CtrlK
BlogDocsLog inGet started
Tessl Logo

upkeep

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

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/upkeep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 highly actionable with copy-paste Membrane CLI commands and a clear connection workflow, but it is padded by a redundant overview list and intro fluff, and it lacks verification steps for destructive proxy/action operations. Structure is good for a single-file skill.

Suggestions

Remove the redundant 'UpKeep Overview' bullet list (the four entities repeated in four orderings) and the filler line 'Use action names and parameters as needed.'

Add a verification checkpoint after running actions or destructive proxy requests (e.g., check the response `output`/error fields and confirm success before proceeding).

Trim the marketing-style intro sentence about industries and downtime; keep only what Claude needs to act.

DimensionReasoningScore

Conciseness

The CLI sections are lean with copy-paste commands, but the intro fluff ('It's used by businesses across various industries to improve maintenance operations and reduce downtime'), the redundant 'UpKeep Overview' bullet list (the same four entities repeated in four orderings), and the filler line 'Use action names and parameters as needed.' are unnecessary. This is 'Mostly efficient but includes some unnecessary explanation' rather than score 4's tight, trimmed state.

3 / 5

Actionability

It provides fully executable, copy-paste-ready commands covering the common cases — 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://www.upkeep.com/" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --json', and 'membrane request CONNECTION_ID /path/to/endpoint' — plus a flags table. Placeholders like CONNECTION_ID are standard and explained, so it clears score 5 rather than 4.

5 / 5

Workflow Clarity

The connect-and-poll flow has explicit checkpoints and a feedback loop (poll until 'READY', re-poll after 'CLIENT_ACTION_REQUIRED'), but the proxy path exposes destructive methods (DELETE/PUT) and action runs have no verification step — 'The result is in the output field' with no confirm-success check. The rubric caps destructive/batch workflows lacking validation at 3, so it cannot reach score 4 despite the clear connection sequence.

3 / 5

Progressive Disclosure

No bundle files exist, so all content is inline in one well-sectioned file with clear headers (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices), matching 'Good structure; most content is appropriately placed.' It is not score 5 because the ~120-line file and the messy redundant overview are minor organization gaps, and not score 3 because navigation via headers is clear and references are not buried.

4 / 5

Total

15

/

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 names the UpKeep niche and includes an explicit 'Use when' clause, but relies on generic management verbs and a thin trigger phrase instead of concrete UpKeep operations users would mention. It is distinct but under-specified.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete UpKeep operations, e.g. 'Create and update work orders, track assets, and manage locations and parts in UpKeep.'

Add concrete trigger phrases users actually say, e.g. 'Use when the user wants to create work orders, track assets, manage maintenance tasks, or interact with UpKeep data.'

DimensionReasoningScore

Specificity

The description names the domain ("UpKeep integration") but its actions are generic management verbs — "Manage data, records, and automate workflows" — rather than concrete UpKeep operations like work orders, assets, locations, or parts. It fits the anchor 'Names the domain but actions are minimal or generic' and not score 3, which requires 1-2 concrete actions.

2 / 5

Completeness

Both halves are present: a 'what' ("Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with UpKeep data"). It is not score 5 because the trigger is generic rather than concrete trigger phrases, and not score 3 because the 'when' clause is explicitly stated.

4 / 5

Trigger Term Quality

It surfaces relevant keywords ("UpKeep", "data", "records", "workflows") and a usable trigger ("interact with UpKeep data"), but misses the natural terms users actually say (work orders, assets, maintenance tasks). This matches 'Some relevant keywords but missing common variations or synonyms' rather than score 4's broad keyword coverage.

3 / 5

Distinctiveness Conflict Risk

Naming a specific product ("UpKeep") gives it a clear niche with low overlap risk, matching 'Mostly distinct; minor overlap risk.' It is not score 5 because the trigger guidance is thin (only 'interact with UpKeep data') rather than a set of distinct, concrete triggers.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-skills
Reviewed

Table of Contents

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.