Name: sellhack
Rating: 60 (1 reviews)
Author: membranedev

sellhack

SellHack integration. Manage data, records, and automate workflows. Use when the user wants to interact with SellHack data.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sellhack/SKILL.md

Quality

Content

78%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 content is highly actionable with executable commands and a well-sequenced, checkpointed connection workflow, though it carries minor redundancy and inlines reference-grade detail that would benefit from a separate file. No validation step confirms action-run success beyond the response field.

Suggestions

Add an explicit post-run verification step (e.g., check the response `output`/`error` fields and retry or surface the error) to give the action-run workflow a clear feedback loop.

Move the proxy flag table and the clientAction state reference into a `references/` file referenced one level deep to improve progressive disclosure.

Trim the duplicated `membrane action list --intent=QUERY` command in 'Popular actions' since the same command already appears under 'Searching for actions'.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — command snippets and a flag table with minimal prose — but includes some restatable detail (the multi-paragraph clientAction state breakdown and the repeated action-list command in 'Popular actions') that could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the fully lean level 5 or the padded level 3.	4 / 5
Actionability	It provides copy-paste-ready, fully executable commands for install, auth, connection ensure/get with polling, action list/run with JSON input, and the proxy request with a complete flag table, covering the common cases — matching 'fully executable; copy-paste ready code or commands; specific examples cover the common cases.'	5 / 5
Workflow Clarity	The connection flow is clearly sequenced (ensure → poll --wait → branch on state) with explicit feedback checkpoints (poll again after user action, handle CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but there is no explicit verification that an executed action succeeded beyond reading the output field, so it sits at 'clear sequence with most checkpoints present; minor validation gaps' rather than level 5.	4 / 5
Progressive Disclosure	The skill is a single SKILL.md with no bundle files and reasonable section headers, but content that could live in a separate reference (the proxy flag table and the detailed clientAction state reference) is inlined, matching 'some structure but could be better organized; content that should be separate is inline' rather than the well-split level 4.	3 / 5
	Total	16 / 20 Passed

Description

62%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.

The description correctly includes a 'Use when' trigger and names the SellHack domain, but its action list is generic and the trigger phrasing lacks natural synonyms. It is functional and distinct but not comprehensive or vivid.

Suggestions

Replace generic verbs with concrete SellHack capabilities (e.g., 'find verified email addresses, build prospect lists, look up contact info for sales leads') to lift specificity.

Expand the trigger clause with natural phrasing users actually say, e.g., 'Use when the user wants to find email addresses for prospects, look up contact info, or build a SellHack prospect list.'

Add a file-extension or noun synonym (e.g., 'prospects', 'leads', 'contact info') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the SellHack domain plus a couple of actions, but the actions are generic rather than concrete SellHack-specific capabilities, so it falls at the 'names domain and 1-2 concrete actions, but not comprehensive' anchor rather than the multi-action level 5 or the minimal level 2.	3 / 5
Completeness	It has both a 'what' ("Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with SellHack data"), but the 'when' is generic and the 'what' lacks concrete trigger phrases, fitting 'has both what and when; when could be more explicit or specific' rather than the fully concrete level 5 or the missing-when level 3.	4 / 5
Trigger Term Quality	The trigger "Use when the user wants to interact with SellHack data" relies almost entirely on the product name with no synonyms or natural-phrase variations a user might say, matching 'some relevant keywords but missing common variations or synonyms' and not the richer coverage of level 4.	3 / 5
Distinctiveness Conflict Risk	The named product "SellHack" and its data form a distinct niche with minimal conflict risk, though the generic action verbs ('manage data, records') leave minor overlap with other data-management skills, placing it at 'mostly distinct; minor overlap risk' rather than the unambiguous level 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/sellhack/SKILL.md
Commit: f484c82

Reviewed: 4 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.