Content
68%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.
The body delivers highly actionable negotiation guidance with concrete phrasings, worked examples, and useful diagnostics backed by a well-organized one-level-deep reference file. Its weaknesses are token efficiency (author bio, affiliate links, repeated links, and duplicated passages) and the absence of an explicitly sequenced end-to-end workflow, since techniques are presented as a catalog rather than ordered stages.
Suggestions
Trim non-operational sections ("About the Author", affiliate-tagged "Further Reading") and replace the eight repeated "See: [references/techniques.md]" lines with a single well-placed pointer, removing duplicated passages such as the irrationality diagnosis that appears in both section 8 and "Handling Common Situations".
Add a short sequenced workflow section (e.g., prepare accusation audit -> open with tactical empathy/labeling -> ask calibrated questions -> pursue "That's right" -> Ackerman sequence -> close) so the techniques become an ordered process rather than a catalog.
Move the per-technique "Product applications" tables (or the deeper "Why it works" detail) into references/techniques.md so SKILL.md reads as a lean overview with clearly signaled one-level-deep references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The technique sections are dense and earn their tokens (copy patterns, application tables), but there is measurable padding: the "About the Author" bio and affiliate-tagged "Further Reading" links add nothing executable, the identical "See: [references/techniques.md]" link is repeated 8 times, and content is duplicated (the "ill-informed / constrained / hiding something" diagnosis appears in both section 8 and "Handling Common Situations"). Mostly efficient but could be tightened, matching anchor 3; anchor 2 would require several sections of unnecessary explanation, whereas ~85% of the body is genuinely operational. | 3 / 5 |
Actionability | For an instruction-only skill the guidance is fully executable: copy-paste-ready phrasings ("How am I supposed to do that?", "It seems like...", "Have you given up on [the project]?") and a worked numeric Ackerman example ("Target $120K: open discussion at $78K, move to $102K, $114K, final $120,350 + extra PTO"). Concrete conditionals ("They anchor with an extreme number -> 'How did you arrive at that figure?'") cover the common cases, matching anchor 5. | 5 / 5 |
Workflow Clarity | The eight numbered sections are a technique catalog, not a sequenced negotiation workflow; there is no explicit prep-to-close order of operations. Checkpoints do exist (the Quick Diagnostic table with "If No -> Action" and the Scoring feedback loop of rating and iterating to 10/10), but the sequence is only implicit, fitting anchor 3 ("sequence present but checkpoints missing or implicit") better than anchor 4's "clear sequence". | 3 / 5 |
Progressive Disclosure | The single bundle file (references/techniques.md, 432 lines, table of contents, no nested references) is real, one level deep, clearly signaled per section and summarized in the "Reference Files" section — good structure. It falls short of anchor 5 because the body itself carries substantial per-technique detail that overlaps the reference file and the per-section links are redundant (8 repeats of the same link), a minor organization gap consistent with anchor 4. | 4 / 5 |
Total | 15 / 20 Passed |