fast-review
Mandatory post-delegation gate that checks output completeness, verifies acceptance criteria compliance, flags regressions, and produces a PASS/FAIL verdict. Use when checking delegated work against acceptance criteria, running the post-delegation gate, validating agent output before acceptance, verifying a sub-agent completed its assignment, or running a post-delegation QA check.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It provides specific concrete actions, includes natural trigger terms with good variation coverage, explicitly addresses both what the skill does and when to use it, and occupies a clearly distinct niche in the multi-agent delegation workflow space.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'checks output completeness', 'verifies acceptance criteria compliance', 'flags regressions', and 'produces a PASS/FAIL verdict'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (checks output completeness, verifies acceptance criteria compliance, flags regressions, produces PASS/FAIL verdict) and 'when' with an explicit 'Use when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users/agents would use: 'post-delegation gate', 'acceptance criteria', 'delegated work', 'agent output', 'sub-agent', 'QA check', 'PASS/FAIL verdict'. Good coverage of variations including 'post-delegation QA check' and 'validating agent output before acceptance'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche: post-delegation quality gate for sub-agent work. The terms 'post-delegation gate', 'sub-agent', 'delegated work', and 'PASS/FAIL verdict' are highly distinctive and unlikely to conflict with general testing or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly defines a post-delegation review gate with explicit workflows, escalation paths, and anti-patterns. Its main weaknesses are the illustrative (rather than fully executable) code examples and the reference to a REFERENCE.md file that isn't provided in the bundle. The anti-patterns section adds valuable guardrails.
Suggestions
Provide the referenced REFERENCE.md file containing the full reviewer prompt template, or inline a minimal but complete version in the skill itself.
Make the runSubagent JS snippet more complete by showing how criteria, diff, and gate results are gathered/passed, or clarify that it's a schematic example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured using tables, bullet points, and minimal prose. It assumes Claude understands concepts like sub-agents, diffs, and acceptance criteria without explaining them. Every section earns its place. | 3 / 3 |
Actionability | Provides a concrete JS snippet for spawning the reviewer and a shell command for logging, plus a structured verdict format. However, the JS example is illustrative rather than fully executable (no imports, no variable definitions for criteria/diff), and the full reviewer prompt template is deferred to REFERENCE.md which is not provided. | 2 / 3 |
Workflow Clarity | The 4-step procedure is clearly sequenced with explicit validation checkpoints (verdict parsing, retry logic, escalation path). The handle-verdict table provides a clear feedback loop with retry counts and escalation. The hard gate for logging before proceeding is explicitly called out. | 3 / 3 |
Progressive Disclosure | The skill references REFERENCE.md for the full reviewer prompt template and team-lead-reference for dispute protocol, which is good structure. However, REFERENCE.md is not provided in the bundle, making it impossible to verify the reference exists. The skill itself is well-organized but the missing bundle file weakens confidence in the progressive disclosure. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
cc13aaf
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.