feat: add migration benchmarking + terminal-forward README#2
Merged
Conversation
Add an optional, opt-in benchmarking capability that quantifies a migration
with measured evidence instead of assertions.
Skill changes:
- Ask once in Phase 0 whether the user wants pre/post benchmark stats in the
evidence report; capturing the baseline later is impossible, so it is gated
up front.
- Three-arm methodology wired into the existing phase boundaries:
- Arm A (baseline: old model + old prompts) captured in Phase 0, pre-edit
- Arm B (naive swap: new model + old prompts) captured mid Phase 4, after
runtime edits but before prompt tuning -- the honest raw-model control
- Arm C (new model + enhanced system) captured in Phase 5
- New references/benchmarking.md: dimensions (quality, output-contract, tool
calling, latency, cost, safety, robustness), composite scoring, honesty
rules, and leaderboard format.
- Phase 6 report gains an optional Benchmark Results section; anti-patterns and
the validation checklist updated; validate_skill.py now requires the new doc.
- examples/example-output.md shows a filled three-arm leaderboard (clearly
labelled illustrative).
README:
- Replace the bland Problem/Solution prose with a terminal-style hero session
contrasting the naive find/replace swap with the ModelPort migration.
- New "Benchmark your migration" section with an illustrative leaderboard and a
link to the methodology; benchmark added to the feature table, why-teams
list, expected-output list, repo structure, and roadmap.
All benchmark numbers in docs are illustrative and labelled as such; latency and
cost are described as measured-not-assumed. validate_skill.py passes and
markdownlint is clean across all 25 markdown files.
The borderless hero session had unequal prefix padding, so the inline comment markers and the ✓/x columns drifted out of alignment when rendered. Pad to fixed columns: comment markers at col 32, the three status columns at 2 / 26 / 48.
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.
What
Adds an optional migration benchmarking capability to the skill and gives the README a terminal-forward refresh.
Benchmarking feature
Opt-in, asked once in Phase 0. Measures the migration with three arms on the same eval set so the model delta and the skill's value are attributed separately:
references/benchmarking.md— dimensions (quality, output-contract, tool-calling, latency, cost, safety, robustness), composite scoring, honesty rules, leaderboard format.SKILL.md— opt-in input, per-phase capture points, optional Benchmark Results report section, new anti-patterns, checklist item.examples/example-output.md— filled three-arm leaderboard (labelled illustrative).scripts/validate_skill.py— requires the new doc.README
Honesty note
All benchmark numbers in the docs are illustrative and labelled as such. The pattern shown (naive swap regresses output-contract/tool-calling, enhanced arm recovers them) is the documented effect of literal instruction following + retokenization; latency and cost are described as measured-not-assumed.
Validation
python3 scripts/validate_skill.py .→ validmarkdownlint-cli2 "**/*.md"→ 0 errors (25 files)