CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deepline-feedback

Retired. Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`. Kept only so installed CLIs that still list this skill keep syncing.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

The body is an exemplary retired stub: minimal, fully executable, and unambiguous. It wastes no tokens, points to the authoritative documentation (the CLI's --help) for both former functions, and clearly declares that the skill holds no instructions and will be removed. Nothing in the written content warrants a deduction on any dimension.

DimensionReasoningScore

Conciseness

The ~16-line body is lean with zero padding: an install block ("npm install -g deepline", "deepline -h"), one status line ("This skill holds no instructions and will be removed"), and two one-line redirects. Every token earns its place and nothing explains concepts Claude already knows, matching the anchor-5 example's economy.

5 / 5

Actionability

All guidance is copy-paste executable — `npm install -g deepline`, `deepline -h`, `deepline feedback send --help`, `deepline sessions send --help` — and the two bullets cover both common cases (reporting feedback, sharing a session) with the exact command for each. This fully matches the anchor-5 standard of executable commands covering the common cases.

5 / 5

Workflow Clarity

This is a simple single-purpose skill where the single action is unambiguous: for a feedback or session-sharing request, run the corresponding `--help` command, and each bullet maps task to command ("`deepline feedback send --help` explains when to report feedback... ", "`deepline sessions send --help` explains sharing a session transcript..."). The rubric's simple-skill exception applies, and there are no destructive or batch operations that would require validation checkpoints.

5 / 5

Progressive Disclosure

The body is under 50 lines with no need for external reference files — the detailed documentation intentionally lives in the CLI's own help output, which the body signals clearly. Sections (Quick Start, redirect bullets) are well organized and there are no nested references, so the under-50-lines rule scores this a 5.

5 / 5

Total

20

/

20

Passed

Description

70%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.

This is a well-executed retired-stub description: it is honest about its status, gives exact CLI commands for both former functions, and explains why it still exists ("Kept only so installed CLIs that still list this skill keep syncing"). Its main weakness is the absence of any explicit "Use when..." trigger guidance, which caps completeness, and slightly thin coverage of natural trigger variations.

Suggestions

Add an explicit trigger clause (e.g., "Use when the user asks to report deepline feedback or share a deepline session") so the description answers 'when' as well as 'what' and lifts the completeness cap.

Include natural trigger variations such as "send feedback", "report a bug", or "share a session transcript" to broaden keyword coverage for users phrasing the request differently.

Briefly state what the two commands cover (one clause each, e.g., "`deepline feedback send` reports bugs or friction; `deepline sessions send` shares a rated session transcript") to make the capability statements self-contained.

DimensionReasoningScore

Specificity

The description lists both of the stub's areas with exact, concrete commands — "Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`" — going beyond the anchor-3 example of bare 1-2 action names. It stays at 4 rather than 5 because it never states what those actions actually do, deferring entirely to the CLI help.

4 / 5

Completeness

The "what" is clear — "Retired... documented by the CLI itself" with the exact commands — but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural user phrases are present: "Reporting feedback", "sharing a session", and the product name "deepline" — comparable keyword density to the anchor-4 example ("PDF files, forms, document extraction"). It is not 5 because common variations like "send feedback", "report a bug", or "session transcript" are missing.

4 / 5

Distinctiveness Conflict Risk

It is scoped to a specific tool and its two subcommands ("deepline feedback send", "deepline sessions send") and explicitly marks itself "Retired", giving it a clear niche with minimal conflict risk. No other plausible skill would trigger for these tool-specific commands, so it fits the anchor-5 example's level of distinctness.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

getaero-io/gtm-eng-skills

Path

skills/deepline-feedback/SKILL.md

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.