CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-polish

Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-polish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-engineered orchestration layer: a tight overview with explicit done-criteria, boundaries, and clearly signaled one-level-deep references that were verified to exist and to declare their own ownership. Weaknesses are minor: the step-1 disclosure run-on sentence hurts readability, and in-body verification checkpoints are thin because validation is delegated to the referenced files.

DimensionReasoningScore

Conciseness

The body is lean: no explanations of concepts Claude already knows, and nearly every sentence encodes a rule, ownership boundary, or done-criterion. It falls short of anchor 5 mainly because step 1's disclosure is a single ~130-word run-on sentence that packs the live-mode privacy and setup details into hard-to-parse prose that could be structured or tightened.

4 / 5

Actionability

Guidance is concrete for an orchestration skill: named files with declared ownership ("read references/live-start.md; it owns preconditions, install, the endpoint, and the URL handoff"), a named action for closing ("invoke ce-commit"), and an explicit ordering rule ("Ask once, before any server starts"). Not a 5 because step 4 remains high-level ("inspect only as needed, edit the in-scope surface") and all executable detail is delegated rather than illustrated, leaving minor gaps in the body itself.

4 / 5

Workflow Clarity

The numbered Run sequence with an explicit traditional/live branch, a stated Done contract, boundaries, and a close-out that reports commits, the server URL, and residual blockers matches anchor 4's "clear sequence with most checkpoints present". It is not a 5 because verification of applied fixes is conditional (only when the user asks or a browser capability exists) and reachability/validation gates live in delegated files rather than explicit checkpoints in the body.

4 / 5

Progressive Disclosure

The body is a clear overview that names each reference and states what it owns; all cited files (references/run.md, references/live-start.md, references/live-loop.md) exist in the bundle, and the body maps the full routing chain (live-start "routes to references/live-loop.md") so no hop is undiscoverable. Heavy content (the 33 KB live-stream contract, per-framework dev-server recipes, install steps) is appropriately split into separate files, and navigation is easy — matching the anchor-5 pattern.

5 / 5

Total

17

/

20

Passed

Description

62%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 cleanly answers both what the skill does and when to use it, in third person and without fluff, and it carves a recognizable niche. Its main limitation is breadth: one action statement and a single general trigger condition, with few natural synonyms a user would actually say. (Note: the skill sets disable-model-invocation: true, so trigger breadth matters less in practice, but the rubric scores what is written.)

Suggestions

Enumerate the concrete capabilities in the what-clause, e.g. "Polish a working feature: collect the user's live observations in the browser, apply focused UX fixes, and commit them locally".

Broaden the when-clause with concrete trigger phrases users would naturally say, e.g. "Use when the user asks to polish, tweak, or refine the UX of a feature that already works".

Mention the two feedback modes (typed observations vs. live voice/draw-on-page) in the description so the skill's distinctive capability is visible up front.

DimensionReasoningScore

Specificity

"Polish a working feature through user-directed live browser feedback" names the domain (working feature, UX refinement, browser feedback) but delivers only one concrete action rather than a list of specific capabilities. It matches anchor 3 ("1-2 concrete actions, but not comprehensive") better than anchor 4, which expects several specific actions enumerated.

3 / 5

Completeness

Both parts are explicit: the what ("Polish a working feature through user-directed live browser feedback") and the when ("Use when a functional feature needs focused UX refinement before shipping"). It is not a 5 because the when-clause is a single general condition rather than concrete trigger phrases a user would say (compare the anchor-5 example's "when the user mentions PDFs, forms, or document extraction").

4 / 5

Trigger Term Quality

Natural phrases like "polish", "working feature", "UX refinement", and "before shipping" are present, but common user variations ("tweak the UI", "clean up the design", "make it look better") are missing. This sits at anchor 3 ("some relevant keywords but missing common variations or synonyms"), below anchor 4's "good keyword coverage".

3 / 5

Distinctiveness Conflict Risk

"Polish a working feature ... focused UX refinement before shipping" carves a clear niche (pre-ship UX polish of an already-working feature) with only minor overlap risk against general code-review or refactoring skills. Not a 5 because the trigger wording lacks distinctive phrases that fully separate it from adjacent dev-loop skills.

4 / 5

Total

14

/

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

EveryInc/compound-engineering-plugin

Path

skills/ce-polish/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.