Content
87%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.
This is a strong, lean command-reference skill: exact syntax for every command, executable examples, and no filler. The one weakness is the absence of any validation or confirmation guidance around the destructive unregister (and disable) operations, which both caps workflow clarity and leaves the riskiest action unguarded.
Suggestions
Add a verification step before destructive commands, e.g. "Before unregistering, run `/webhooks get <id>` to confirm the path and trigger count, and confirm with the user before `/webhooks unregister`."
Document the feedback loop for failed signature validation (e.g. what happens to a request whose HMAC check fails) in the Security section.
Note whether registration is idempotent or what happens when registering an id that already exists, to remove ambiguity around the register/unregister cycle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: a command table, copy-paste examples, a short list of what `get` shows, and a two-line security note. It never explains what webhooks or HMAC are, assumes Claude's competence, and every section adds information. Matches "Lean and efficient; assumes Claude's competence; every token earns its place"; the mild redundancy of the opening line restating the description is not enough to drop to 4. | 5 / 5 |
Actionability | Full slash-command syntax is given for every operation ("/webhooks register <id> <path> --secret <key>", "/webhooks get <id>", etc.) and the Examples block shows copy-paste-ready invocations covering all common cases including registering with a secret. Matches "Fully executable; copy-paste ready code or commands; specific examples cover the common cases". | 5 / 5 |
Workflow Clarity | Each individual command is unambiguous, but the skill includes a destructive operation — "/webhooks unregister <id>" removes a registration — with no validation or verification step (e.g. run `/webhooks get <id>` first or confirm before deleting). Per the judging guidelines, a destructive operation without validation caps workflow clarity at 3, and this cap takes precedence over the simple-skill exception. It is not a 2 because the command reference itself is coherent and well-sequenced. | 3 / 5 |
Progressive Disclosure | The body is under 50 lines, single-purpose, and needs no external references (none exist in the bundle: references/, scripts/, and assets/ are absent). It is organized into clear sections (Commands, Examples, Webhook Details, Security), which per the guidelines earns a 5 for a short, self-contained skill. | 5 / 5 |
Total | 18 / 20 Passed |