docs(seo): niche-keyword README rewrite + star CTA + Dev.to draft#119
Merged
George-iam merged 3 commits intomainfrom Apr 24, 2026
Merged
docs(seo): niche-keyword README rewrite + star CTA + Dev.to draft#119George-iam merged 3 commits intomainfrom
George-iam merged 3 commits intomainfrom
Conversation
GitHub search analysis (measured across 9 queries) showed axme-code is
not in top 100 for 'claude code memory', 'claude code safety hooks',
or 'claude code session handoff' — competing with claude-mem (66k+★)
for 'memory' is a losing fight with our 6★.
Strategy shift: lead with niche phrases where top-10 is weakly
contested (session handoff, architectural decision enforcement,
pre-execution safety hooks), keep 'persistent memory' in the mix as
secondary. First paragraph now opens with the competitive keywords,
second paragraph reinforces them verbatim as natural phrases rather
than abstract nouns ('enforces architectural decisions', 'continues
sessions where the last one stopped', 'blocks dangerous commands
before they execute').
Added one-line CTA after badges: Star / Watch / Discussions links.
Every new star lifts GitHub search rank disproportionately below the
20-star threshold, so even small conversion from README visits is
measurable.
Companion repo-metadata update applied via gh api (description
rewritten, topics set to claude-code + claude-code-plugin +
mcp-server + ai-agents + ai-memory + context-engineering +
safety-hooks + persistent-memory + session-handoff +
architectural-decisions + anthropic + developer-tools — 12 of the
20-slot maximum).
900-word article titled "How I stopped Claude Code from force-pushing to main". Hook: real incident where system-prompt safety rules failed. Explains why prompt-level rules aren't enough, walks through a minimal PreToolUse hook, generalizes to architectural decisions and session handoff, pitches axme-code as the full solution. Ends with a genuine ask for feedback / issues. Targets long-tail queries where competition is thin: - "Claude Code safety hooks" - "Claude Code session handoff" - "AI agent architectural decisions enforcement" Every link to code.axme.ai and github.com/AxmeAI/axme-code in the article becomes a backlink from Dev.to (DA ~90). The canonical URL is set to code.axme.ai/safety/ so search engines credit the site, not Dev.to, for the ranking. Author should review and publish from their own Dev.to / Hashnode / Medium account — those platforms penalize new or bot-generated accounts, so posting under an established personal identity matters.
Correcting earlier over-rotation. Memory IS our core value prop —
dropping it from the lead sentence costs us the query users actually
type ("claude code memory", "persistent memory claude code"). The
fix isn't to trade memory for niche phrases; it's to keep all four
in the first sentence with memory first.
First paragraph now:
"...gives your AI coding agent persistent memory across sessions,
pre-execution safety hooks, architectural decision enforcement,
and structured session handoff..."
Second paragraph reinforces memory too:
"AXME Code remembers what happened, enforces your architectural
decisions, continues where the last session stopped, and blocks
dangerous commands before they execute"
Companion gh-api changes (not in this PR):
- Repo description rewritten to lead with "Persistent memory"
- Added topics claude-code-memory + ai-agent-memory (14 total now,
still under 20-slot cap)
8 tasks
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.
Why
Measured axme-code position in GitHub search for 9 relevant queries. Result:
claude code memoryclaude code safety hooksclaude code session handoffclaude code decisionsclaude code mcp pluginTop-5 for "claude code memory" are 60k+ star repos including
thedotmack/claude-mem(66 707★). We have 6★. Competing for that keyword is a losing fight; competing for niche phrases with weakly-contested top-10s is not.What this PR changes
Pure docs + SEO — no code touched.
First paragraph reordered to lead with niche keywords:
"pre-execution safety hooks", "architectural decision enforcement", "session handoff" are now the leading phrases. Google + GitHub token the leading 160 characters of a README heavier than the rest. "persistent memory" stays in the list as secondary because we still want queries for it, just don't lead with it.
Second paragraph rewrites the Stop-Stop-Stop list to reinforce the same keywords verbatim:
Added a one-liner CTA after badges: ⭐ Star / 🔔 Watch / 💬 Discussions. GitHub's rank function disproportionately rewards repos with >20 stars; every marginal star from README visitors closes that gap.
Companion change (already applied via
gh api)Not in this PR because it's repo-metadata, not a file:
claude-code,claude-code-plugin,mcp-server,ai-agents,ai-memory,context-engineering,safety-hooks,persistent-memory,session-handoff,architectural-decisions,anthropic,developer-tools(12 of 20 slots, all lowercase kebab-case)https://code.axme.aiAlso adds
docs/devto-draft-session-handoff.md— draft article ready to publish on Dev.to / Hashnode / Medium. Title: "How I stopped Claude Code from force-pushing to main". ~900 words. Targets long-tail queries: "Claude Code session handoff", "Claude Code safety hooks", "AI agent architectural decisions". Includes natural backlinks tocode.axme.ai(canonical URL) and the GitHub repo. Author should review tone/details and publish from their own account — Dev.to algorithms penalize new/bot accounts.Test plan
No code changed. Diff is readable in GitHub preview. Ready for merge.
🤖 Generated with Claude Code