refactor(skill): align SKILL.md with sandover (405→131 lines)#2
Merged
refactor(skill): align SKILL.md with sandover (405→131 lines)#2
Conversation
Cut CLI reference, shell compat table, state machine, anti-patterns, and troubleshooting — all derivable from `ergo --help` / `ergo quickstart`. Keep jamestjat-specific workflow: agent rules table, multi-agent coordination, and "land the plane" protocol. Tuned description via trigger eval: 100%/100%/100% accuracy/precision/recall on 20-query benchmark × 5 runs, up from 65%/100%/30% on the lean sandover-style description.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
.claude/skills/ergo/SKILL.mdto mirror the sandover ergo-feature-planning skill structure while preserving jamestjat workflow conventions.ergo --help/ergo quickstart.--helpcannot teach: Agent rules (7-row table), Multi-agent coordination (single-source-of-truth, race-safe claiming, unique agent identity), Landing the plane (phrase-triggered wrap-up with mandatorygit push).Description optimization
Tuned the frontmatter description via a 20-query trigger benchmark (10 should-trigger multi-commit/coordination/
.ergo/cases, 10 near-miss should-not-trigger cases like Linear, Taskfile, GitHub Projects, Claude Code's native TaskCreate).Benchmark ran 5 trials × 20 queries = 100 trials per candidate, on
claude-opus-4-6. The ALWAYS-leading phrasing with explicit command keywords and exclusion list achieved perfect triggering without regressing on near-misses.Test plan
ergoCLI installed🤖 Generated with Claude Code