CtrlK
BlogDocsLog inGet started
Tessl Logo

peach

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

54

Quality

61%

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/peach/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 provides solid executable Membrane CLI commands and a reasonably sequenced connection workflow with feedback loops. It is dragged down by verbose generic filler, a stray error/refusal line, and the absence of any Peach-specific action examples or validation before destructive calls.

Suggestions

Remove the stray refusal line ("I don't have enough information about the app...") and the filler sentence "Use action names and parameters as needed." — they add no guidance.

Add at least one concrete Peach-specific action example (e.g., a real `membrane action run` for a common Peach task) so the skill is actionable for Peach rather than only generic CLI usage.

Resolve the dangling "skip to Step 2" reference and add an explicit validation/check step before running mutating actions against Peach data.

DimensionReasoningScore

Conciseness

Noticeably verbose: a stray refusal line ("I don't have enough information about the app to fulfill that request..."), filler ("Use action names and parameters as needed."), an unexplained generic overview list, and non-Peach best-practice padding add several unnecessary sections, matching anchor 2.

2 / 5

Actionability

Concrete, executable commands throughout (install, login, connection ensure, action list/run, request) plus a flags table; it falls short of 5 because entries use placeholders and no Peach-specific action example is demonstrated.

4 / 5

Workflow Clarity

A clear install→auth→connect→poll→search→run/proxy sequence with a connection state-machine and a poll-again feedback loop is present; below 5 due to a dangling "skip to Step 2" reference and no validation guidance before running mutating actions.

4 / 5

Progressive Disclosure

Good section structure with no nested references (no bundle files exist) and single-level organization; below 5 because at over 50 lines, detailed reference material such as the proxy flags table and full connection state machine could be split into separate files for a leaner overview.

4 / 5

Total

14

/

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 cleanly states both what the skill does and when to use it, with a named-app trigger that keeps conflict risk low. Its main weakness is generic, non-concrete action language and a single trigger phrase with no synonyms.

DimensionReasoningScore

Specificity

Names the domain ("Peach integration") and a few actions ("Manage data, records, and automate workflows"), but the actions are generic rather than concrete like the anchor-4 examples, so it sits at 3 and below 4.

3 / 5

Completeness

Both a clear "what" ("Peach integration. Manage data, records, and automate workflows.") and an explicit "when" ("Use when the user wants to interact with Peach data.") are present, but the single generic trigger phrase keeps it below a 5.

4 / 5

Trigger Term Quality

Relevant keywords appear ("Peach", "interact with Peach data", data/records/workflows), but coverage is limited to essentially one trigger phrase with no synonyms or variations, matching anchor 3 rather than 4.

3 / 5

Distinctiveness Conflict Risk

The named app "Peach" gives a distinct niche with only minor overlap risk against other data-integration skills; the generic action wording prevents a 5.

4 / 5

Total

14

/

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.