CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

jbaruch/blog-writer

Write and revise developer blog posts or run a humanizer / humanization pass on existing drafts using the AI anti-pattern catalog, structural audits, and reusable personal and explicitly selected corporate writing identities.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

blog-writer-script-location.mdrules/

alwaysApply:
No
applyTo:
skills/**/*.md — when a skill or reference invokes a blog-writer script

Blog-Writer Script Location

Scope

  • Authority-of-record for blog-writer's scoped skill lookup under coding-policy: script-delegation Scoped Plugin Contracts
  • Loaders: blog-writer, cfp-abstract, create-personal-identity, create-corporate-identity
  • Files that invoke scripts: skills/blog-writer/SKILL.md and the shared references sweep-review.md, identity-storage.md, identity-composition.md, catalog-refresh.md under skills/blog-writer/references/

Co-Shipped Targets

  • Every target lives in skills/blog-writer/
  • sweep.py, check-shape-convergence.sh, record-post-shape.sh
  • check-catalog-version.py, fetch-signs-of-ai-writing.sh
  • setup-identity-root.py, discover-identities.py, resolve-identities.py, configure-identities.py

Lookup Contract

  • Input: the base directory of the skill that loaded the file
  • <blog-writer-dir> resolves to that directory when the loader is blog-writer
  • For any other loader it resolves to the sibling tessl__blog-writer directory
  • Each shared reference defines <blog-writer-dir> before its first command
  • Every command names its interpreter, bash or python3
  • Every command names one target above under <blog-writer-dir>/
  • Each target's input/output contract is its top-of-file header
  • resolve-identities.py and configure-identities.py document theirs in skills/blog-writer/references/identity-composition.md instead
  • The lookup grants no runtime authority and waives no check a target performs

Regression Coverage

  • skills/blog-writer/tests/test_script_location.sh checks each command names a listed, existing target
  • It checks each file defines the name above its first command
  • It checks no command spells the consumer path
  • In a simulated install it resolves blog-writer to its own base directory
  • It resolves each other loader to the sibling tessl__blog-writer directory
  • It parses every target the lookup reaches

README.md

tile.json