CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plugin-router

Analyze broad, mixed, or unclear Plugin Factory follow-up requests and select the correct plugin lane. Use when plugin intent lacks a clear lane owner.

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/plugin-factory/skills/team_automation/plugin-router/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 router overview with concrete examples, an enumerated handoff schema, explicit failure handling, and a genuinely one-level-deep reference bundle. Its weaknesses are repetition (workflow.md listed three times, a fluffy Philosophy section) and three referenced files that are never given read-when signals.

Suggestions

Consolidate the three separate mentions of references/workflow.md (Workflow section, Read-when bullet, References list) into one clearly signaled pointer.

Drop or merge the Philosophy section into When to Use; its two bullets restate routing principles already enforced elsewhere.

Give contract.yaml, evals.yaml, and task-profile.json the same 'Read when' treatment as workflow.md (or mark them as non-agent-facing infra files) so every listed reference has a clear navigation signal.

DimensionReasoningScore

Conciseness

Line-level writing is lean ('Route first, execute second', terse Constraints/Anti-Patterns bullets), but there is systematic redundancy: 'references/workflow.md' is named three times (Workflow section, a Read-when bullet, and the References list), and the Philosophy section adds platitudes rather than new information. This fits 'mostly efficient but could be tightened' rather than anchor 4's minor-trimming level.

3 / 5

Actionability

Concrete guidance dominates: example requests map to specific lanes ('Create a new plugin with marketplace entry.' -> '[[plugin-creator]]'), the handoff object's fields are enumerated, and a runnable validation command is given. Minor gaps keep it below anchor 5: no example handoff object inline (deferred to workflow.md) and examples cover only 3 of the 5 documented route intents.

4 / 5

Workflow Clarity

The multi-step sequence (classify intent, choose direct/clarify-once, select one lane, emit handoff and stop) is clearly sequenced one well-signaled level deep in references/workflow.md, and the body adds explicit checkpoints: a fail-fast validation gate ('stop at first failed gate and report blocker text') and a blocked_by/one-blocking-question fallback. Not anchor 5 because the sequence and its checkpoints are not presented inline in SKILL.md itself.

4 / 5

Progressive Disclosure

The bundle structure matches the references: workflow.md, contract.yaml, evals.yaml, and task-profile.json all exist, and the detailed protocol is one level deep with clear 'Read when' purpose bullets per reference. Minor gaps: contract.yaml, evals.yaml, and task-profile.json are listed in References with no read-when guidance, and the ../../../../../Infrastructure/ paths are deep, unverifiable cross-tree hops, keeping it below anchor 5.

4 / 5

Total

15

/

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 is a clear, third-person, two-sentence statement with both a what and an explicit Use-when clause, but its trigger vocabulary leans on internal jargon rather than natural user phrasing and its capability coverage is minimal. Its main risk is overlap with the canonical plugin-factory-router entry point it defers to in the body.

Suggestions

Add 1-2 more concrete capabilities to the what-clause (e.g., 'emit a structured routing handoff with the selected lane, next skill, and required inputs') to lift specificity and completeness.

Replace or supplement jargon triggers ('lane owner', 'Plugin Factory follow-up') with natural phrases users would actually type, such as 'plugin request', 'route plugin work', 'which plugin skill handles this'.

Disambiguate from the canonical router in the description itself, e.g., 'Use when intent is still unmapped after plugin-factory-router's initial routing', to reduce trigger conflict between the two routers.

DimensionReasoningScore

Specificity

The description names its domain ('Plugin Factory follow-up requests') and exactly two actions ('Analyze... requests and select the correct plugin lane'), matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage. It does not reach anchor 4 because it lists only two verbs and no more granular capabilities such as handoff emission or blocked-request handling.

3 / 5

Completeness

Both parts are explicitly present: what ('Analyze broad, mixed, or unclear Plugin Factory follow-up requests and select the correct plugin lane') and when ('Use when plugin intent lacks a clear lane owner'). The when-clause is explicit but abstract — it lacks the concrete trigger phrases (user-mentionable words or request shapes) that anchor 5 requires.

4 / 5

Trigger Term Quality

Terms like 'Plugin Factory follow-up', 'plugin lane', and 'lane owner' are relevant but internal jargon, and common natural variations a user would say (e.g., 'route this plugin request', 'which plugin skill should handle this') are missing. This fits 'some relevant keywords but missing common variations or synonyms' better than anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (post-routing lane selection) and is unlikely to fire for unrelated skills. It stops short of anchor 5 because the skill family includes a canonical 'plugin-factory-router' front door with overlapping routing triggers, creating minor conflict risk with that closely related skill.

4 / 5

Total

14

/

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

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

14

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Plugins/plugin-factory/skills/team_automation/plugin-router/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.