CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

state-machine

Validate state machine and lifecycle correctness

Quality

70%

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 ./plugins/pragma/skills/state-machine/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 body is a well-structured, actionable validation playbook with concrete input gathering, a detection gate, tiered rules with review checklists, and a strict output schema. Minor gains are available from removing the duplicated scope restatement.

Suggestions

Remove the restated scope at the end of the Scope Declaration block (lines ~32-35) since it duplicates the 'checks ONLY' / 'MUST NOT report on' lists already given.

Consider adding a short validation/self-check step before emitting JSON (e.g. confirm summary counts match the array lengths) to add an explicit feedback loop.

The single-item normative References section could be folded into the Operating Rules preamble to avoid a near-empty trailing section.

DimensionReasoningScore

Conciseness

Mostly efficient and action-oriented with concrete commands and a tight schema; the only trimming opportunity is the scope being restated after the Scope Declaration block.

4 / 5

Actionability

Provides concrete, copy-paste bash for gathering diffs, grep patterns for detection, and an exact JSON output schema with typed fields; the rules themselves are review-guidance rather than executable code, which is appropriate for a judgment task.

4 / 5

Workflow Clarity

Clear sequence (gather diffs -> detect -> gate -> evaluate rules in order -> categorize -> emit JSON) with a detection checkpoint and per-rule 'When reviewing, check' lists; not a 5 because there is no error-recovery feedback loop, though the skill is non-destructive so the validation cap does not apply.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections in a single self-contained file with no nested references; not a 5 because it exceeds ~50 lines and the normative References section is a single inline bullet rather than externalized material.

4 / 5

Total

16

/

20

Passed

Description

53%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 clear and appropriately scoped to a distinct niche, but it is minimal: it states only the 'what' with one action verb and omits any 'when to use' trigger guidance.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing diffs that touch status/state enums, transition functions, or terminal-state classifications.'

Expand the action list beyond the single verb 'Validate' to concrete behaviors like 'detect unreachable states, verify cleanup on terminal entry, and check model-vs-runtime consistency.'

Include synonyms users might say (e.g. 'FSM', 'workflow', 'status fields') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('state machine', 'lifecycle') and a concrete action ('Validate ... correctness'), but coverage is not comprehensive—only a single validating verb across two nouns.

3 / 5

Completeness

Has a clear 'what' ('Validate state machine and lifecycle correctness') but no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('state machine', 'lifecycle'), but lacks common variations, synonyms, or related phrasing users might also use.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (state-machine/lifecycle validation) with minimal overlap risk; not a 5 because it lacks explicit trigger phrasing that would fully distinguish it from sibling validators.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

peteski22/agent-pragma

Path

plugins/pragma/skills/state-machine/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.