Name: specific
Rating: 56.8 (1 reviews)
Author: membranedev

specific

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

Quality

65%

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

Fix and improve this skill with Tessl

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

Quality

Content

67%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 a well-structured, largely executable Membrane CLI guide with explicit connection-state validation checkpoints, but it is marred by a stray refusal line and an unrelated MDN link at the top and some redundant content. Cleaning those up and enumerating the workflow would lift it clearly into the top band.

Suggestions

Remove the opening 'I don't have enough information to do that...' line and the unrelated 'Official docs: https://developer.mozilla.org/.../eval' link — both are junk that waste tokens and confuse scope.

Number the end-to-end workflow (1. Install, 2. Authenticate, 3. Connect, 4. Wait for READY, 5. Discover actions, 6. Run/Proxy) and ensure the referenced 'Step 2' maps to a real header.

De-duplicate the action-discovery command: 'Popular actions' repeats `membrane action list` from 'Searching for actions' — merge them or make 'Popular actions' point to specific named actions.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient CLI commands, but the body opens with an irrelevant LLM-refusal line ('I don't have enough information to do that...') and an off-topic MDN eval link, and the 'Popular actions' section repeats the 'Searching for actions' command, adding avoidable noise that keeps it below the lean 4/5 anchors.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, login, headless auth, connection ensure/poll, action list/run, and proxy requests with a flags table, but placeholder-heavy examples (CONNECTION_ID, QUERY) and the redundant action-list repetition leave minor gaps versus the fully comprehensive 5.	4 / 5
Workflow Clarity	There is a clear install→authenticate→connect→poll-until-READY→search→run sequence with explicit state checkpoints (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-after-action feedback loop, but 'Step 2' is referenced without a matching numbered header and the steps are not formally enumerated, so it falls short of the checklist-grade 5.	4 / 5
Progressive Disclosure	No bundle files exist, so this is a single-file skill; it is well-organized into clearly headed sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with easy navigation, but at ~137 lines it exceeds the under-50-line simple-skill exception that would allow a 5, so it lands at 4.	4 / 5
	Total	15 / 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 is third-person, includes an explicit 'Use when' trigger, and answers both what and when, but its action language is generic and the trigger terms lack synonyms or concrete variations. It is solid but not exemplary.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete operations Specific actually performs (e.g., 'Create, update, and query records; trigger workflows') so capabilities are unmistakable.

Expand the 'Use when' clause with natural trigger phrases and synonyms users would say (e.g., 'Use when the user wants to query Specific records, trigger Specific workflows, or interact with Specific data').

Tighten distinctiveness by referencing Specific-specific objects or triggers (records, meetings, transcriptions) rather than the generic word 'data'.

Dimension	Reasoning	Score
Specificity	It names the domain ('Specific integration') and a few actions ('Manage data, records, and automate workflows'), but those actions are generic abstractions rather than concrete operations, so it sits at the 'names domain + 1-2 actions, not comprehensive' anchor rather than the more concrete 4 or the minimal 2.	3 / 5
Completeness	Both 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Specific data') are present and explicit, but the 'when' clause is generic rather than tied to concrete trigger phrases, fitting the 4 anchor instead of the fully explicit 5.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Specific data' surfaces the app name plus 'data/records/workflows', but it lacks common variations, synonyms, or file-type triggers, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'Specific' app name and 'Specific data' trigger give it a distinct niche with minor overlap risk against generic data/CRM skills, placing it above the 'somewhat specific, could overlap' 3 and below the 'clear niche, minimal conflict' 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/specific/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.