures the last-few-days workflows so a post-compaction agent finds them. 1 new skill (worldos-latency-forensics) + worldos-dev callout/ledger/palette/discipline updates + MODEL-TIERING measured-state rewrite (model choice left OPEN) + SCORECARD/SCORING/QA_TOOLS ledger-drift fixes. Doc-only; from the gap-checked skillify-discovery workflow.
Summary by CodeRabbit