CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-code-bug-spec

This skill should be used when the user says "bug spec", "arness code bug spec", "investigate this bug", "help me debug", "trace this bug", "diagnose this issue", "I found a bug", "something is broken", "why is X not working", "fix this bug", "debug this", "why is this not working", or wants to iteratively investigate a bug through guided conversation with diagnostic analysis. Bridges the gap between a bug report and either a direct fix or a structured bug specification for the Arness pipeline.

80

Quality

76%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/arn-code/skills/arn-code-bug-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

82%

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 excels at providing extensive natural trigger terms and clearly addresses both what the skill does and when to use it. However, the actual capabilities could be more concretely specified (e.g., what diagnostic steps it performs, what the output bug spec looks like), and the generic debugging trigger terms create moderate conflict risk with other coding/debugging skills.

Suggestions

Add more specific concrete actions the skill performs, e.g., 'Analyzes stack traces, reproduces issues, traces code paths, and generates structured bug specifications with root cause analysis.'

Consider narrowing some generic trigger terms or adding disambiguation guidance to reduce conflict with general debugging skills, e.g., clarifying this is for structured investigation workflows rather than quick code fixes.

DimensionReasoningScore

Specificity

The description mentions some actions like 'iteratively investigate a bug through guided conversation with diagnostic analysis' and 'bridges the gap between a bug report and either a direct fix or a structured bug specification,' but it doesn't list multiple concrete specific actions (e.g., trace call stacks, analyze logs, reproduce steps). The actions remain somewhat abstract.

2 / 3

Completeness

The description clearly answers both 'what' (bridges bug report to direct fix or structured bug specification via guided conversation with diagnostic analysis) and 'when' (explicit list of trigger phrases and scenarios). The 'Use when' equivalent is the opening clause with extensive trigger terms.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would actually say: 'bug spec', 'investigate this bug', 'help me debug', 'something is broken', 'why is X not working', 'fix this bug', 'debug this', 'I found a bug', 'diagnose this issue'. These are very natural phrases a user would use.

3 / 3

Distinctiveness Conflict Risk

While the 'bug spec' and 'Arness pipeline' terms are distinctive, many of the trigger phrases like 'help me debug', 'fix this bug', 'why is this not working' are very generic debugging terms that could easily overlap with general coding assistance or other debugging skills. The Arness-specific context helps but doesn't fully prevent conflicts.

2 / 3

Total

10

/

12

Passed

Implementation

70%

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 conversational workflow skill with excellent workflow clarity and progressive disclosure. The multi-step process is clearly sequenced with branching paths, iterative loops, convergence criteria, and thorough error handling. The main weaknesses are moderate verbosity (some redundancy between inline summaries and referenced files) and a lack of concrete executable examples for agent invocations, which keeps actionability at a moderate level.

Suggestions

Add a concrete example of an agent invocation call (e.g., exact syntax for invoking arn-code-investigator with parameters) so Claude knows the precise format rather than inferring from abstract descriptions.

Reduce redundancy in Steps 5 and 6A by either removing the inline summaries entirely (since they point to diagnosis-flow.md) or removing the reference pointer and keeping the content inline — currently both exist.

DimensionReasoningScore

Conciseness

The skill is fairly long but most content is necessary for a complex multi-step workflow. However, there's some redundancy — Steps 5, 6A, and 6B each summarize what's in the referenced diagnosis-flow.md file while also telling the reader to go read that file, creating partial duplication. Some explanatory text could be tightened (e.g., the opening paragraphs restate the same routing logic twice).

2 / 3

Actionability

The skill provides clear step sequences and specific agent invocation patterns with parameter descriptions, but lacks concrete executable examples — no actual command outputs, no example agent invocation syntax, no sample bug spec content. The mkdir commands are concrete, but the agent invocations are described abstractly ('invoke the arn-code-investigator agent with...') without showing exact invocation format.

2 / 3

Workflow Clarity

The workflow is exceptionally well-sequenced with clear steps (0-7), explicit branching logic (simple vs complex path), iterative loops with convergence criteria, and comprehensive error handling covering multiple failure modes with specific recovery actions. Validation checkpoints are present (architectural validation, user confirmation gates, test attempt limits).

3 / 3

Progressive Disclosure

The skill effectively uses progressive disclosure — the main SKILL.md provides a clear overview of each step while deferring detailed procedures to well-signaled reference files (diagnosis-flow.md, bug-spec-template.md, agent-invocation-guide.md, bugfix-plan-template.md). References are one level deep and clearly signaled with consistent formatting. Steps 4-6A explicitly point to the same reference file for detailed procedures.

3 / 3

Total

10

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
AppsVortex/arness
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.