CtrlK
BlogDocsLog inGet started
Tessl Logo

appfire

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

61

Quality

72%

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/appfire/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a strong, command-driven skill: it is highly actionable with copy-paste-ready Membrane CLI commands, a clear connect-and-poll workflow with a feedback loop, and well-organized sections. Its main weaknesses are minor padding (the company intro, some restated examples) and slightly thinner validation guidance on the action-run/proxy paths.

Suggestions

Trim the company-background paragraph ("Appfire is a software company that creates apps for Atlassian, Microsoft, and Salesforce...") since Claude does not need it to act.

Add an explicit validate/error-handling step to the action-run and proxy sections (e.g., check the response `error` field and retry or surface it) to strengthen workflow clarity.

Move the detailed `clientAction.*` field breakdown out of the main connect flow or into a compact reference so the core workflow reads as a tighter checklist.

DimensionReasoningScore

Conciseness

The body is mostly efficient, leading with executable commands and terse descriptions (e.g., "Add `--json` to any command for machine-readable JSON output.") with only minor over-explanation like the Appfire company intro and the repeated action-list instructions, matching the score-4 anchor of 'efficient; minor instances that could be trimmed'; it is not a 5 because the company background paragraph and a few restated examples add small padding.

4 / 5

Actionability

Nearly every instruction is a copy-paste-ready CLI command ("npm install -g @membranehq/cli@latest", "membrane connection ensure ... --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --json") plus a flag table, fully executable and covering the common cases per the score-5 anchor; it does not drop to 4 because guidance is concrete and complete rather than having gaps.

5 / 5

Workflow Clarity

The connect workflow is clearly sequenced (ensure -> poll with --wait -> branch on READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), with an explicit re-poll feedback loop after the user acts, fitting the score-4 anchor of 'clear sequence with most checkpoints'; it is not a 5 because there is no explicit validation checkpoint/error-recovery checklist for the action-run and proxy paths, and not a 3 because key checkpoints (polling until non-BUILDING, re-poll after action) are present.

4 / 5

Progressive Disclosure

Content is well-organized into overview, install, auth, connecting, searching, popular actions, proxy, and best-practices sections with no bundle files needed and only shallow self-contained structure, matching the score-4 anchor of 'good structure; appropriately placed; minor gaps'; it is not a 5 because the 'Appfire Overview' bullet list and some inline API-detail content (clientAction fields) could be split out for a cleaner overview, and not a 3 because structure is clear and navigable.

4 / 5

Total

17

/

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 is adequate: it names the Appfire domain and provides both a 'what' and a 'Use when...' clause, which keeps it distinguishable from generic integration skills. Its main weakness is generic action verbs (manage, interact) and thin natural-language trigger terms with no synonyms or product variations.

Suggestions

Replace generic verbs with concrete Appfire actions (e.g., 'Search Appfire actions, run workflows, and proxy Appfire API requests') to raise specificity.

Add natural trigger synonyms users might say, such as 'Use when the user wants to query Appfire records, run Appfire workflow executions, or call the Appfire API.'

Tighten the 'when' clause with specific triggers (workflows, integrations, audit logs) instead of the broad 'interact with Appfire data'.

DimensionReasoningScore

Specificity

It names the domain (Appfire) and a few actions ("Manage data, records, and automate workflows"), but the actions are generic verbs with no concrete operations, matching the score-3 anchor of 'domain and 1-2 concrete actions, not comprehensive'; it is not a 4 because there are not several specific, differentiated actions.

3 / 5

Completeness

It states what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Appfire data"), satisfying both halves per the score-4 anchor; it is not a 5 because the 'when' is generic ('wants to interact with Appfire data') rather than concrete trigger phrases, and not a 3 because both what and when are explicitly present.

4 / 5

Trigger Term Quality

"Appfire" is the only natural keyword and "interact with Appfire data" restates it; it lacks common synonyms or product-name variations users might say, fitting the score-3 anchor of 'some relevant keywords but missing common variations', and not a 4 because keyword coverage is thin rather than 'good'.

3 / 5

Distinctiveness Conflict Risk

The Appfire niche is clearly named with a domain-specific trigger, giving mostly-distinct routing with only minor overlap risk against other integration skills, matching the score-4 anchor; it is not a 5 because "interact with Appfire data" is a fairly broad trigger rather than tightly scoped.

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.