CtrlK
BlogDocsLog inGet started
Tessl Logo

architectural-proposals

How to write comprehensive architectural proposals that drive alignment before code is written

56

Quality

64%

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 ./.copilot/skills/architectural-proposals/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.

A well-structured, instruction-only skill with concrete formats, worked examples, and an anti-pattern review checklist; it respects token budget and is genuinely actionable. The workflow is implied through pattern lists and retrospective examples rather than explicit steps, and the file is long enough that some example material could move to a reference file.

DimensionReasoningScore

Conciseness

The body is list-driven and dense ('Required sections: 1-7', 'Never: Hype...'), with no explanations of concepts Claude already knows; only minor tightening opportunities remain, e.g., the 10-item 'Key patterns demonstrated' recap and the do/don't tone lists partially restate the anti-patterns section.

4 / 5

Actionability

Gives executable, concrete guidance: a 7-section required template, exact file paths ('docs/proposals/', '.squad/decisions.md'), and copy-paste-ready format blocks for decision framing and risk documentation. Falls short of a 5 because no complete worked proposal skeleton is shown — the reader assembles structure from fragments.

4 / 5

Workflow Clarity

A clear sequence exists ('Read user directive first... Document problem... Propose solution... Define scope', plus tool ordering in frontmatter) and the 'Red flags in proposal reviews' list acts as a review checkpoint. Not a 5 because the sequence is presented as a retrospective example list rather than explicit steps, and there is no validate/fix/retry loop for the proposal itself.

4 / 5

Progressive Disclosure

A single-file skill with no bundle files, organized under clear headers (Context, Patterns, Examples, Anti-Patterns) with no nested references — all references cited (e.g., docs/proposals/squad-interactive-shell.md) are project artifacts, not skill files. Kept at 4 rather than 5 because at ~135 lines, the worked Wave Restructuring and Interactive Shell examples would arguably fit better in a separate reference file.

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 states a clear purpose and domain in third person, but it omits any explicit 'when to use this' trigger guidance and undersells the skill's concrete capabilities. Adding a trigger clause and natural synonyms would move it from adequate to strong.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when writing an architecture proposal, RFC, or design doc before implementation begins, or when a decision will affect multiple waves or milestones.'

Include the skill's concrete actions and natural synonyms in the description: structuring required sections, framing decisions with sign-off owners, and documenting risks — matched to user terms like 'design doc', 'RFC', 'tech spec', 'ADR'.

Drop or replace the vague 'drive alignment' phrasing with a specific outcome, such as 'that get explicit sign-off before code is written'.

DimensionReasoningScore

Specificity

The description names the domain ('architectural proposals') and one concrete action ('write ... proposals'), but 'drive alignment' is purpose-fluff rather than an action, and none of the skill's actual capabilities (structure required sections, frame decisions, document risks, restructure waves) surface. Matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the multi-action anchor at 4.

3 / 5

Completeness

The 'what' is clear ('write comprehensive architectural proposals'), but the 'when' is only weakly implied by the temporal phrase 'before code is written' — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords are present ('architectural proposals', 'alignment', 'code'), but common user phrasings are missing: users asking for a 'design doc', 'RFC', 'tech spec', or 'ADR' would not naturally match. Fits 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

The niche (pre-implementation architectural proposals) is fairly distinct with low conflict risk against typical skills. Not a 5 because the description lacks explicit triggers that would separate it from general writing or planning skills someone might invoke instead.

4 / 5

Total

13

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
bradygaster/squad
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.