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

predicthq

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/predicthq/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 well-structured, actionable guide with strong command examples and a clear state-driven connection workflow. Its main weaknesses are mild verbosity (intro paragraph, redundant section, empty stubs) and a missing verification step before running actions.

Suggestions

Trim the opening paragraph that explains what PredictHQ is; assume Claude knows or link to docs instead.

Remove the redundant 'Popular actions' section that re-states the 'action list' command already shown under 'Searching for actions', or merge them.

Add a verify/confirm step before destructive action runs (e.g. inspect outputSchema or confirm with the user before mutating records), and either flesh out or delete the empty 'PredictHQ Overview' bullet stubs.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the opening paragraph explaining what PredictHQ is, the empty 'PredictHQ Overview' bullet stubs, and the redundant 'Popular actions' section that re-states 'action list --intent=QUERY' add unnecessary tokens, matching 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides copy-paste-ready commands (membrane login, connection ensure, action list/run, request) with a flags table and --json usage, but relies on placeholders like CONNECTION_ID and QUERY without a fully worked example, fitting 'mostly executable guidance with minor gaps' rather than the complete anchor 5.	4 / 5
Workflow Clarity	The connect-and-poll workflow has an explicit, state-driven feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR with re-polling), giving clear checkpoints; the gap is that 'Running actions' lacks a verify/confirm step before potentially destructive record operations, so it stays at 4 rather than 5.	4 / 5
Progressive Disclosure	The single file is well-organized with clear section headers and no nested references, but the empty 'PredictHQ Overview' stubs and the lengthy inline proxy-flags table are minor organization gaps that keep it below the cleanly-split anchor 5.	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 answers both what and when with an explicit 'Use when' clause and a distinct platform name, but its actions are generic rather than PredictHQ-specific. Trigger coverage relies on a single proper noun with no synonyms.

Suggestions

Replace generic actions with concrete PredictHQ capabilities, e.g. 'Search events, fetch features, and look up place rankings'.

Add natural trigger phrasing users would say, e.g. 'Use when the user mentions demand intelligence, events impacting demand, or the PredictHQ API'.

Tighten the 'when' clause to name specific tasks (forecasting, event-driven demand) rather than the broad 'interact with PredictHQ data'.

Dimension	Reasoning	Score
Specificity	Names the domain ('PredictHQ integration') and several actions ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete PredictHQ capabilities like searching events or fetching features, so it sits at the anchor-3 level and not the more specific anchor 4.	3 / 5
Completeness	It states both what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with PredictHQ data'), but the 'when' is somewhat broad and the 'what' is generic, so it fits 'has both what and when; when could be more explicit' rather than the fully concrete anchor 5.	4 / 5
Trigger Term Quality	The core natural term 'PredictHQ' appears in 'interact with PredictHQ data', but coverage is limited to that single proper noun with no synonyms or phrasing variations users might say, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'PredictHQ integration' is a clear, distinct niche tied to a specific platform with minimal conflict risk, but the trigger 'interact with PredictHQ data' is slightly broad, placing it just below the maximally distinct anchor 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/predicthq/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.