CtrlK
BlogDocsLog inGet started
Tessl Logo

stalker-portal

Use when changing Stalker or Ministra routes, stores, catalog or series shapes, playback progress, favorites and recent items, EPG, or remote control.

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exceptionally lean, high-signal instruction skill: exact names, paths, and validation commands with well-signaled doc references. The only notable weaknesses are the missing top-level 'what' in the description (judged separately) and a slightly malformed e2e command in the body.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific facts Claude cannot know ('isStalkerSeriesFlag() accepts exactly true, 1, and the string 1'; 'Auth failures are HTTP 200 plus plain text') with no padding and no explanation of concepts Claude already knows.

5 / 5

Actionability

Guidance is concrete throughout — exact predicates (isFullStalkerPortalPlaylist(), executeStalkerRequest()), exact file paths, and runnable commands ('pnpm nx test shared-interfaces') — but 'pnpm nx run web-e2e:e2e-ci--src/stalker.e2e.ts' omits the '--' separator before the flag and will not run verbatim, a minor executable gap.

4 / 5

Workflow Clarity

Validation is explicit (a full list of test targets plus the e2e fallback) and risky operations carry ordering and failure-recovery rules ('save the scoped row before clearing a confirmed legacy row, and keep legacy progress when the save fails'), but the body is structured as reference rules rather than a sequenced end-to-end workflow.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~85-line body keeps rules inline while clearly signaling one-level-deep doc pointers with their purpose ('docs/architecture/stalker-epg.md for ITV EPG', 'docs/architecture/remote-control.md for live remote control'), organized under well-labeled sections.

5 / 5

Total

18

/

20

Passed

Description

72%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.

A strong, highly specific trigger clause with excellent natural keywords and no conflict risk, but it is missing an explicit 'what' statement, leaving the skill's actual capabilities implied rather than stated.

Suggestions

Add a leading 'what' clause before the 'Use when' trigger, e.g. 'Maintains Stalker/Ministra portal ownership rules, wire-format and series contracts, and validation commands. Use when changing...'.

Mention that the skill covers test validation and e2e workflow coverage so the 'what' reflects the body's Validation section, not just the areas of change.

DimensionReasoningScore

Specificity

The single action 'changing' is applied to an exhaustive, concrete list of subsystems ('routes, stores, catalog or series shapes, playback progress, favorites and recent items, EPG, or remote control'), but the description never states what the skill actually provides (ownership rules, wire-format contracts, validation), so action coverage is not comprehensive.

3 / 5

Completeness

The 'Use when changing...' clause explicitly and richly answers 'when', but the description is trigger-only: no 'what' clause exists, and the skill's actual capabilities are only weakly implied through the enumerated triggers.

3 / 5

Trigger Term Quality

Natural terms cover every subsystem a developer would mention, including the synonym pair 'Stalker or Ministra', plus 'routes', 'stores', 'catalog', 'series', 'playback progress', 'favorites', 'EPG', and 'remote control'.

5 / 5

Distinctiveness Conflict Risk

'Stalker or Ministra' plus the specific subsystem triggers define a clear niche with distinct trigger terms and minimal risk of firing for an unrelated skill.

5 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
4gray/iptvnator
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.