refactor(core-skills): flatten 7 skills by inlining workflow.md#2077
Merged
refactor(core-skills): flatten 7 skills by inlining workflow.md#2077
Conversation
🤖 Augment PR SummarySummary: This PR flattens several core skills by embedding their former Changes:
Technical Notes: This follows the same “flattened skill” pattern used elsewhere (e.g., advanced-elicitation), aiming for no functional/behavioral change while simplifying packaging and reducing cross-file indirection. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| - **Empty `phase` = anytime** — Universal tools work regardless of workflow state | ||
| - **Numbered phases indicate sequence** — Phases like `1-discover` → `2-define` → `3-build` → `4-ship` flow in order (naming varies by module) | ||
| - **Phase with no Required Steps** - If an entire phase has no required, true items, the entire phase is optional. If it is sequentially before another phase, it can be recommended, but always be clear with the use what the true next required item is. |
There was a problem hiding this comment.
This sentence reads like a typo: "be clear with the use" (likely "user"), which could make the routing rule ambiguous for the agent.
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
| ### Step 3: Execute Sharding | ||
|
|
||
| - Inform user that sharding is beginning | ||
| - Execute command: `npx @kayvan/markdown-tree-parser explode [source-document] [destination-folder]` |
There was a problem hiding this comment.
Consider clarifying how to handle paths with spaces when forming this command (e.g., quoting [source-document]/[destination-folder]), otherwise copy/paste execution can fail on common inputs.
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
…SKILL.md Inline workflow.md content directly into SKILL.md for: editorial-review-prose, editorial-review-structure, help, index-docs, review-adversarial-general, review-edge-case-hunter, and shard-doc. Deletes the now-redundant workflow.md files. No behavioral change — same pattern as advanced-elicitation in PR #2076. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
alexeyv
force-pushed
the
flatten-core-skills
branch
from
18471cc to
f100d6f
Compare
📝 WalkthroughWalkthroughThis PR consolidates workflow specifications across seven core skills by moving comprehensive procedural details from separate Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (3)
src/core-skills/bmad-shard-doc/SKILL.md (1)
76-93: Use level-3 headings instead of####in workflow sections.The subsection headers under Step 6 should avoid level-4 headings to stay consistent with project formatting conventions.
✍️ Suggested markdown change
-#### If user selects `d` (delete) +### If user selects `d` (delete) ... -#### If user selects `m` (move) +### If user selects `m` (move) ... -#### If user selects `k` (keep) +### If user selects `k` (keep)As per coding guidelines, docs-style conventions for these skill/workflow instructions specify to avoid
####.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/core-skills/bmad-shard-doc/SKILL.md` around lines 76 - 93, Replace the level-4 subsection headers under Step 6 with level-3 headers: change "#### If user selects `d` (delete)", "#### If user selects `m` (move)" and "#### If user selects `k` (keep)" to "### If user selects `d` (delete)", "### If user selects `m` (move)" and "### If user selects `k` (keep)"; ensure the surrounding workflow text (delete/move/keep steps and examples such as the default archive path) remains unchanged and that heading levels are consistent with the rest of SKILL.md.src/core-skills/bmad-review-adversarial-general/SKILL.md (1)
27-37: Clarify findings threshold behavior (>=10vs0)The contract is inconsistent: Line 27 requires at least ten issues, but Line 36 only halts on zero. Please define behavior for
1..9findings (e.g., re-analyze once, then return best-effort with rationale).Proposed wording adjustment
- Review with extreme skepticism — assume problems exist. Find at least ten issues to fix or improve in the provided content. + Review with extreme skepticism — assume problems exist. Target at least ten substantive issues to fix or improve in the provided content. - - HALT if zero findings — this is suspicious, re-analyze or ask for guidance + - If findings < 10, re-analyze once for missed issues; if still < 10, return findings with a brief note explaining constraints + - HALT if zero findings after re-analysis; ask for guidance🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/core-skills/bmad-review-adversarial-general/SKILL.md` around lines 27 - 37, The SKILL.md contract is inconsistent about findings thresholds: "Step 3: Present Findings" requires at least ten issues but "HALT CONDITIONS" only halts on zero; update the text for Step 3 and HALT CONDITIONS to define explicit behavior for 1..9 findings (e.g., attempt one re-analysis, then return a best-effort list with a rationale), change the "at least ten" requirement to a clear threshold statement (>=10) and add a new clause in HALT CONDITIONS that describes re-analysis behavior and the required rationale when fewer than ten findings are produced; modify the headings or sentences around "Step 3: Present Findings" and "HALT CONDITIONS" so they reference the same numeric rule and include the re-analysis and rationale steps.src/core-skills/bmad-review-edge-case-hunter/SKILL.md (1)
27-27: Avoid duplicating the HALT payload in two places.Line 27 and Line 67 repeat the same JSON literal; this can drift over time. Prefer one canonical definition (e.g., keep full payload in HALT CONDITIONS and reference it from Step 1).
Also applies to: 67-67
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/core-skills/bmad-review-edge-case-hunter/SKILL.md` at line 27, The HALT JSON payload is duplicated in Step 1 and again in HALT CONDITIONS; remove the copy in Step 1 and replace it with a reference to the canonical HALT payload declared under "HALT CONDITIONS" (keep the full JSON only once under HALT CONDITIONS and reference it from Step 1 by name, e.g., "see HALT CONDITIONS canonical payload: [HALT JSON]"). Update any mention in Step 1 to clearly point to the HALT CONDITIONS definition so the single source of truth is the payload under HALT CONDITIONS.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/core-skills/bmad-review-adversarial-general/SKILL.md`:
- Line 10: The role description under the "**Your Role:**" header contains a
personal-insult phrase ("clueless weasel") that conflicts with the stated
requirement for a professional, non-personal-attacks tone; replace that phrase
in SKILL.md (the "**Your Role:**" section) with adversarial but non-insulting
wording such as "a careless or overconfident submitter" or "a submitter prone to
sloppy work," preserving the cynical, skeptical reviewer stance and the rest of
the sentence structure and instructions.
