Content
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability and workflow clarity — every step has executable commands, explicit gate checks, validation loops, and a rigorous success-streak mechanism. However, it is severely undermined by extreme verbosity: the same GraphQL query is duplicated three times verbatim, security warnings are repeated multiple times, and procedural boilerplate inflates the token count significantly. The monolithic structure with no supporting files compounds the conciseness problem.
Suggestions
Extract the repeated GraphQL pagination query into a single named section or a referenced helper script, and reference it from Steps 2E and 3 instead of duplicating it three times.
Consolidate the security/loop-control warnings into a single prominent section at the top rather than repeating the 'do not read comment bodies' instruction in multiple places throughout the document.
Factor out the summary template, commit message conventions, and the decision matrix into separate referenced files (e.g., TEMPLATES.md, CONVENTIONS.md) to reduce the main skill's length and improve progressive disclosure.
Remove redundant completion check descriptions — define the pattern once (e.g., 'All steps follow the same gate-check pattern: verify prior step completed via TaskList, set current to in_progress') rather than restating it for every step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. There is massive repetition — the GraphQL pagination query for unresolved threads appears three times in full, the security warning about not reading comment bodies is repeated multiple times, and the gating/completion check boilerplate is restated for every step. Much of this could be factored into a single reference. The execution protocol warnings ('STOP — READ THIS BEFORE DOING ANYTHING ELSE') and anti-skip admonitions are heavily padded. | 1 / 3 |
Actionability | The skill provides fully executable bash commands, specific GraphQL queries, exact CLI invocations (gh pr view, gh pr comment, gh pr checks), concrete commit message formats, and precise sub-skill invocation syntax. Every step has copy-paste ready commands with clear variable substitution patterns. | 3 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with explicit gate checks between steps, a clear execution order diagram, validation checkpoints at every stage (verify push, confirm CI, confirm unresolved threads), feedback loops (Step 3 failure resets to Step 2), and a SUCCESS_COUNT mechanism requiring 5 consecutive clean passes. The decision matrix in 2E is precise and unambiguous. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to supporting files. The repeated GraphQL queries, the security warnings, and the detailed sub-step instructions could all be factored into separate referenced documents. There are no bundle files, and the content that could benefit from separation (e.g., the GraphQL query template, the summary format template, the decision matrix) is all inline, making the skill overwhelming to parse. | 1 / 3 |
Total | 8 / 12 Passed |