Name: punchh
Rating: 52.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

punchh

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

Quality

59%

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/punchh/SKILL.md

Quality

Content

61%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 concrete, copy-paste CLI commands and a genuine polling-based feedback loop for connection readiness, but it is weakened by redundant sections and broken step cross-references that fragment the workflow narrative. No bundle files exist, yet the in-body sectioning is sound.

Suggestions

Remove the redundant "Popular actions" section (it restates the "Searching for actions" command) and trim the marketing overview paragraph to a one-line context note.

Fix the broken step numbering: replace "skip to Step 2" and "1b" with a consistent numbered connection workflow (1. install, 2. auth, 3. connect, 4. poll until READY).

Add an explicit validation checkpoint for action results (e.g., check the `output`/`error` field and retry on failure) since action runs can mutate Punchh data.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient CLI commands and a flag table, but the marketing overview paragraph ("Punchh is a marketing platform for brick-and-mortar retailers..."), the thin "Punchh Overview" tree, and the redundant "Popular actions" section are unnecessary padding that could be tightened, fitting anchor 3.	3 / 5
Actionability	Concrete, copy-paste-ready commands cover the common cases (install, login, connection ensure, action list/run, proxy) plus a complete proxy flag table, but ID placeholders (CONNECTION_ID, <actionId>, <id>) and minor gaps keep it just below a clean 5.	4 / 5
Workflow Clarity	A sequence with a real feedback loop exists (poll until READY, handle CLIENT_ACTION_REQUIRED, re-poll), but the broken cross-references ("skip to Step 2" and "1b" with no matching "1a" or labeled "Step 2") make the flow partially incoherent, matching anchor 3's 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The body is well-organized into clearly headed sections (Overview, Working with Punchh, Install, Authentication, Connecting, Searching actions, Running actions, Proxy, Best practices) with no bundle files to over-inline; minor redundancy from the "Popular actions" section keeps it from a clean 5.	4 / 5
	Total	14 / 20 Passed

Description

57%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 identifies the Punchh platform and includes an explicit 'Use when' trigger, but relies on generic action verbs rather than concrete Punchh-specific capabilities and offers limited trigger-term variety. It is distinct as a platform integration but would benefit from sharper, domain-specific wording.

Suggestions

Replace generic verbs with concrete Punchh operations, e.g. "look up loyalty accounts, issue rewards, and retrieve guest orders".

Broaden trigger terms to natural user phrasings like "Punchh loyalty program", "Punchh rewards", or "guest orders".

Tighten the 'when' clause to name the specific intents (loyalty, promotions, campaigns) rather than the generic "interact with Punchh data".

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Punchh domain but the actions are generic (manage data, automate workflows) rather than concrete Punchh-specific operations, matching anchor 2's 'actions are minimal or generic' better than anchor 3's 'concrete actions'.	2 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Punchh data") with an explicit trigger clause, but the 'when' could be more specific, matching anchor 4; the explicit 'Use when' clause keeps it above the cap-at-3 rule.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with Punchh data" surfaces the core natural keyword "Punchh" but lacks synonyms or variations (e.g., loyalty, rewards, guest orders), fitting anchor 3's 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Naming the specific platform "Punchh" gives it a clear niche with low conflict risk, but the generic 'manage data, records, and automate workflows' wording leaves minor overlap risk with other integration skills, fitting anchor 4 rather than a clean 5.	4 / 5
	Total	13 / 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/punchh/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.