Name: oysterhr
Rating: 51.2 (1 reviews)
Author: membranedev

oysterhr

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

Quality

56%

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/oysterhr/SKILL.md

Quality

Content

50%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 CLI operational guidance is concrete, executable, and sequenced with a polling checkpoint, which is the skill's real strength. It is undermined by a ~240-line inlined entity/policy/procedure list that bloats the token budget without actionable guidance and by the absence of verification steps for destructive record/workflow operations.

Suggestions

Move the entity/policy/procedure enumeration into a separate reference file (e.g. references/entities.md) and link to it, or remove it in favor of the action-discovery workflow that already surfaces available entities.

Add an explicit verify-after-run checkpoint for write/automation actions, e.g. re-query the affected record or check the action output's success/status before reporting completion.

Tighten the overview to the handful of top-level resources users actually manipulate and let `membrane action list --intent` cover the long tail.

Dimension	Reasoning	Score
Conciseness	The body inlines roughly 240 bullet points enumerating every OysterHR entity, policy clause, and procedure (lines 23-259), which is heavy padding that adds little actionable value, while the CLI sections themselves are reasonably tight. Not a 1 because the operational sections are efficient and not concept-explaining; not a 3 because the inlined entity list is a large, clearly unnecessary padded section.	2 / 5
Actionability	Concrete copy-paste commands are provided throughout ("membrane login --tenant --clientName=<agentType>", "membrane connection ensure", "membrane action run <actionId>", "membrane request CONNECTION_ID /path"), plus a flags table for proxy requests. Not a 5 because the giant entity list and "Use action names and parameters as needed" are non-executable filler and a few flows lack worked parameter examples.	4 / 5
Workflow Clarity	A clear sequence exists (install, login, connection ensure, poll until READY, search actions, run/proxy) with a polling checkpoint and state-based branching for CLIENT_ACTION_REQUIRED, but the actual action execution — which manages records and automates workflows (destructive/batch-capable) — has no verify-after-run checkpoint. The destructive/batch cap holds this at 3 rather than 4.	3 / 5
Progressive Disclosure	The body has section headers and a logical flow for the CLI usage, but no bundle files exist and the ~240-line entity enumeration is inlined bulk content that belongs in a separate reference file. Not a 4 because that inlined bulk is not split out or referenced; above 2 because the operational sections are genuinely well-structured with headers.	3 / 5
	Total	12 / 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 is well-anchored to a specific named product, keeping conflict risk low. Its main weakness is generic action verbs and thin trigger-term coverage rather than concrete, varied natural phrases.

Suggestions

Replace generic verbs with concrete operations, e.g. "Create and update employee records, submit time-off requests, and run payroll reports".

Expand trigger terms with synonyms users actually say, e.g. "Use when the user mentions OysterHR, employee records, time-off, payroll, or onboarding workflows".

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the OysterHR domain plus two-to-three actions, but the verbs (manage, automate) are generic rather than concrete API operations, matching the anchor that lists 1-2 actions without comprehensive coverage. Not a 2 because it does enumerate multiple actions beyond a single domain mention; not a 4 because none of the actions are specific concrete operations.	3 / 5
Completeness	Both halves are present: "what" ("Manage data, records, and automate workflows") and an explicit "when" clause ("Use when the user wants to interact with OysterHR data"), matching the anchor with both what and when where when could be more specific. Not a 5 because the trigger phrase is generic rather than a concrete set of trigger phrases; clearly above 3 since the when clause is explicit.	4 / 5
Trigger Term Quality	The phrase "Use when the user wants to interact with OysterHR data" supplies the product name plus "data" and "records" as natural terms, but it lacks common synonyms or variations a user might actually say. Not a 4 because coverage of natural phrasings is thin; not a 2 because the product name is itself a strong natural trigger term.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product OysterHR gives it a clear niche with low conflict risk against unrelated skills, but the generic action verbs (manage data, automate workflows) could overlap with other HR/integration skills. Not a 5 because the action language is not uniquely distinguishing; above 3 because the named product anchors it firmly.	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/oysterhr/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.