CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

model-routing-golden

Maintain model-routing audit golden fixtures and expected outputs.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/model-routing-golden/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary project-operations skill: token-efficient, command-driven, and safety-conscious around regenerating goldens, with verification woven in before and after every mutation. The only minor gap is that the destination file for `modelRoutingGoldenCases` (and the fixture README path) is referenced without being located, which slightly dents copy-paste readiness.

Suggestions

Name the file that contains `modelRoutingGoldenCases` (and the path of the fixture README) so the add-a-fixture step is fully self-contained.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and assumes competence: every sentence carries project-specific instructions (make targets, flags, guardrails like "refuses to write if analysis on the fixture differs from analysis on the full download") with zero concept explanation or padding. It matches the anchor of every token earning its place.

5 / 5

Actionability

Nearly all guidance is executable: exact commands (`make verify-model-routing-golden`, `python3 scripts/model-routing-golden.py --run <id-or-url> --case <case-name>`) and flag semantics (`--replace`, `--source-dir`). It falls just short of fully copy-paste-ready because the file containing `modelRoutingGoldenCases` is never named, leaving the reader to locate it.

4 / 5

Workflow Clarity

The regenerative workflow has explicit validation checkpoints on both sides ("Run make verify-model-routing-golden ... before changing fixtures", "Review the complete diff ... confirm that routing status, classifier attribution, AWF credits ... match", final verify after update) plus error-recovery guidance ("Treat a mismatch as a behavior change to investigate", "Do not regenerate outputs merely to silence an unexplained failure"). This matches the anchor with explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained with no bundle files (no references/, scripts/, or assets/ directories exist), and organized into three clearly headed task-oriented sections (Verify, Refresh, Add or replace). Per the simple-skill guideline, this warrants a 5 with well-organized sections and no external references needed.

5 / 5

Total

19

/

20

Passed

Description

41%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 identifies a precise, distinctive niche but is thin as a triggering description: it uses one generic action verb, contains mostly jargon, and completely omits any "use when" guidance. The body of the skill actually contains excellent natural trigger conditions ("when a model-routing golden test fails, analysis output changes intentionally, or a new routed workflow run needs coverage") that should be surfaced into the description.

Suggestions

Add an explicit trigger clause, e.g. "Use when a model-routing golden test fails, expected outputs change intentionally, or a new routed workflow run needs coverage" — this would raise both completeness and trigger-term quality.

Replace the generic verb "Maintain" with the concrete actions the skill performs: verify goldens, refresh expected outputs, capture new fixture runs.

Include natural phrasing users would say, such as "golden test failure" or "update expected outputs", alongside the existing domain terms.

DimensionReasoningScore

Specificity

The description names a specific domain ("model-routing audit golden fixtures and expected outputs") but relies on a single generic action verb ("Maintain"), analogous to the anchor example "Processes PDF files". It does not list the concrete actions involved (verify, refresh, capture fixtures), so it sits between the score-2 and score-3 anchors but is noticeably closer to the minimal-action anchor.

2 / 5

Completeness

The 'what' is stated fairly clearly ("Maintain model-routing audit golden fixtures and expected outputs") but the 'when' is entirely absent — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 because 'when' is not even weakly implied, and not 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Terms like "model-routing", "audit", "golden fixtures", and "expected outputs" are domain jargon; a couple ("golden", "expected outputs") are phrases a project member might say, but common natural variations ("golden test failed", "update the goldens", "routing audit") are absent. It matches the anchor of one or two relevant keywords while missing the natural phrases users would actually say.

2 / 5

Distinctiveness Conflict Risk

"model-routing audit golden fixtures" is a clear niche unlikely to trigger for unrelated skills, giving minimal conflict risk. However, the anchor-5 example pairs a clear niche with distinct trigger phrases, which this description lacks, and generic fixture/test-maintenance skills could claim minor overlap — so the mostly-distinct anchor fits best.

4 / 5

Total

11

/

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: 2 missing

Warning

Total

15

/

16

Passed

Repository

github/gh-aw

Path

.github/skills/model-routing-golden/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.