CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codescene

CodeScene integration. Manage Projects. Use when the user wants to interact with CodeScene data.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/codescene/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 executable CLI commands for every phase of setup and use, and the connection workflow handles intermediate states well. Its main weaknesses are an unlabeled 'Step 2' dangling reference, no validation guidance for destructive actions, bulk action-catalog content inlined rather than split out, and filler overview material.

Suggestions

Fix the dangling 'Step 2' references by numbering the workflow sections explicitly (e.g. '### Step 2: Search for actions') so the READY-state skip target resolves.

Add validation/confirmation guidance for destructive actions (Delete Project, Delete Team), e.g. verify the project ID with get-project and confirm with the user before running delete-project.

Move the 20-row Popular actions table into a references/ file (e.g. references/actions.md) and keep only the top few actions inline with a clear pointer, and trim the CodeScene Overview taxonomy tree to the branches that map to actual workflow steps.

DimensionReasoningScore

Conciseness

The body is mostly lean command blocks and tables, but the 19-line 'CodeScene Overview' taxonomy tree carries no usage guidance, the intro ('It is used by software architects, development managers, and CTOs') is marketing filler, and the vague 'Agent Types' aside adds little. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 4's 'minor instances'.

3 / 5

Actionability

Concrete, copy-paste-ready commands cover install, login (including headless completion), connection ensure/get with --wait polling, action list/run with --input JSON, and proxy requests with a flags table. It falls short of anchor 5 only because there is no worked end-to-end example running a real action with actual parameters — the run example uses the placeholder --input '{"key": "value"}'.

4 / 5

Workflow Clarity

The connection setup has a good state-driven sequence with re-poll feedback (READY/BUILDING/CLIENT_ACTION_REQUIRED/error states), but 'Step 2' is referenced twice and never exists as a labeled step, and destructive actions (Delete Project, Delete Team) appear in the actions table with no validation or confirmation guidance. Per the rubric, destructive operations without validation cap workflow clarity at 3.

3 / 5

Progressive Disclosure

The skill has no bundle files at all — all ~180 lines are inline, including a 20-row 'Popular actions' reference table that is bulk API-catalog content belonging in a separate file. Section structure is present, but 'content that should be separate is inline' matches anchor 3 rather than anchor 4's 'most content is appropriately placed'.

3 / 5

Total

13

/

20

Passed

Description

57%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 an explicit trigger clause and a clearly distinct product niche, but it undersells the skill's capabilities. It names only one generic action and omits the natural terms (hotspots, technical debt, code quality) users would say when needing CodeScene.

Suggestions

Enumerate concrete capabilities in the description, e.g. 'Analyze codebases for technical debt, hotspots, and team knowledge distribution; manage projects, teams, and analyses.'

Add natural trigger phrases users would actually say, such as 'Use when the user mentions CodeScene, code hotspots, technical debt, or code health analysis.'

Replace the generic 'interact with CodeScene data' with a more specific when-clause tied to the tasks the skill supports (listing projects, running analyses, managing developers/teams).

DimensionReasoningScore

Specificity

The description names the domain ('CodeScene integration') but lists only one generic action ('Manage Projects'), omitting concrete capabilities like hotspot analysis, technical debt detection, or team analytics. It matches the anchor 'Names the domain but actions are minimal or generic' rather than anchor 3, which expects 1-2 concrete actions with broader coverage.

2 / 5

Completeness

Both 'what' ('CodeScene integration. Manage Projects.') and an explicit 'when' ('Use when the user wants to interact with CodeScene data') are present, so the cap-at-3 rule for a missing Use-when clause does not apply. However, the when-clause is generic and the what is thin, matching anchor 4 ('when' could be more explicit or specific) rather than anchor 5's concrete trigger phrases.

4 / 5

Trigger Term Quality

'CodeScene' is the natural product term and is present, but common user phrasings such as 'hotspots', 'technical debt', 'code quality', or 'code health analysis' are missing. This fits 'Some relevant keywords but missing common variations or synonyms' rather than anchor 4's 'Good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

CodeScene is a distinct named SaaS product and the description is entirely CodeScene-bound, making wrong-skill triggering unlikely. 'Manage Projects' is generic in isolation and carries minor overlap risk with generic project-management skills, so it fits anchor 4 ('Mostly distinct; minor overlap risk') rather than anchor 5.

4 / 5

Total

13

/

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/codescene/SKILL.md

Revision

f484c82

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill