CtrlK
BlogDocsLog inGet started
Tessl Logo

reviewflowz

Reviewflowz integration. Manage Organizations. Use when the user wants to interact with Reviewflowz data.

56

Quality

65%

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/reviewflowz/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 solid, actionable getting-started guide with a well-sequenced connection lifecycle and real executable commands. Its main weaknesses are a few editorial padding passages and an undefined "Step 2" reference that breaks the workflow's end-to-end clarity.

Suggestions

Define or remove the "Step 2" reference (the doc says "skip to Step 2" but no Step 2 exists) — either renumber the Searching/Running actions sections as Step 2/3 or replace with a concrete pointer.

Trim editorial asides (e.g. "so you can focus on the integration logic rather than auth plumbing", the normalized-URL explanation) that restate what the commands already show.

Consider a short end-to-end numbered checklist (connect → wait READY → search actions → run) so Claude has one unambiguous happy-path sequence.

DimensionReasoningScore

Conciseness

Most of the body is concrete commands and flags, but editorial asides like "so you can focus on the integration logic rather than auth plumbing" and the normalized-URL explanation add padding Claude does not need.

3 / 5

Actionability

Provides concrete, executable commands for install, auth, connection lifecycle, action search/run, and proxy (with a flags table), with only minor gaps where <actionId> and CONNECTION_ID remain placeholders and Reviewflowz-specific actions are deferred to runtime discovery.

4 / 5

Workflow Clarity

A clear connect → search → run sequence with a state-machine feedback loop (poll → check READY/BUILDING/CLIENT_ACTION_REQUIRED → act → re-poll), but the referenced "Step 2" is never defined and no single end-to-end checklist ties it together.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and no nested references; no bundle files exist, and runtime action discovery appropriately defers API specifics, though at this length a dedicated reference file could help.

4 / 5

Total

15

/

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 covers the basics — a product-specific what and an explicit when — but is thin on concrete actions and natural trigger terms. Listing the actual entities/tasks and more user-like trigger phrases would lift it from adequate to strong.

Suggestions

Expand the "what" beyond "Manage Organizations" to name the concrete capabilities surfaced in the body (Pull Request comments, Reviews, Users) so specificity reaches comprehensive coverage.

Replace the generic "interact with Reviewflowz data" trigger with concrete phrases users actually say, e.g. "Use when the user wants to manage Reviewflowz reviews, PR comments, or organization members."

Add common synonyms and product-specific terms (reviews, PR comments, review requests) to improve trigger-term quality and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain (Reviewflowz) and one concrete action ("Manage Organizations") but omits the other entities documented in the body (Pull Request, Comment, Review, User), so coverage is not comprehensive.

3 / 5

Completeness

Both a "what" (Reviewflowz integration, Manage Organizations) and an explicit "when" (Use when the user wants to interact with Reviewflowz data) are present, though the when-trigger is generic rather than concrete.

4 / 5

Trigger Term Quality

The product name "Reviewflowz" is a real keyword, but natural task phrases users would say (reviews, pull requests, PR comments) and synonyms are missing, with "interact with Reviewflowz data" being generic.

3 / 5

Distinctiveness Conflict Risk

The "Reviewflowz integration" framing ties it to a distinct product niche with minimal conflict risk, though the generic "Manage Organizations" wording keeps the trigger set from being crisp.

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.