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

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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.

Highly actionable with copy-paste commands and a clear sequenced workflow, and well-organized for a single-file skill. The main weakness is workflow_clarity: the transcript-send step is a fallback chain without an explicit success/failure checkpoint, and some inline shell one-liners could be leaner.

Suggestions

Add an explicit validation checkpoint after 'sessions send' (e.g. check the --json output for a success/error field) and a retry-on-failure step rather than a silent fallback chain.

Tighten the long inline fallback install and transcript-bridging shell one-liners — break into separate, commented steps or move the Cowork-specific path logic into a short script to reduce inline noise.

State the expected outcome of each command (what 'auth wait' / 'sessions send' returns) so Claude can detect a failure and branch, giving the workflow a true feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with executable commands and tight prose, but the fallback install line and the Cowork-bridging block are long inline shell one-liners with embedded commentary that could be trimmed; no concept-padded fluff, yet some lines could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready bash commands (npm install, auth register/wait/status, feedback send, sessions send) with concrete flags like --json, --current-session, --timeout and a real fallback transcript path.

3 / 3

Workflow Clarity

Steps are clearly numbered and sequenced with an explicit confirm gate, but the transcript-send step lacks a true validation/checkpoint loop — it tries one command then a fallback chain without verifying success or handling errors beyond a retry, and no destructive-operation feedback loop is present.

2 / 3

Progressive Disclosure

A compact single-file skill (~50 lines) with well-organized sections (Quick Start, Steps) and no external bundle references to mislink; content is appropriately self-contained for a skill this size.

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.

A strong description: concrete actions, natural trigger phrasings, and an explicit 'Use when...' clause that satisfies both the what and the when. Voice is third person throughout. No significant weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Send feedback or bug reports', 'including session transcript and environment info', 'share the current Claude/Cowork session' — each tied to a specific artifact.

3 / 3

Completeness

Explicitly answers both what ('Send feedback or bug reports...including session transcript and environment info') and when ('Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session').

3 / 3

Trigger Term Quality

Covers natural trigger phrasings users would say — 'report a bug', 'send product feedback', 'share the current...session' — with good variation including 'bug reports' and 'support'.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Deepline feedback with transcript/env collection) with triggers unlikely to fire for unrelated skills; the Deepline/Cowork-specificity narrows conflict risk.

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.