CtrlK
BlogDocsLog inGet started
Tessl Logo

deepline-feedback

Send feedback or bug reports to the Deepline team, including session transcript and environment info. Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session with Deepline support.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with executable commands and a clear confirm step, but slightly over-explains in places and lacks an explicit success-verification checkpoint after the external send operations.

Suggestions

Add a final validation step that inspects the `--json` output of `deepline feedback send` / `deepline sessions send` to confirm success before telling the user it was sent.

Trim Claude-derivable inline commentary (e.g. 'completes Cowork/browser approval; no-op if already connected') to tighten token efficiency.

Move the Cowork-bridge shell snippet into a clearly labeled fallback block so the primary happy path reads as a simple two-command workflow.

DimensionReasoningScore

Conciseness

The body is mostly lean and command-driven, but includes some Claude-derivable explanation such as the inline comment 'completes Cowork/browser approval; no-op if already connected' and the prose 'the run is likely in Cowork' that pads beyond what is needed to act.

2 / 3

Actionability

It provides concrete, executable commands throughout — install fallback chain, `deepline feedback send`, `deepline sessions send`, and a copy-paste-ready shell bridge for the Cowork transcript case — with specific flags and a fallback `ls -t ... | head -1` path.

3 / 3

Workflow Clarity

The five-step sequence is clearly numbered, but the destructive/irreversible action of sending a session transcript and environment info to an external party has a confirm checkpoint (good) and no post-send verification that the send actually succeeded (e.g. checking the `--json` response), leaving a validation gap at the end of the workflow.

2 / 3

Progressive Disclosure

The skill is a single-purpose, under-50-line body organized into Quick Start, CLI resolution, and Steps sections with no bundle files and no nested references — well-structured and appropriately self-contained.

3 / 3

Total

10

/

12

Passed

Description

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.

The description is specific, third-person, and supplies explicit trigger guidance covering both what the skill does and when to invoke it, with low conflict risk against other skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Send feedback or bug reports to the Deepline team, including session transcript and environment info' — naming the specific payload components transmitted rather than a single vague action.

3 / 3

Completeness

It answers both 'what' (send feedback/bug reports with transcript and environment info) and 'when' via an explicit 'Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session with Deepline support' clause.

3 / 3

Trigger Term Quality

It captures natural phrasings a user would actually say — 'report a bug', 'send product feedback', 'share the current Claude/Cowork session' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The Deepline-specific target and narrow trigger set (reporting bugs / product feedback to Deepline support) carve a clear niche unlikely to overlap with general skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
getaero-io/gtm-eng-skills
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.