Name: phonepe
Rating: 52 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

phonepe

PhonePe integration. Manage PhonePes. Use when the user wants to interact with PhonePe data.

Quality

58%

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/phonepe/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 content is a solid, mostly executable CLI guide with a well-structured connection lifecycle and a genuine polling/validation loop for connection state. Weaknesses are mild redundancy between the discovery sections, unfilled placeholders in examples, and a dangling "Step 2" reference with no matching header.

Suggestions

Merge or differentiate the "Searching for actions" and "Popular actions" sections so the discovery command appears once with all context.

Add one fully-worked end-to-end example with realistic values (a concrete connection id, intent, and action id) so the run path is copy-paste ready.

Label the major lifecycle stages as Step 1 / Step 2 (or remove the "skip to Step 2" reference) so the "Step 2" pointer resolves to an actual section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes redundancy: the "searching for actions" and "Popular actions" sections both present the same `action list --intent` discovery command, and the "Popular actions" heading carries no distinct content. Not a 4 because of these padded/duplicated spots; not a 2 because it avoids explaining concepts Claude already knows.	3 / 5
Actionability	The body provides many executable commands (install, login, connection ensure, action run, request proxy) plus a flags table. Not a 5 because common-case examples rely on unfilled placeholders (CONNECTION_ID, QUERY, <actionId>) and never show a concrete end-to-end run with real values.	4 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-until-ready → search → run sequence with a genuine validation loop (polling READY/BUILDING/CLIENT_ACTION_REQUIRED and re-polling after user action). Not a 5 because the body references "Step 2" yet defines no "Step 2" or "Step 1" header, leaving the sequence slightly confusing.	4 / 5
Progressive Disclosure	The body is well-organized into clear ## / ### sections with no nested external references and no bundle files (references/, scripts/, assets/ absent). Not a 5 because at ~150 lines it exceeds the under-50-line simple-skill exception and the action overview tree could arguably live in a separate reference.	4 / 5
	Total	15 / 20 Passed

Description

48%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 both a capability statement and an explicit "Use when" trigger, and the named brand gives it good distinctiveness. Its main weakness is specificity — "Manage PhonePes" is generic and lists no concrete actions or trigger synonyms.

Suggestions

Replace "Manage PhonePes" with 2-3 concrete capabilities, e.g. transactions, account balances, offers, and merchant lookups.

Add natural trigger phrases users would say, such as "PhonePe transactions", "PhonePe balance", or "merchant payouts", rather than repeating only the brand name.

Tighten "interact with PhonePe data" to specific verbs (query, retrieve, list) so the "when" clause is more actionable.

Dimension	Reasoning	Score
Specificity	The description names the domain ("PhonePe integration") but the only action phrase is the generic "Manage PhonePes", with no concrete actions enumerated. It is not a 1 because the PhonePe domain is clearly named, and not a 3 because there are no 1-2 specific named actions.	2 / 5
Completeness	Both a "what" ("Manage PhonePes") and a "when" ("Use when the user wants to interact with PhonePe data") are present, but the "what" is vague and does not describe what management entails. Not a 4 because the "what" side is generic rather than concrete; not a 2 because an explicit trigger clause exists.	3 / 5
Trigger Term Quality	"PhonePe" is a natural keyword a user would say, and "interact with PhonePe data" gives a usable trigger, but there are no synonyms, variations, or related phrases. It fits anchor 3 ("Some relevant keywords but missing common variations or synonyms") and is not a 4 because coverage is thin.	3 / 5
Distinctiveness Conflict Risk	PhonePe is a specific named platform, giving the skill a clear niche and low conflict risk. Not a 5 because the trigger vocabulary is essentially just the brand name repeated, with no distinctive action-based triggers.	4 / 5
	Total	12 / 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/phonepe/SKILL.md
Commit: f484c82

Reviewed: 5 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.