CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

attendance-giriton

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

Quality

57%

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/attendance-giriton/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 operational core of this skill is genuinely useful — concrete Membrane CLI commands for install, auth, connection lifecycle with state polling, action discovery/execution, and proxied raw API requests. However, the body is polluted by a leaked LLM refusal paragraph and a meaningless bullet-permutation overview section, and workflow numbering is broken ('skip to Step 2' with no Step 2). Cleaning the noise and tightening the workflow labeling would lift this from mediocre to strong.

Suggestions

Delete the leaked refusal line ('I don't have enough information to do that...') and the nonsensical 'Attendance GIRITON Overview' bullet permutations — they consume tokens and actively confuse.

Fix the workflow numbering: label 'Step 1: Create a connection' and 'Step 2' explicitly so 'skip to Step 2' resolves, and merge the redundant 'Searching for actions' and 'Popular actions' sections.

Add 2-3 GIRITON-specific example intents or action names (e.g., --intent "record employee attendance" or "list timesheets") so users can see what the integration actually does, and unify on one CLI invocation style ('membrane' vs 'npx @membranehq/cli@latest').

DimensionReasoningScore

Conciseness

Two padded sections waste tokens: a leaked LLM refusal ('I don't have enough information to do that. I'm a large language model...') and a nonsensical 'Overview' that permutes Attendance/Employee/Date/Time bullets with no informational value (~25 of ~150 body lines). This matches the level-2 anchor 'Noticeably verbose; several unnecessary explanations or padded sections'; it is not level 1 because the remaining sections (CLI install, auth, connection, actions, proxy) are reasonably lean and free of concept explanations Claude already knows.

2 / 5

Actionability

Concrete, executable commands throughout: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://giriton.com" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json', plus a flags table for proxy requests. This fits the level-4 anchor 'Mostly executable guidance; concrete code or commands with minor gaps'; it is not level 5 because no GIRITON-specific example intents or action names are shown (the 'Popular actions' section lists only the discovery command, not any actual actions), and it is well above level 3 since commands are copy-paste ready rather than pseudocode.

4 / 5

Workflow Clarity

The sequence (install → login → connection ensure → poll states → discover actions → run / proxy) is present with state-based checkpoints ('Keep polling until state is no longer BUILDING', 'poll again... to check if the state moved to READY', 'Check the error field for details'), but there is a dangling reference — 'If the returned connection has state: "READY", skip to Step 2' points to a Step 2 that is never labeled (only a '1b' subsection exists with no '1a'). This matches the level-3 anchor 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' — the broken numbering and missing labeled step make the workflow's checkpoints hard to follow, keeping it below level 4.

3 / 5

Progressive Disclosure

The skill is a single file with no references/, scripts/, or assets/ directories and no external file references, and it uses organized ## / ### section headers — appropriate for a skill of this size. However, 'Searching for actions' and 'Popular actions' are redundant sections repeating the same discovery command in different forms ('membrane action list' vs 'npx @membranehq/cli@latest action list'), and command style is inconsistent between 'membrane' and 'npx @membranehq/cli'. This fits the level-3 anchor 'Some structure but could be better organized'; not level 4 due to the redundant and inconsistent organization gaps.

3 / 5

Total

12

/

20

Passed

Description

48%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 identifies its niche through the product name and includes an explicit 'Use when' trigger, but the capability statement is generic ('manage data, records, and automate workflows') and the trigger is circular, relying solely on the product name rather than natural user phrasing. It reads like a template-generated description with minimal domain-specific tailoring.

Suggestions

Replace the generic action phrase 'Manage data, records, and automate workflows' with 2-3 concrete capabilities, e.g., 'Record employee attendance, pull timesheet and shift data, and automate attendance workflows via the GIRITON API'.

Expand the 'Use when' clause with natural trigger phrases users would actually say, such as 'Use when the user mentions GIRITON, timesheets, clock-in/clock-out records, shift scheduling, or employee attendance data'.

Add common synonyms (timesheet, time tracking, punch clock, shifts) so the skill triggers on natural language rather than only on the product name.

DimensionReasoningScore

Specificity

The description names the domain ('Attendance GIRITON integration') but the actions are generic — 'Manage data, records, and automate workflows' uses vague management verbs with no concrete operations (e.g., record attendance, pull timesheets, manage shifts). This matches the level-2 anchor 'Names the domain but actions are minimal or generic'; it is not level 3 because no 1-2 genuinely concrete actions are listed, and not level 1 because the domain is explicitly named rather than pure abstraction.

2 / 5

Completeness

A 'when' clause is present ('Use when the user wants to interact with Attendance GIRITON data') so the level-3 cap for a missing 'Use when' does not apply, but the 'what' is vague ('Manage data, records, and automate workflows') and the 'when' is circular — it triggers only on the product name rather than concrete tasks. It sits between anchors 3 and 4: the 'what' is too weak for anchor 4 ('both what and when' with a meaningful what), and better than anchor 2 since a 'when' is explicitly stated.

3 / 5

Trigger Term Quality

Relevant keywords exist ('Attendance', 'GIRITON', 'records', 'workflows') but common natural variations users would say are missing — 'timesheet', 'time tracking', 'clock in/out', 'shifts', 'punch clock'. This fits the level-3 anchor 'Some relevant keywords but missing common variations or synonyms'; not level 4 because several natural terms a user would actually use are absent, and not level 2 because the distinctive product name plus 'attendance'/'records' are genuinely relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

The specific product name 'GIRITON' carves out a clear niche with minimal conflict risk against unrelated skills. It is not level 5 because the generic phrase 'Manage data, records, and automate workflows' could superficially overlap with other data-management or workflow-automation skills, and no distinct task-level triggers are given; it is above level 3 because the named integration target is far more specific than 'works with document files'.

4 / 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.

Validation — 15 / 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

Path

skills/attendance-giriton/SKILL.md

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.