CtrlK
BlogDocsLog inGet started
Tessl Logo

update-from-starter-template

Update Mattermost plugin repositories with common files from mattermost-plugin-starter-template and fix all linter issues. Use when syncing build tooling, updating golangci-lint config, or fixing linter errors in a Mattermost plugin.

68

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 content is a tight, well-sequenced workflow with executable commands and explicit verification steps. The main improvement is making the fetch step and the validate-fix retry loop fully explicit to lift actionability and workflow clarity to the top anchor.

Suggestions

Add a concrete command for fetching the starter-template files (e.g., a `gh api`/`git fetch` invocation) instead of the bare 'Fetch and compare these files' instruction.

Make the feedback loop explicit: after 'Run make check-style to confirm 0 issues', state 'If issues remain, return to Phase 2 and re-run until clean.'

Tighten 'Fix remaining issues manually' with a pointer to the specific linter output format or a one-line example of a typical manual fix.

DimensionReasoningScore

Conciseness

The body is lean and instructional — phased steps, terse file lists, and short troubleshooting/commit-message sections with no padding or re-explanation of concepts Claude already knows (e.g., no primer on what golangci-lint or a Makefile is). Every line earns its place, matching the 'Lean and efficient; assumes Claude's competence' anchor. It is not a 4 because there are no meaningful instances of over-explanation to trim.

5 / 5

Actionability

Mostly executable guidance with copy-paste-ready commands ('git switch -c update-from-starter-template', 'go install mvdan.cc/gofumpt@latest', 'gofumpt -w server/', 'make check-style', 'go mod tidy') and a specific file manifest, but with minor gaps — 'Fetch and compare these files' gives no concrete fetch command, and 'Fix remaining issues manually' / 'Create a descriptive commit and PR' are high-level. It is not a 5 because the common cases are not uniformly copy-paste ready, and not a 3 because the bulk is concrete and executable.

4 / 5

Workflow Clarity

A clear Phases 0-4 sequence with explicit verification checkpoints ('Run make test to verify all tests pass', 'Run make check-style to confirm 0 issues'), forming an implicit validate-fix-retry flow plus a troubleshooting section for error recovery. It is not a 5 because the feedback loop is implicit rather than stated as 'if check-style fails, return to Phase 2', and not a 3 because validation checkpoints are clearly present (so the batch/destructive cap does not apply).

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is self-contained with well-signaled sections (## Instructions, ### Phase 0-4, ## Example commit message, ## Troubleshooting) and easy navigation, satisfying the simple-skill exception for a skill with no external references. It is not a 4 because there are no organization gaps or buried references — all content is appropriately inline.

5 / 5

Total

18

/

20

Passed

Description

82%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 well-crafted: it pairs a concrete 'what' with an explicit 'Use when' trigger clause and occupies a distinctive, low-conflict niche. Its only weak spot is specificity, where two top-level actions suffice but a broader enumeration would push it higher.

DimensionReasoningScore

Specificity

It names the domain and two concrete actions — 'Update Mattermost plugin repositories with common files' and 'fix all linter issues' — but stops at the 1-2 action level rather than enumerating several specific actions, matching the anchor for 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because coverage is not broad enough (only two top-level actions), and not a 2 because both actions are concrete rather than generic.

3 / 5

Completeness

It explicitly answers both 'what' ('Update Mattermost plugin repositories with common files... and fix all linter issues') and 'when' ('Use when syncing build tooling, updating golangci-lint config, or fixing linter errors in a Mattermost plugin') with concrete trigger phrases, matching the top anchor. It is not a 4 because the 'when' clause is already explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Natural trigger phrases a user would say are present — 'syncing build tooling', 'updating golangci-lint config', 'fixing linter errors', 'Mattermost plugin' — giving good keyword coverage with only minor variations missing. It is not a 5 because synonyms and file extensions are not exhaustively covered, and not a 3 because the terms go well beyond a single generic keyword.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche — syncing the mattermost-plugin-starter-template and golangci-lint config in Mattermost plugins — with distinct, domain-specific triggers and minimal overlap risk with other skills. It is not a 4 because the niche is sharply bounded rather than having residual overlap with closely related skills.

5 / 5

Total

17

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
mattermost/mattermost-ai-marketplace
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.