CtrlK
BlogDocsLog inGet started
Tessl Logo

greptile

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

59

Quality

68%

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/greptile/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 content is a well-structured, command-driven CLI guide with mostly executable guidance and an explicit polling/feedback loop for connection readiness. Its main gaps are a lack of concrete Greptile-specific examples (it relies on placeholder intents and discovered actions) and minor organizational redundancy between the overview and popular-actions sections.

DimensionReasoningScore

Conciseness

The body is command-heavy and largely lean, with concrete bash snippets earning their place; minor over-explanation remains in the best-practices rationale, the agent-types line, and the intro. Not a 5 because of these trimmable prose passages; not a 3 because it is not noticeably verbose or padded.

4 / 5

Actionability

Mostly executable, copy-paste-ready commands cover install, auth, connect, search, run, and proxy. Not a 5 because it uses placeholder intents ('--intent "QUERY"') and never shows a concrete Greptile code-search example, and the 'Greptile Overview' section is sparse; not a 3 because the guidance is real executable commands rather than pseudocode.

4 / 5

Workflow Clarity

Clear sequence (install → auth → connect → poll → search → run → proxy) with an explicit polling feedback loop and state branching (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR). Not a 5 because 'Step 2' is referenced without coherent numbering and action-run outputs are not validated; not a 3 because explicit checkpoints and error recovery are present, and the skill is not destructive/batch so the cap does not apply.

4 / 5

Progressive Disclosure

Good section structure with clear headers and no nested references in a single file with no bundle files. Not a 5 because some sections are thin or redundant ('Greptile Overview' bullets, 'Popular actions' overlaps 'Searching for actions') and there is no file-level disclosure; not a 3 because the structure is well-organized and navigable.

4 / 5

Total

16

/

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 correctly answers both what and when with an explicit 'Use when' clause and a distinctive brand anchor, but it relies on generic action language ('manage data, records, and automate workflows') that fails to convey Greptile's actual purpose (search and analytics over source code). It omits the natural trigger terms a user would say when needing this skill.

Suggestions

Replace the generic actions with concrete Greptile-specific capabilities, e.g. 'Search source code across repositories, find and understand code, and run code analytics.'

Add natural trigger terms users would actually say — such as 'search code', 'query repositories', or 'find code with Greptile' — instead of the generic 'interact with Greptile data'.

State what Greptile is (a search and analytics platform for source code) in the description so the trigger is clearer and more distinctive.

DimensionReasoningScore

Specificity

Names the domain ('Greptile integration') and lists 2-3 actions ('Manage data, records, and automate workflows'), but the actions are generic and omit what Greptile actually does (search/analyze source code). Not a 4 because the actions lack concrete specificity; not a 2 because multiple actions are named rather than a single generic one.

3 / 5

Completeness

Provides both a 'what' ('Greptile integration. Manage data, records, and automate workflows.') and an explicit 'when' ('Use when the user wants to interact with Greptile data.'). Not a 5 because the 'when' lacks concrete trigger phrases (no mention of search/code); not a 3 because an explicit 'Use when' clause is present, so the missing-trigger cap does not apply.

4 / 5

Trigger Term Quality

Includes the brand keyword 'Greptile' and 'data/records', but misses the natural phrases users would say ('search code', 'query repositories', 'find code'). Not a 4 because keyword coverage is thin and lacks common variations; not a 2 because relevant brand and data terms are present.

3 / 5

Distinctiveness Conflict Risk

The 'Greptile' brand name in both the what and when gives it a distinct niche and trigger, but the generic 'manage data, records, automate workflows' phrasing is shared across many integration skills, creating minor overlap risk. Not a 5 because the actions are generic rather than comprehensively distinct; not a 3 because the brand anchor is specific.

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.