verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
83
76%
Does it follow best practices?
Impact
92%
1.22xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/verification-before-completion/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively communicates when this skill should be triggered and its core purpose of requiring verification before success claims. However, it lacks specificity about what concrete verification actions should be taken (e.g., running tests, linting, building) and could include more natural trigger terms. The description reads more as an internal behavioral rule for Claude than a traditional skill description.
Suggestions
Add specific concrete verification actions like 'run tests, check linting, build project, verify type checks' instead of the generic 'running verification commands'.
Include more natural trigger terms users might say such as 'done', 'finished', 'ready to merge', 'all tests pass', 'ship it', 'looks good'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (verification before claiming completion) and some actions ('running verification commands and confirming output'), but doesn't list specific concrete actions like 'run tests', 'check linting', 'build project', or 'run type checks'. | 2 / 3 |
Completeness | Clearly answers both what ('running verification commands and confirming output before making success claims') and when ('when about to claim work is complete, fixed, or passing, before committing or creating PRs'). The 'Use when' clause is explicit and detailed. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'complete', 'fixed', 'passing', 'committing', 'creating PRs', but misses natural user phrases like 'done', 'finished', 'ready to merge', 'tests pass', 'ship it'. The terms are more about when Claude should self-trigger rather than what users would say. | 2 / 3 |
Distinctiveness Conflict Risk | This skill has a very clear and distinct niche — it's specifically about verification discipline before claiming completion. It's unlikely to conflict with other skills since it targets a behavioral pattern (evidence before assertions) rather than a domain of work. | 3 / 3 |
Total | 10 / 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 strong behavioral/process skill with excellent actionability and workflow clarity. The Gate Function and Common Failures table provide concrete, unambiguous guidance. The main weakness is moderate verbosity - the skill repeats its core message through multiple framings (Red Flags, Rationalization Prevention, When To Apply, The Bottom Line) which, while reinforcing the point, consumes tokens that could be saved.
Suggestions
Consolidate the 'Red Flags', 'Rationalization Prevention', and 'The Bottom Line' sections into a single compact section to reduce redundancy and save tokens.
Consider moving the 'Why This Matters' section (failure memories) to a separate reference file, as the behavioral guidance stands on its own without the motivational context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but has some redundancy - the 'Rationalization Prevention' table largely repeats the 'Red Flags' section, and the motivational framing ('This is non-negotiable', 'lying, not verifying') adds tokens without adding actionable information. The tables are well-structured but some content could be tightened. | 2 / 3 |
Actionability | The Gate Function provides a clear, concrete 5-step process. The 'Common Failures' table maps specific claims to specific required evidence. The Key Patterns section shows exact verification patterns with concrete examples of correct vs incorrect behavior, making it immediately actionable. | 3 / 3 |
Workflow Clarity | The Gate Function is a clear sequential workflow with an explicit validation checkpoint (step 4) and a feedback loop (if NO: state actual status). The Key Patterns section provides specific verification workflows for different scenarios including the red-green TDD cycle with explicit revert-and-verify steps. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's somewhat long for a single file with no references to external resources. The 'Why This Matters' section with failure memories and the extensive 'When To Apply' section could potentially be trimmed or moved to a separate file, as the core skill is well-captured in the first half. | 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
- obra/superpowers
- Commit
6efe32c
- 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.