slack-qa-investigate
Investigate and answer repository questions in read-only mode. Use when asked for research-backed answers that require codebase and documentation investigation without making file changes.
Install with Tessl CLI
npx tessl i github:warpdotdev/oz-skills --skill slack-qa-investigate72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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.
This description has good structure with explicit 'Use when' guidance and clear differentiation through the read-only constraint. However, it could benefit from more specific concrete actions and additional natural trigger terms that users would actually say when needing codebase exploration help.
Suggestions
Add specific concrete actions like 'search files, trace function calls, analyze dependencies, find usage patterns' to improve specificity.
Include more natural trigger terms users would say such as 'explore code', 'understand the codebase', 'find where X is defined', 'how does this work'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (repository questions, read-only mode) and some actions (investigate, answer, research-backed answers, codebase and documentation investigation), but lacks specific concrete actions like 'search files', 'analyze dependencies', or 'trace function calls'. | 2 / 3 |
Completeness | Clearly answers both what ('Investigate and answer repository questions in read-only mode') and when ('Use when asked for research-backed answers that require codebase and documentation investigation without making file changes') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'research-backed answers', 'codebase', 'documentation investigation', but misses common natural variations users might say like 'explore code', 'find where', 'how does X work', 'understand the codebase', or 'code search'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'read-only mode' and 'without making file changes' constraints create a clear niche that distinguishes this from code editing or modification skills. The focus on investigation/research further differentiates it. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides clear behavioral guidance for a read-only Q&A investigation role with good workflow structure. However, it lacks concrete examples (specific grep commands, citation formats, sample investigation outputs) and has some redundancy between the read-only mode section and prohibited actions. The content tells Claude what to do but doesn't show how with executable specificity.
Suggestions
Add concrete examples of investigation commands: specific grep patterns, semantic search queries, or file glob patterns that demonstrate the investigation process
Include a sample answer format showing how to properly cite files/lines (e.g., 'Found in `src/auth/login.ts:45-52`: ...')
Consolidate the 'Read-Only Mode (STRICT)' and 'Prohibited Actions' sections to eliminate redundancy about not modifying files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary elaboration. Phrases like 'Your role is to thoroughly investigate' and repeated emphasis on read-only mode across multiple sections add bulk. The principles could be more condensed. | 2 / 3 |
Actionability | Provides clear guidance on what to do and not do, but lacks concrete executable examples. No specific command examples for 'safe shell commands', no grep patterns, no demonstration of how to cite files/lines. Guidance is directional rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The 5-step investigation process is clearly sequenced and logical. For a read-only research skill, validation checkpoints are less critical since no destructive operations occur. The workflow from understanding to synthesis is unambiguous. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear section headers, but everything is in one file with no references to external docs. For a skill of this size (~60 lines), this is acceptable, but the 'Prohibited Actions' section partially duplicates 'Read-Only Mode' content. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 13 / 16 Passed | |
- 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.