fix(skill): align with SPEC on deps, result fields, plan stdin#5
Merged
fix(skill): align with SPEC on deps, result fields, plan stdin#5
Conversation
Three SPEC-accuracy fixes to prevent agents from hitting CLI rejections: - **Dependencies:** call out that edges must be same-kind (task→task or epic→epic). task→epic and epic→task are rejected. task→task can cross epic boundaries. - **Result attachments:** result_path and result_summary are required together (single-line, max 120 chars). Previously the skill mentioned only result_path. - **JSON piping exception:** ergo plan requires a single JSON object on stdin and has no flags-only form — it's the exception to "prefer flags".
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Three SPEC-accuracy fixes in
.claude/skills/ergo/SKILL.mdto stop agents from hitting preventable CLI rejections:task→taskorepic→epic.task→epicandepic→taskare rejected by the CLI (per SPEC.md:73-74). Previously the skill said only "dependencies can cross epic boundaries," which is ambiguous about whether task↔epic is allowed (it isn't).result_pathandresult_summaryare required together (single-line, max 120 chars), per SPEC.md:109-110. Previously the skill mentioned onlyresult_path, so a literal agent would pass just--result-pathand get rejected.ergo planrequires a single JSON object on stdin and has no flags-only form (per SPEC.md:40-42). Previously the agent-rules table said "prefer flags over JSON piping" with no carve-out, which would leave an agent stuck on the one command that can't accept flags.Net: +3/-3 lines, no structural changes.
Test plan
references/SPEC.md(lines 73-74, 40-42, 109-110)plancommand help text againstergo --help🤖 Generated with Claude Code