CtrlK
BlogDocsLog inGet started
Tessl Logo

sorry

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

53

Quality

60%

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/sorry/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 highly actionable with concrete CLI commands, a thorough connection state machine, and good section structure. Its main weaknesses are a leftover placeholder 'Official docs' line, duplicated action-discovery guidance, and a bare Overview section that lists entities without explanation.

Suggestions

Remove the placeholder line 'Official docs: I am sorry, but I cannot provide an API or developer documentation URL…' or replace it with the real documentation URL.

Merge the duplicated 'Searching for actions' and 'Popular actions' sections into a single action-discovery section to avoid repeating the `membrane action list` command.

Expand the bare '## Sorry Overview' bullets (Message, Conversation) with a one-line explanation each, or remove them if they add no guidance value.

DimensionReasoningScore

Conciseness

The body is mostly efficient CLI command examples, but it includes a junk placeholder line ("Official docs: I am sorry, but I cannot provide an API or developer documentation URL…") and a duplicated action-discovery section ('Searching for actions' vs 'Popular actions') that should be tightened, fitting the score-3 anchor.

3 / 5

Actionability

It provides concrete, copy-paste-ready commands for install, login, connection, action search/run, and proxy requests plus a complete flags table, matching the score-4 anchor of mostly executable guidance with minor gaps (e.g. unresolved CONNECTION_ID placeholders).

4 / 5

Workflow Clarity

The install → authenticate → connection ensure → poll until ready → search actions → run actions sequence is clear, and the connection state machine (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) with re-poll feedback loops provides explicit checkpoints, matching the score-4 anchor.

4 / 5

Progressive Disclosure

With no bundle files present, content is appropriately kept inline and organized under clear headings; minor organization gaps (the bare Overview bullets and the misplaced 'Official docs' line) keep it at score-4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

53%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 has a proper third-person voice and includes an explicit 'Use when' clause, but its capability list is generic and the trigger phrasing is thin on natural synonyms. It is distinguishable mainly by app name rather than by concrete, distinctive actions.

Suggestions

Replace the generic verb list ('Manage data, records, and automate workflows') with concrete Sorry-specific actions, e.g. 'Issue customer refunds, manage compensation workflows, and track apology records'.

Add natural trigger phrases and synonyms users would say, e.g. 'Use when the user wants to issue refunds, handle customer compensation, or manage Sorry records'.

Tie the 'when' clause to specific scenarios (refunds, compensation, restitution) rather than the abstract 'interact with Sorry data'.

DimensionReasoningScore

Specificity

The description names the domain (Sorry) but its actions — "Manage data, records, and automate workflows" — are generic and could apply to almost any app, matching the score-2 anchor of minimal/generic actions rather than the concrete actions needed for a 3.

2 / 5

Completeness

It states both a what ("Manage data, records, and automate workflows") and an explicit when clause ("Use when the user wants to interact with Sorry data"), but the when is generic rather than tied to concrete trigger phrases, matching the score-4 anchor.

4 / 5

Trigger Term Quality

"Use when the user wants to interact with Sorry data" supplies a relevant natural keyword ("Sorry"), but lacks common variations or synonyms a user might actually say, fitting the score-3 anchor.

3 / 5

Distinctiveness Conflict Risk

The Sorry app name makes it somewhat specific, but the generic action vocabulary ("manage data, records, automate workflows") creates real overlap risk with many data-oriented skills, fitting the score-3 anchor rather than the more distinct score-4.

3 / 5

Total

12

/

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.