---
Nitpick comments:
In `@src/core-skills/bmad-review-adversarial-general/SKILL.md`:
- Around line 27-37: The SKILL.md contract is inconsistent about findings
thresholds: "Step 3: Present Findings" requires at least ten issues but "HALT
CONDITIONS" only halts on zero; update the text for Step 3 and HALT CONDITIONS
to define explicit behavior for 1..9 findings (e.g., attempt one re-analysis,
then return a best-effort list with a rationale), change the "at least ten"
requirement to a clear threshold statement (>=10) and add a new clause in HALT
CONDITIONS that describes re-analysis behavior and the required rationale when
fewer than ten findings are produced; modify the headings or sentences around
"Step 3: Present Findings" and "HALT CONDITIONS" so they reference the same
numeric rule and include the re-analysis and rationale steps.
In `@src/core-skills/bmad-review-edge-case-hunter/SKILL.md`:
- Line 27: The HALT JSON payload is duplicated in Step 1 and again in HALT
CONDITIONS; remove the copy in Step 1 and replace it with a reference to the
canonical HALT payload declared under "HALT CONDITIONS" (keep the full JSON only
once under HALT CONDITIONS and reference it from Step 1 by name, e.g., "see HALT
CONDITIONS canonical payload: [HALT JSON]"). Update any mention in Step 1 to
clearly point to the HALT CONDITIONS definition so the single source of truth is
the payload under HALT CONDITIONS.
In `@src/core-skills/bmad-shard-doc/SKILL.md`:
- Around line 76-93: Replace the level-4 subsection headers under Step 6 with
level-3 headers: change "#### If user selects `d` (delete)", "#### If user
selects `m` (move)" and "#### If user selects `k` (keep)" to "### If user
selects `d` (delete)", "### If user selects `m` (move)" and "### If user selects
`k` (keep)"; ensure the surrounding workflow text (delete/move/keep steps and
examples such as the default archive path) remains unchanged and that heading
levels are consistent with the rest of SKILL.md.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 8a6155db-f9d4-4692-af76-b9bda14182fe
📒 Files selected for processing (14)
src/core-skills/bmad-editorial-review-prose/SKILL.mdsrc/core-skills/bmad-editorial-review-prose/workflow.mdsrc/core-skills/bmad-editorial-review-structure/SKILL.mdsrc/core-skills/bmad-editorial-review-structure/workflow.mdsrc/core-skills/bmad-help/SKILL.mdsrc/core-skills/bmad-help/workflow.mdsrc/core-skills/bmad-index-docs/SKILL.mdsrc/core-skills/bmad-index-docs/workflow.mdsrc/core-skills/bmad-review-adversarial-general/SKILL.mdsrc/core-skills/bmad-review-adversarial-general/workflow.mdsrc/core-skills/bmad-review-edge-case-hunter/SKILL.mdsrc/core-skills/bmad-review-edge-case-hunter/workflow.mdsrc/core-skills/bmad-shard-doc/SKILL.mdsrc/core-skills/bmad-shard-doc/workflow.md
💤 Files with no reviewable changes (7)
- src/core-skills/bmad-review-adversarial-general/workflow.md
- src/core-skills/bmad-index-docs/workflow.md
- src/core-skills/bmad-editorial-review-prose/workflow.md
- src/core-skills/bmad-help/workflow.md
- src/core-skills/bmad-editorial-review-structure/workflow.md
- src/core-skills/bmad-shard-doc/workflow.md
- src/core-skills/bmad-review-edge-case-hunter/workflow.md
|
|
||
| **Goal:** Cynically review content and produce findings. | ||
|
|
||
| **Your Role:** You are a cynical, jaded reviewer with zero patience for sloppy work. The content was submitted by a clueless weasel and you expect to find problems. Be skeptical of everything. Look for what's missing, not just what's wrong. Use a precise, professional tone — no profanity or personal attacks. |
There was a problem hiding this comment.
Remove contradictory/insulting persona wording
“submitted by a clueless weasel” conflicts with the same line’s “professional tone” and “no personal attacks.” Keep the adversarial stance, but remove personal-insult language.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/core-skills/bmad-review-adversarial-general/SKILL.md` at line 10, The
role description under the "**Your Role:**" header contains a personal-insult
phrase ("clueless weasel") that conflicts with the stated requirement for a
professional, non-personal-attacks tone; replace that phrase in SKILL.md (the
"**Your Role:**" section) with adversarial but non-insulting wording such as "a
careless or overconfident submitter" or "a submitter prone to sloppy work,"
preserving the cynical, skeptical reviewer stance and the rest of the sentence
structure and instructions.
This was referenced Mar 25, 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.
Summary
workflow.mdcontent directly intoSKILL.mdfor 7 core skills: editorial-review-prose, editorial-review-structure, help, index-docs, review-adversarial-general, review-edge-case-hunter, and shard-docworkflow.mdfilesTest plan
npm run qualitypasses (238 tests, lint, markdown lint, format all green)🤖 Generated with Claude Code