alpha

Fixture dispatcher with a mode table and forced-read references.

Quality

39%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./test/fixtures/context-bill/tree-a/alpha/SKILL.md

Quality

Content

57%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 commendably concise and structurally organized as an overview-plus-references, but it offers only abstract dispatch instructions with no concrete executable actions, no validation checkpoints, and two dangling reference paths that break navigation.

Suggestions

Replace abstract steps with concrete, executable guidance — e.g. specify how to infer the mode (which signals map to which mode) rather than 'Infer the mode from the request'.

Add validation/verification checkpoints to the dispatch protocol, especially before delegating to a specialist, so mis-inferred modes are caught.

Fix or remove the missing references/legacy/office.md and references/legacy/auto.md paths (or create those files) so all cited references resolve.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a short numbered protocol and one small table — with no padding or explanation of concepts Claude already knows, so every token earns its place, matching the score-5 anchor.	5 / 5
Actionability	Steps are high-level abstractions ("Infer the mode from the request", "Read references...") with no concrete commands or code, matching the score-2 anchor of minimal concrete guidance and missing specific executable steps.	2 / 5
Workflow Clarity	A numbered dispatch sequence is present, but there are no validation checkpoints or error-recovery feedback loops for the routing decisions, matching the score-3 anchor of a listed sequence with missing/implicit checkpoints.	3 / 5
Progressive Disclosure	The body is short and points to one-level-deep reference files, but two cited paths (references/legacy/office.md, references/legacy/auto.md) do not exist, so navigation is not actually easy — between the score-3 and score-4 anchors, the broken references pull it down to 3.	3 / 5
	Total	13 / 20 Passed

Description

21%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 meta-descriptive and jargon-laden rather than user-facing: it explains the skill's internal mechanics instead of what it does for the user or when to invoke it. It lacks both concrete capabilities and any trigger guidance.

Suggestions

Rewrite the description in third person around concrete user-facing actions (e.g. 'Routes requests to the appropriate specialist...') instead of internal terms like 'mode table' and 'forced-read references'.

Add an explicit 'Use when...' clause stating the natural trigger phrases a user would say when this skill applies.

Include natural synonyms or keywords users actually say to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	It names a domain ("Fixture dispatcher with a mode table") but describes the skill in implementation/meta terms rather than user-facing actions, so actions are minimal or generic — matching the score-2 anchor.	2 / 5
Completeness	There is only a vague "what" ("Fixture dispatcher...") and no "when"/"Use when" clause at all, matching the score-2 anchor of a vague what with no when.	2 / 5
Trigger Term Quality	"dispatcher", "mode table", and "forced-read references" are internal jargon; no natural keywords a user would actually say, matching the score-1 anchor of only technical jargon.	1 / 5
Distinctiveness Conflict Risk	"Fixture dispatcher with a mode table" is somewhat niche but generic enough to overlap with other routing/dispatch skills, fitting the score-3 anchor of somewhat specific but possible overlap.	3 / 5
	Total	8 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: garrytan/gstack
Path: test/fixtures/context-bill/tree-a/alpha/SKILL.md
Commit: 96764e8

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.