CtrlK
BlogDocsLog inGet started
Tessl Logo

postman

Postman integration. Manage Workspaces. Use when the user wants to interact with Postman data.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%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 well-documented connection state machine including error-recovery feedback loops. Its weaknesses are conciseness padding (concept explanation, filler lines, a 20-row 'No description' table) and minor workflow/organization gaps.

Suggestions

Remove the Postman intro paragraph and 'Use action names and parameters as needed.' — Claude already knows what Postman is, and the line adds no executable guidance.

Trim the 20-row 'Popular actions' table where every entry reads 'No description'; either drop the empty descriptions or move the full action catalog to a separate reference file.

Convert the connect-to-Postman flow into an explicit numbered checklist with a labeled 'Step 2' target and a 'Validate state is READY before proceeding' checkpoint, and fix the orphaned '1b' subsection numbering.

DimensionReasoningScore

Conciseness

The body includes concept explanation Claude already knows ("Postman is an API client that makes it easier for developers to develop, test, and document APIs"), filler ("Use action names and parameters as needed."), marketing prose, and a 20-row action table where every row says "No description". The core command reference is efficient, so this is more than minor over-explanation but not severely padded. It is not a 4 because the padding is more than minor, and not a 2 because the actionable core is solid.

3 / 5

Actionability

The body provides copy-paste-ready, fully executable commands for every common case — install, login, connection ensure/get, action list/run, and request proxy — plus a flags table. Specific examples cover the common cases, matching the fully-executable anchor. It is not a 4 because the guidance is complete rather than having minor gaps.

5 / 5

Workflow Clarity

The connection workflow has an explicit state machine with feedback loops: poll until READY, re-poll after the user completes CLIENT_ACTION_REQUIRED, and check the error field on CONFIGURATION_ERROR/SETUP_FAILED. It is not a 5 because steps are not framed as a crisp numbered checklist with explicit 'Validate' steps and the 'skip to Step 2' forward reference has no matching label, and not a 3 because checkpoints are present and explicit rather than missing.

4 / 5

Progressive Disclosure

The skill is self-contained with clear section headers and no broken or nested references, and no bundle files exist to verify. It is not a 5 because at ~160 lines it exceeds the simple-skill threshold and has minor organization gaps (a '#### 1b.' subsection with no '1a', and a 'Step 2' reference without a labeled target), and not a 3 because structure is genuinely good rather than merely present.

4 / 5

Total

16

/

20

Passed

Description

66%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 is third-person, names a distinct application, and includes an explicit 'Use when...' trigger, so it answers both what and when. Its main weakness is thin capability coverage — only Workspaces is named — and limited trigger-term variety.

Suggestions

Expand the 'what' to enumerate concrete actions across Postman entities (e.g., collections, APIs, environments, requests, mocks, monitors) rather than only 'Manage Workspaces'.

Broaden trigger terms to include natural phrases users say, such as 'collections', 'APIs', 'requests', or 'environments', not just 'Postman data'.

Tighten 'Postman integration.' into a capability-led verb phrase (e.g., 'Manage Postman workspaces, collections, and environments.') to lift specificity.

DimensionReasoningScore

Specificity

"Postman integration." names the domain and "Manage Workspaces." gives one concrete action, matching the anchor for naming a domain plus 1-2 actions without comprehensive coverage. It is not a 2 (which requires minimal/generic actions only) nor a 4 (which requires several specific actions).

3 / 5

Completeness

"Postman integration. Manage Workspaces." states what it does and "Use when the user wants to interact with Postman data." gives an explicit when clause, satisfying both. It is not a 5 because the what-side is thin (only Workspaces) and lacks comprehensive concrete trigger phrases, and not a 3 because the when clause is explicit rather than weakly implied.

4 / 5

Trigger Term Quality

"Postman" and "Workspaces" are natural keywords a user would say, but common variations such as collections, APIs, requests, and environments are absent, so coverage is partial rather than good. It does not reach 4 because several common terms are missing, and is above 2 because the core natural phrase "Postman" is present.

3 / 5

Distinctiveness Conflict Risk

"Postman" is a distinct, named application with a clear niche, and the trigger "interact with Postman data" is specific, giving minimal conflict risk with other skills. It is not a 4 because there is no meaningful overlap risk with closely related skills.

5 / 5

Total

15

/

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.