@erclx/aitk 0.51.0 → 0.53.0

package/standards/readme.md

@@ -5,7 +5,7 @@ description: Readme voice, structure, and content conventions
 
 # Readme reference
 
-Applies to every `README.md`. The `## Voice` section states the voice for a repository's root README, so `prose.md` yields to it there. The yield covers voice alone. The punctuation bans, spelling rules, banned words, and formatting rules in `prose.md` stay in force, so the warmer register ships with the same hygiene: no em dashes, no semicolons, no buzzwords.
+Applies to every `README.md`. The `## Voice` section states the voice for a repository's root README, so `prose.md` yields to it there. The yield covers voice alone. The spelling rules and banned words in `prose.md` stay in force, as do the punctuation and formatting rules in `markdown.md`, so the warmer register ships with the same hygiene: no em dashes, no semicolons, no buzzwords.
 
 The reader is what changes. Reference prose serves someone who already committed to the project and is scanning for a fact. A root README meets someone deciding whether to commit at all, and it is often the only file they read.
 
@@ -15,7 +15,8 @@ Governs every `README.md`: voice, heading structure, required and optional secti
 
 Does not govern:
 
-- Punctuation, formatting, spelling, and banned words in README prose: `prose.md`, which yields the voice and keeps the rest
+- Spelling and banned words in README prose: `prose.md`, which yields the voice and keeps the rest
+- Punctuation and formatting in README prose: `markdown.md`, which yields nothing
 - Product scope and goals: `requirements.md`
 
 ## Voice

package/standards/skill.md

@@ -17,7 +17,8 @@ Does not govern:
 
 - Path-scoped coding rules, which load on a file match rather than on a request match: `rule.md`
 - Single-purpose chat prompts carrying no frontmatter, references, or scripts: `snippets.md`
-- Voice, punctuation, and formatting in a skill body: `prose.md`
+- Voice and word choice in a skill body: `prose.md`
+- Punctuation and formatting in a skill body: `markdown.md`
 - The transform from a branch name to a slug a skill carries in a filename: `slug.md`
 - The domain conventions a skill cites, each of which belongs to the standard that owns it
 

package/standards/standard.md

@@ -17,7 +17,8 @@ Governs each authored standard under `standards/`: its stated jurisdiction, succ
 
 Does not govern:
 
-- The voice, punctuation, and formatting a standard is written in: `prose.md`
+- The voice and word choice a standard is written in: `prose.md`
+- The punctuation and formatting a standard is written in: `markdown.md`
 - The shape of any artifact a standard governs, which is that standard's own subject
 
 ## What a working standard looks like

package/standards/versioning.md

@@ -16,7 +16,8 @@ Does not govern:
 - The format of a phase label, which is project-specific by the rule below
 - Task filenames and board layout: `tasks.md`
 - Commit subject, branch name, and pull request title format: `commit.md`, `branch.md`, and `pr.md`
-- Voice, punctuation, and formatting in any text carrying a label: `prose.md`
+- Voice and word choice in any text carrying a label: `prose.md`
+- Punctuation and formatting in any text carrying a label: `markdown.md`
 
 ## Phase labels
 

package/standards/wireframes.md

@@ -17,7 +17,8 @@ Does not govern:
 
 - Tokens, typography, spacing, and the rest of the visual system: `design.md`
 - The mechanism behind a surface: `context.md`
-- Voice, punctuation, and formatting in wireframe prose: `prose.md`
+- Voice and word choice in wireframe prose: `prose.md`
+- Punctuation and formatting in wireframe prose: `markdown.md`
 
 ## What a working wireframe looks like
 
@@ -74,7 +75,7 @@ Reference the context entry from the wireframe by path when a reader needs the m
 ## Maintenance
 
 - When a surface's layout or interaction changes, update its wireframe file in the same PR. A wireframe showing a defunct layout is worse than none.
-- The Behavior and Copy prose around an ASCII block is prose and follows `prose.md`. The fenced block itself is not, so a check scoped to prose is the wrong thing to rely on for what sits inside it.
+- The Behavior and Copy prose around an ASCII block is prose and follows `prose.md` and `markdown.md`. The fenced block itself is not, so a check scoped to prose is the wrong thing to rely on for what sits inside it.
 
 ## Template
 

package/tooling/claude/seeds/.claude/hooks/standards-audit.sh

@@ -19,6 +19,10 @@ esac
 # Read the closed-set word bans from the standard so the hook never carries a
 # second copy. Every "Do not use ... (`a`, `b`)" bullet contributes its
 # single-word backticked terms, which skips the multi-word and punctuation bans.
+#
+# The word bans sit in prose.md and the em-dash and semicolon bans in
+# markdown.md, so this parses the first and hardcodes the second. A "Do not use"
+# bullet added to markdown.md is parsed by nothing and enforces silently.
 standard="${CLAUDE_PROJECT_DIR:-.}/.claude/standards/prose.md"
 words=""
 if [ -f "$standard" ]; then
@@ -56,6 +60,6 @@ hits=$(awk -v words="$words" '
 
 [ -z "$hits" ] && exit 0
 
-msg=$(printf 'Standards-audit: prose.md violations in %s. Rewrite or restructure (do not lazy-swap).\n%s' "$file" "$hits")
+msg=$(printf 'Standards-audit: prose.md and markdown.md violations in %s. Rewrite or restructure (do not lazy-swap).\n%s' "$file" "$hits")
 
 jq -nc --arg msg "$msg" '{hookSpecificOutput:{hookEventName:"PostToolUse",additionalContext:$msg}}'