CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scan-pipeline

Reference for how the scan pipeline actually works — process_scan()'s call order, the CurrentScan/Events/Sessions/DevicesView relationships, how a session actually "closes" (there is no close function), and the FIELD_SPECS field-write authority mechanism. Load this before modifying server/scan/session_events.py or server/scan/device_handling.py, or when reasoning about device presence, connect/disconnect events, or session/timeline behavior.

73

Quality

92%

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

The canonical home for this skill is scan-pipeline in netalertx/NetAlertX

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A dense, high-value reference that documents genuinely non-obvious pipeline behavior (edge-triggered event design, emergent session closing, field-write authority) with named functions, files, and explicit do/don't rules. Its weaknesses are stylistic and structural rather than substantive: a few run-on gotcha paragraphs that could be tightened, described-but-unstructured validation loops, and a numbering error in the Gotchas list.

Suggestions

Fix the Gotchas numbering: item 7 appears twice (the LatestEventsPerMAC and MAC-keyed gotchas are both numbered 7) and the list then jumps to 9 — renumber sequentially.

Split Gotcha 8's ~300-word single paragraph into shorter sentences or a small cause/fix/test breakdown to preserve clarity without losing the detail; the same applies to parts of Gotcha 9.

Consider moving the deepest gotchas (e.g. 7-9 on view gating, SQL scoping, and IP-known logic) into a references/ file with one-level-deep pointers from SKILL.md, keeping the main body to the table map, call order, and authority mechanism.

DimensionReasoningScore

Conciseness

Nearly every sentence carries non-inferable, project-specific fact (call-order rationale, silent-failure modes, index coverage) with no padding of concepts Claude already knows. However, Gotcha 8 ("A correlated helper's `mac_column` argument silently binds to the helper's own inner row...") is a ~300-word single paragraph with nested parentheticals, and Gotcha 9 is similarly dense — trimmable verbosity, matching anchor 4 rather than 3 (nothing is padding) or 5 (a few passages sacrifice clarity for density).

4 / 5

Actionability

Concrete, executable directives throughout: "To close a session, insert the right `Events` row — never mutate `Sessions` directly", "Check any new presence-adjacent query against both patterns", "Don't design around these tables ever becoming devGUID-keyed", each tied to named functions, files, and columns. Per the scoring note, absence of code in an instruction-only skill is not penalized when guidance is this actionable — and it fully is.

5 / 5

Workflow Clarity

The 14-step "`process_scan()` call order — order is load-bearing" is a clearly sequenced list with per-step rationale ("If this ran after the presence update, every query would see the new value and the edge-triggered design would break") and explicit checkpoints ("Check any new query here with `EXPLAIN QUERY PLAN` at a realistic row count"). It falls short of anchor 5 because validate→fix→retry loops are described rather than structured, and the Gotchas section has a numbering defect (two items labeled 7, then a jump to 9) that slightly muddies an otherwise coherent sequence.

4 / 5

Progressive Disclosure

Clear sections (Scope, Core tables, Key views, call order, Field-write authority, Gotchas) plus a dedicated "When to read this vs. other docs/skills" section with well-signaled one-level-deep pointers ("→ `database-patterns`", "see `plugin-development` and `docs/PLUGINS_DEV*.md`"). No bundle files exist, so nothing is misfiled, but the ~19KB body of deep-gotcha material is dense enough that some belongs in a reference file, and the duplicated gotcha numbering is a minor organization gap — anchor 4, not 5.

4 / 5

Total

17

/

20

Passed

Description

100%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 is exemplary: it states what the skill covers in concrete, codebase-specific terms and gives an explicit, trigger-rich 'load this before...' clause. It is distinguishable from adjacent skills and free of vague language or over-claims.

DimensionReasoningScore

Specificity

"process_scan()'s call order, the CurrentScan/Events/Sessions/DevicesView relationships, how a session actually \"closes\" (there is no close function), and the FIELD_SPECS field-write authority mechanism" lists multiple specific concrete items with comprehensive coverage of the skill's scope, in third person with no fluff.

5 / 5

Completeness

"Reference for how the scan pipeline actually works — ..." (what) is followed by an explicit when clause: "Load this before modifying server/scan/session_events.py or server/scan/device_handling.py, or when reasoning about device presence, connect/disconnect events, or session/timeline behavior" — both answered with concrete triggers.

5 / 5

Trigger Term Quality

"device presence, connect/disconnect events, or session/timeline behavior" plus "server/scan/session_events.py or server/scan/device_handling.py" gives comprehensive natural trigger phrasing with synonyms and concrete file-level triggers a developer would actually name.

5 / 5

Distinctiveness Conflict Risk

"scan pipeline", "FIELD_SPECS field-write authority mechanism", and table-level specifics carve a clear niche; the skill is explicitly about post-plugin pipeline behavior, distinct from plugin authoring or general database patterns, so conflict risk is minimal.

5 / 5

Total

20

/

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

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

netalertx/NetAlertX

Path

.gemini/skills/scan-pipeline/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.