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.

Quality

62%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/slack-qa-investigate/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a competent behavioral skill that clearly defines read-only constraints and investigation principles. Its main weaknesses are moderate verbosity (some principles restate what Claude would naturally do) and lack of concrete, executable examples of investigation commands or patterns. The prohibited actions section effectively reinforces boundaries but partially duplicates the read-only mode section.

Suggestions

Add concrete examples of investigation commands (e.g., specific grep patterns, glob patterns, or shell commands that are safe to use) to improve actionability.

Consolidate the 'Read-Only Mode (STRICT)' and 'Prohibited Actions' sections to reduce redundancy and improve conciseness.

Add a brief example of a well-structured answer showing file/line citations to make the 'Answer Quality' section more actionable.

Dimension	Reasoning	Score
Conciseness	The content is reasonably structured but includes some unnecessary elaboration. Phrases like 'Your role is to thoroughly investigate questions and provide accurate, well-supported answers' and some of the bullet points explain behaviors Claude would naturally follow. The prohibited actions section has some redundancy with the read-only mode section.	2 / 3
Actionability	The skill provides clear behavioral guidelines and specific tool names to avoid (create_file, edit_files), but lacks concrete examples of actual commands to use for investigation (e.g., specific grep patterns, semantic search syntax). The investigation process is described at a high level without executable specifics.	2 / 3
Workflow Clarity	The 5-step investigation process is clearly sequenced and logical, but lacks validation checkpoints or feedback loops. There's no guidance on what to do if initial searches yield nothing, or how to verify that findings are correct before synthesizing an answer.	2 / 3
Progressive Disclosure	For a skill of this size and scope (behavioral guidance, single-purpose), the content is well-organized into clear sections with logical groupings. No external references are needed, and the sections are appropriately structured with headers and bullet points for easy scanning.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 has a solid structure with an explicit 'Use when' clause and a clear differentiator (read-only mode), which helps with completeness and some distinctiveness. However, it lacks specific concrete actions beyond the general 'investigate and answer' and could benefit from more natural trigger terms that users would actually say when needing this skill.

Suggestions

Add specific concrete actions like 'trace code paths, search for references, analyze architecture, explain module relationships' to improve specificity.

Include natural trigger terms users would say, such as 'explain how X works', 'find where Y is defined', 'understand the codebase', 'search the repo', or 'code exploration'.

Dimension	Reasoning	Score
Specificity	Names the domain (repository investigation, read-only mode) and some actions (investigate, answer questions, codebase/documentation investigation), but doesn't list multiple specific concrete actions like 'search code references, trace function calls, analyze dependencies'.	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 an explicit 'Use when' clause and clear trigger conditions.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'research-backed answers', 'codebase', 'documentation investigation', and 'read-only', but misses common natural user phrases like 'explain this code', 'how does X work', 'find where', 'search the repo', or 'understand the codebase'.	2 / 3
Distinctiveness Conflict Risk	The 'read-only mode' and 'without making file changes' qualifiers help distinguish it from code editing skills, but 'investigate and answer repository questions' is broad enough to potentially overlap with general code explanation or documentation skills.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: warpdotdev/oz-skills
Commit: 6c08c49

Reviewed: 2 months ago

Table of Contents

Discovery Implementation Validation

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.