Content
96%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
An exemplar instruction-skill body: concrete commands, explicit validation checkpoints with feedback loops, and lean prose that assumes competence. The only gap is that the referenced bundle files could not be verified as present in the package.
Suggestions
Ship the referenced bundle files (scripts/post_linter.py, scripts/format_picker.py, scripts/repurpose_splitter.py, the four references/*.md, and the two assets/*.md) alongside SKILL.md so the signaled navigation actually resolves.
Confirm each body link target exists at the stated path before release; a broken reference undermines the otherwise strong progressive-disclosure structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient throughout — it assumes Claude's competence, never explains what LinkedIn or a hook is, and every line (workflow, rules, scripts table, references) earns its place, matching the 5 anchor. | 5 / 5 |
Actionability | Fully executable copy-paste commands with real flags (e.g. 'python3 scripts/post_linter.py --input draft.md --has-image --output human') plus documented exit codes, covering the common cases per the 5 anchor. | 5 / 5 |
Workflow Clarity | A clearly numbered 5-step workflow with explicit validation checkpoints (exit 0 SHIP / 2 REVISE / 3 REWRITE) and a feedback loop ('Two passes is normal; the stop condition is exit 0'), matching the 5 anchor for sequenced steps with error-recovery loops. | 5 / 5 |
Progressive Disclosure | Well-signaled one-level-deep references with one-line descriptions and a scripts table give clear navigation, but the referenced bundle files (scripts/*.py, references/*.md, assets/*.md) are not present in the bundle to verify, leaving a minor gap below the 5 anchor. | 4 / 5 |
Total | 19 / 20 Passed |