analyze-misfires
Identify skills injected where not needed, propose regex and description tightening
Draft X/Twitter announcement post (or thread) for the latest plugin release
> /plugin marketplace add iliaal/whetstone > /plugin install whetstone@iliaal-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
/announceContext preview
What this command does when you run it.
Draft X/Twitter announcement post (or thread) for the latest plugin release
name: announce description: Draft X/Twitter announcement post (or thread) for the latest plugin release argument-hint: "[optional: version to announce, defaults to current]"
Generate an announcement post for the latest whetstone plugin release. The account is X Premium — one long post usually covers a release; only thread when a second distinct theme justifies the visual pacing.
This command is the dedicated X drafter for whetstone releases. For other repos, other platforms, or non-release posts (benchmark drops, opinion takes, real-time engagement), use `/ia-promote <repo> <platform>` instead.
Before drafting, read these to anchor voice, platform constraints, and ethics:
When this command's inline guidance disagrees with those rules, the rules win — the rules are the canonical source, this command is the orchestration wrapper. Apply the `ia-writing` skill throughout for prose hygiene (no filler, no AI slop, no throat-clearing).
Also check `~/ai/promotion/announcement-matrix.md` for the whetstone row. If `Last announced` already equals the version being drafted, ask the user whether to skip, redraft anyway, or target a different version.
1. Read the current version from `plugins/whetstone/.claude-plugin/plugin.json` 2. Read CHANGELOG.md -- combine ALL entries newer than the matrix's `Last announced` version for X (from `~/ai/promotion/announcement-matrix.md`, read in Step 0) into one announcement. The announcement covers the full gap, not just the newest version: the matrix can lag several versions behind current, and every unannounced version's user-visible changes belong in this post. If `Last announced` already equals the current version, there is nothing new to announce (see Step 0). 3. Get the ai-skills repo version from its sync commit: `cd ~/ai/ai-skills && git log --oneline --grep '^sync: v' -1 && cd -` 4. Count components (read-only, no writes): `bash scripts/update-metadata.sh --dry-run`
X posts are marketing. Assume the reader is scrolling a busy feed — you have the first ~250 characters to earn a click-through. Craft them as a compelling hook that tells the reader what this release is about and why they should care. Everything past that is only read by readers who already opted in.
The account is X Premium (25,000 character limit per post), so most releases fit in one post. Thread only when a second distinct theme genuinely benefits from visual pacing, not to chunk content that belongs together.
**Target 1,500-2,500 chars for most releases.** Rich releases (10+ user-visible changes) condense into 3-5 top-impact bullets plus a link to the full CHANGELOG — do not list every change. Small releases (1-3 user-visible changes) fit in ~800-1,200 chars and skip the changelog link. Practical ceiling is 3,500 chars; beyond that you trade reader attention for completeness.
**Single post structure:**
1. **Opener (first ~250 chars, the feed preview — marketing copy that has to earn the click):**
2. **Body (the 3-5 top-impact bullets):**
3. **Full-changelog link with theme teaser** (rich releases only):
4. **Install commands:**
5. **Repo URL footer (standalone final line):**
**Thread fallback (only when justified):**
Split across multiple posts when the release has two or more clearly distinct themes that benefit from visual pacing in the feed — not because one post would be "too long." Each continuation post still gets the Premium character budget; don't chunk at 280.
Invoke the `ia-writing` skill in audit mode on the drafted post. The skill returns an AUDIT (tagged offenses), CORRECTED TEXT, and 5-dimension scores (Directness / Rhythm / Tr
A Claude Code plugin that makes AI coding agents follow engineering discipline. Plan before coding. Verify before claiming done. Find root cause before patching. Review before merge. Skills activate based on file type and task signals, not manual toggling.
Repo: iliaal/whetstone
Identify skills injected where not needed, propose regex and description tightening
Deep quality audit of all skills, agents, and commands for inconsistencies, gaps, duplication, and token waste
Analyze negative-signal sessions for a skill, identify failure patterns, propose and apply fixes
Eval all skills with sufficient data, rank by procedure-following score, identify candidates for optimization
Propose a skill revision and compare fresh executions under a frozen rubric
Prune stale entries from the whetstone sync decision log