th-blogpost
Use for any work on a blog post — deep editorial review for publication readiness (narrative, structure, scannability, factual risk, tone) or mechanical publish-hardening (frontmatter normalization, MD/MDX safety fixes, structural scaffolding, asset hygiene). Triggers: "review my blog post", "edit this post", "is this post ready to publish", "format this post for the blog", "fix the frontmatter", "make this MDX build".
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- th-blogpost
- metadata
- { "owner": "tze", "status": "active", "authors": [ "tze", "Claude Fable 5" ], "last_reviewed": "2026-07-19" }
- description
- Use for any work on a blog post — deep editorial review for publication readiness (narrative, structure, scannability, factual risk, tone) or mechanical publish-hardening (frontmatter normalization, MD/MDX safety fixes, structural scaffolding, asset hygiene). Triggers: "review my blog post", "edit this post", "is this post ready to publish", "format this post for the blog", "fix the frontmatter", "make this MDX build".
02 资源文件 2
- 参考文档evo-skill-manifest.yaml12 B
- 参考文档workflow.md1.2 KB
03 SKILL.md 正文
TH Blogpost
Superskill router for blog-post work. Two subskills live under subskills/,
each a complete skill package, discovered lazily — load at most one
subskill body per task.
The split is editorial judgment vs. mechanical pipeline: the editor changes nothing silently and reports findings; the formatter changes files but exercises minimal editorial judgment.
Routing table
| Task intent | Subskill | Typical trigger |
|---|---|---|
| Editorial review for publication readiness: narrative, structure, scannability, factual risk, tone, reader usefulness. Findings only — no silent rewrites. | subskills/blogpost-editor/SKILL.md | "review/edit my post", "is this ready to publish", "critique this draft" |
| Publish-hardening: frontmatter normalization, MD/MDX safety fixes, structural scaffolding, asset hygiene. Preserves the author's voice and meaning. | subskills/blogpost-formatter/SKILL.md | "format this for the blog", "fix the frontmatter", "make this build/render" |
Routing rules
- Judgment vs. mechanics: "is the writing good / ready" → editor; "make it build / conform" → formatter. A full publish pass runs editor first, then formatter — as two sequential subskill loads, not one merged pass.
- Fallback: writing a post from scratch or non-blog documentation fits neither row — draft with general writing guidance, then return here for review and hardening.
Discover subskills
The routing table above is the primary index. Verify frontmatter only if the table seems stale:
PKG="$(dirname "<absolute-path-to-this-SKILL.md>")"
rg -n "^name:|^description:" "$PKG"/subskills/*/SKILL.md
04 同仓库更多 Skills
user-run
Use when a step needs privileges this session lacks (docker, sudo, another user's checkout or secrets, host access) and the owner must run it as tze. Writes a reviewable /home/orca/.tmp/<slug>/run.sh that impersonates tze (USER_TO_IMPERSONATE overrides), tees timestamped logs plus latest.log and collects artifacts there; Claude presents it with a risk and time brief, then continues from the logs. Triggers: "I'll run it for you", "permission denied on docker.sock", "needs sudo", "sudo: a password is required", "run as tze", "/user-run".
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies