e2e-template-testing

End-to-end validation of coordinator and agent template changes

Quality

67%

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 ./.squad-templates/skills/e2e-template-testing/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with a clearly sequenced, validation-checked workflow and many copy-paste-ready commands. Its main weaknesses are token redundancy from repeated comment-table blocks and a monolithic structure that could offload the Progress Reporting detail into a reference file.

Suggestions

De-duplicate the tracking-comment table: show the initial body once and reference it from Step 0 and the Progress Reporting section instead of repeating it four times.

Move the detailed Progress Reporting comment-lifecycle code into a references/progress-reporting.md file and keep SKILL.md as an overview pointer.

Tighten the duplicated Step 0 guidance so the two-step post-then-update sequence is stated once rather than re-explained across sections.

Dimension	Reasoning	Score
Conciseness	Most content is concrete and non-obvious (the ~15-min connection limit, stale-SDK shadowing, --allow-all-tools requirement), but the comment-body table is repeated roughly four times and Step 0 is duplicated in the Progress Reporting section, so it is not lean enough for anchor 3 while staying well above the verbose anchor 1.	2 / 3
Actionability	The body provides fully executable PowerShell and bash commands, exact gh api/copilot/git invocations, and copy-paste-ready file-verification checks, matching anchor 3.	3 / 3
Workflow Clarity	A clear Step 0-6 sequence is paired with explicit fast-fail checkpoints (BUILD_FAILED/LINK_FAILED/CLI_NOT_FOUND), per-step verify actions, feedback loops (fix and re-validate, stop on failure), and a verdict checklist, satisfying anchor 3.	3 / 3
Progressive Disclosure	Sections are well organized and the single CONTRIBUTING.md reference is one level deep, but the ~550-line body is monolithic with the long comment-body/Progress-Reporting code inline that could live in a separate reference file, matching anchor 2 rather than the appropriately-split anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 names a specific niche and one concrete action but stops short of listing multiple actions or providing any explicit trigger guidance, capping most dimensions at 2. It is distinctive because the domain is very narrow, but lacks the "Use when" clause that would raise completeness and trigger quality.

Suggestions

Add 2-3 concrete actions, e.g. "...by building a local CLI, running real squad sessions, and verifying outcomes against git state".

Append an explicit trigger clause, e.g. "Use when you change .squad-templates/ coordinator prompts, agent charters, or notes-protocol.md".

Include natural-term variations users would say ("testing", "regression", "prompt changes") alongside "validation".

Dimension	Reasoning	Score
Specificity	Names a concrete domain ("coordinator and agent template changes") and one action ("validation"), matching anchor 2 rather than 3 which requires multiple specific actions, and above 1 since the domain is concrete rather than vague.	2 / 3
Completeness	It states what the skill does ("End-to-end validation of coordinator and agent template changes") but gives no "when"/"Use when" guidance, and the rubric caps completeness at 2 when explicit trigger guidance is missing.	2 / 3
Trigger Term Quality	Terms like "end-to-end validation", "coordinator", and "agent template changes" are relevant but miss common variations a user might say ("testing", "regression", "prompt changes"), and there is no trigger clause, so it does not reach anchor 3.	2 / 3
Distinctiveness Conflict Risk	"coordinator and agent template changes" is a narrow, squad-specific niche unlikely to trigger for unrelated skills, matching anchor 3's clear-niche criterion.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (558 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: bradygaster/squad
Path: .squad-templates/skills/e2e-template-testing/SKILL.md
Commit: e23dd92

Reviewed: 1 day 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.