deepline-feedback

Send feedback or bug reports to the Deepline team. Use when the user asks to report feedback or share a session, and proactively when a Deepline Play is disproportionately slow, appears stuck, or an ordinary outcome requires avoidable product steps.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

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

A strong, action-first skill body: executable commands cover both invocation paths, and the requested-report workflow includes a confirmation checkpoint plus real error-recovery fallbacks. Remaining gains are marginal tightening of duplicated error-outcome guidance and a slightly more concrete AskUserQuestion example.

Dimension	Reasoning	Score
Conciseness	The body is command-driven and lean, but the --error-outcome rules are explained twice (once per path) and the sandbox install fallback is a dense single line, so a few things could be trimmed without loss, matching anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Concrete, copy-paste-ready commands with explicit placeholders cover both the proactive (deepline feedback send "...") and requested paths, plus an executable transcript fallback bridge; the AskUserQuestion step is given as a prose quote rather than a literal tool-call example, a minor gap that keeps it at anchor 4 instead of 5.	4 / 5
Workflow Clarity	The requested-report path is a numbered 1-6 sequence with an explicit confirmation gate, outcome classification, and a validate-retry-fallback loop (bridge the mounted transcript dir, retry --current-session, else send newest .jsonl), matching anchor 5's explicit checkpoints and error-recovery feedback loop.	5 / 5
Progressive Disclosure	With no bundle files, all content is appropriately self-contained and organized into clear sections (Quick Start, CLI resolution, Choose the path, Proactive, User-requested) with no buried or nested references; at ~110 lines it exceeds the simple-skill threshold, so anchor 4 fits better than the fully-split-with-references anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 well-written description that explicitly covers both what the skill does and when to use it, with concrete natural-language triggers for both user-requested and proactive invocation. Its only weakness is modest action coverage relative to what the body actually supports.

Suggestions

List the fuller action set (e.g. sending session transcripts with a rating, classifying error outcomes) to raise specificity beyond a single verb.

Add common trigger variants such as "send feedback" or "file an issue" to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	"Send feedback or bug reports to the Deepline team" names the domain and one concrete action, but does not enumerate the broader action set the body supports (sending session transcripts, classifying error outcomes), matching anchor 3 rather than the several-actions anchor 4.	3 / 5
Completeness	It explicitly answers both what ("Send feedback or bug reports to the Deepline team") and when, with a concrete "Use when" clause covering both requested ("report feedback or share a session") and proactive triggers ("disproportionately slow, appears stuck"), matching anchor 5; anchor 4 is ruled out because the triggers are concrete rather than merely present.	5 / 5
Trigger Term Quality	Natural phrases like "report feedback", "share a session", "slow", and "appears stuck" are present, but common variants users might say (e.g. "send feedback", "file an issue") are missing, fitting anchor 4.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (Deepline product feedback) with product-specific trigger language, so it is unlikely to fire for unrelated skills, matching anchor 5.	5 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getaero-io/gtm-eng-skills
Path: skills/deepline-feedback/SKILL.md
Commit: a9b9731

Reviewed: 6 days 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.