CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sync-web-site

To synchronize web site with changes made to local *.md files

Quality

65%

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 ./.claude/skills/sync-web-site/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 skill's editorial core is strong: tight lists, a clear sequenced workflow with a HITL approval gate, and genuinely useful operational hard-won commands. Its two weaknesses are self-inflicted: a Lessons learned log that balloons the token cost and belongs in a references/ file, and main-workflow steps whose executable detail is deferred to those lessons instead of stated inline. The skill would score well by simply following its own doctrine.

Suggestions

Move the 'Lessons learned' section to references/lessons.md, keeping a one-line pointer plus the template line in SKILL.md; this cuts token load and fixes progressive disclosure in one change.

Inline the exact commands into Operating rules steps (e.g. git log --since="5 days" -- '*.md' docs/, the jekyll serve + curl verification sequence) instead of leaving them implicit or buried in lessons.

Split each lesson into a bolded one-line rule plus optional detail so durable rules survive while incident-specific narrative (specific bug IDs, session anecdotes) is trimmed.

DimensionReasoningScore

Conciseness

The core sections (Operating rules, Voice & Tone, Writing Constraints) are terse, list-driven, and respect the reader, but the 'Lessons learned' section consumes roughly 40% of the document with dense 40-60 word entries mixing one-off incidents (r2/r3 plugin state, a specific submit_feedback bug, a peer-session anecdote) with durable rules. Mostly efficient overall, but a significant chunk could be tightened or trimmed.

3 / 5

Actionability

The workflow gives executable direction (git over the last 5 days of commits, grep/search into docs/web, HITL gate, apply, verify, run local server with browser validation) and the lessons supply copy-paste commands (bundle exec jekyll serve --detach, curl checks, pkill -f "jekyll serve", git log -S). Not a 5 because the main workflow steps themselves stay high-level ('Use git to query last 5 days' lacks the exact command, 'Run local web server' defers detail to a lesson entry).

4 / 5

Workflow Clarity

Operating rules 0-4 form a clearly sequenced pipeline with an explicit approval checkpoint ('Explicit approval only, Questions are not approval') and verification steps, while the lessons encode validate-then-fix loops (re-check peer work before committing, git status before staging, table-count sanity checks). Not a 5 because the in-workflow validation steps are terse ('Verify') and their substance lives in scattered lesson entries rather than the sequence itself.

4 / 5

Progressive Disclosure

No bundle files exist at all; everything, including a large append-only lessons log, is inlined in one 150-line SKILL.md. The document preaches 'smallest useful document' and 'explicit about where information belongs' yet violates both by keeping the lessons inline instead of a references/ file. Section headers keep it above a 2, but clearly separable content is inlined with no one-level-deep reference structure, capping it at 3.

3 / 5

Total

14

/

20

Passed

Description

50%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, correctly-scoped purpose but does the minimum to do so: one action, no trigger guidance, no synonyms. It reads as a title rather than a trigger-capable description. Adding a 'Use when...' clause and naming the concrete actions (detect changed md files, apply to docs/web, verify rendering) would lift every dimension.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions syncing the website, publishing docs, or after changes to local .md files need to reach docs/web.'

Enumerate the concrete actions the skill performs (find recent changes via git, apply them to docs/web pages, verify with a local Jekyll render) so specificity and completeness rise together.

Include natural synonyms and extensions users would actually say: 'website', 'docs', 'documentation', '.md files', 'docs/web'.

DimensionReasoningScore

Specificity

"To synchronize web site with changes made to local *.md files" names a precise domain and scope but offers only one action ("synchronize"), with no mention of the underlying steps (detecting changed files, applying edits, validating rendering). It matches the anchor for naming a domain with 1-2 concrete actions that fall short of comprehensive coverage.

3 / 5

Completeness

The "what" is clear (synchronize the website with local md changes) but there is no "when" guidance at all. Per the judging guidelines, a missing 'Use when...' clause or equivalent explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords exist ("synchronize", "web site", "*.md files") but natural user phrasings are missing: no "docs", "website", "documentation", "publish", or "sync" variations. Some relevant keywords, but common synonyms are absent.

3 / 5

Distinctiveness Conflict Risk

The niche (website documentation sync) is fairly specific, but the single vague action and absence of distinct trigger phrases leave overlap room with general docs-editing, publishing, or review skills. Somewhat specific, but could still overlap with similar skills.

3 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

griddynamics/rosetta

Path

.claude/skills/sync-web-site/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.