with one click
codebase-blog
Use when: generating technical blogs from codebase-audit results
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Use when: generating technical blogs from codebase-audit results
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | codebase-blog |
| description | Use when: generating technical blogs from codebase-audit results |
| allowed-tools | Bash, Read, Grep, Glob, Write |
| triggers | ["codebase-blog","/codebase-blog","blog from audit","generate blog","technical blog"] |
Check your initial prompt. If it contains the literal string "Use the codebase-blog skill", then:
YOU ARE THE EXECUTOR. Follow these rules:
../../PATTERN.md relative to this SKILL.md, and follow it step by step.csa run, csa review, csa debate, or ANY csa command. You must perform the work DIRECTLY. Running any csa command causes infinite recursion.Only if you are the main agent (Claude Code / human user):
Generate a series of technical blog posts from completed codebase-audit results.
Each audited module gets a blog post explaining what it does, how it works, key
design decisions, and security considerations drawn from its audit report.
Blogs are generated bottom-up (leaf dependencies first) so that each post can reference and link to its dependency blogs, creating a cohesive reading path through the codebase architecture.
Requires a prior codebase-audit run -- this pattern consumes audit results, it
does not perform audits.
codebase-audit must have been completed (at least some modules with status generated)csa audit status --filter generated must return non-empty resultscsa run --sa-mode true --skill codebase-blog "Generate technical blogs for all audited modules in English"
Or with specific parameters:
csa run --sa-mode true --skill codebase-blog "Blog src/executor/ modules --language Chinese --style tutorial"
When operating under SA mode (e.g., dispatched by /sa or any autonomous workflow),
ALL csa invocations MUST include --sa-mode true. This includes csa run,
csa review, csa debate, and any other execution commands. Omitting --sa-mode
at root depth causes a hard error; passing false when the caller is in SA mode
breaks prompt-guard propagation.
csa audit status --filter generated returns audited modules.csa audit status --format json --order topo --filter generated -- filter to entries where blog_exists is false/null.${MIRROR_DIR} directory (default: ./drafts/blog/) mirroring source structure../drafts/security-audit/${path}.audit.md${BLOG_LANGUAGE} with ${BLOG_STYLE} conventions${MIRROR_DIR}/${path}.mdcsa audit update <file> --blog-path <blog_path>${MIRROR_DIR}/INDEX.md linking all blogs in topological order.This pattern is fully resumable. If interrupted:
csa audit status --format json --filter generated with blog_exists=false shows remaining work| Command | Effect |
|---|---|
/codebase-blog | Blog all audited modules (English, technical-deep-dive) |
/codebase-blog --language Chinese | Blog all audited modules in Chinese |
/codebase-blog src/executor/ --style tutorial | Tutorial-style blogs for executor modules |
/codebase-blog --resume | Continue a previously interrupted blog generation |
codebase-audit (must run first to produce audit reports)csa audit CLI (status, update subcommands with --blog-path, --format json, --order topo, --filter)codebase-audit (produces the audit reports this pattern consumes)${MIRROR_DIR} directory (default: ./drafts/blog/) with per-module blog posts and INDEX.md${MIRROR_DIR}.${BLOG_LANGUAGE} with style matching ${BLOG_STYLE}.--blog-path (csa audit status shows blog_exists=true for all processed modules).${MIRROR_DIR}/INDEX.md generated with links to all blog posts in topological order.Use when: full dev cycle branch->plan->implement->review->PR->merge
Use when: executing tasks via csa run/review/debate, session mgmt
Use when: iterative review-fix loop until csa review --diff is clean
Use when: running CSA-driven code review, independent model selection
Use when: three-layer manager-employee orchestration for delegation
Use when: legacy alias, redirects to dev2merge pipeline