CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verify-wake-progress

Check whether Web keeps late progress hidden after observing the published outcome of a Space Wake. Use when changing the Space progress presentation cache, signal projection, or publication matching.

Quality

88%

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

96%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.

Excellent, token-efficient content for a focused verification skill: one executable command, explicit environment prerequisites, specific files and test names for verification, and concrete failure-triage guidance. The only minor gap is the buried, path-less view.mjs reference in the closing sentence.

DimensionReasoningScore

Conciseness

The ~16-line body is lean and dense with domain-specific semantics ("A final reply or notice clears matching progress. Subsequent transient updates and summaries can still arrive.") with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching anchor 5 rather than the minor-trimming anchor 4.

5 / 5

Actionability

The body gives a copy-paste ready command ("node .agents/skills/verify-wake-progress/check.mjs"), explicit prerequisites ("after pnpm install, with Java 11 or newer", "TLC 1.7.4 using WakeProgress.cfg"), and named files and test cases ("PublishedProgressStaysHidden", "FirstPublicationSticks") covering the common case. This matches the fully-executable anchor 5.

5 / 5

Workflow Clarity

For this simple verification skill the single action is unambiguous: install prerequisites, run one command, then triage. Explicit failure feedback loops are present ("If TLC fails, use its event trace to replay the same order at that boundary"), matching anchor 5; the operation is read-only, so no destructive/batch validation cap applies.

5 / 5

Progressive Disclosure

The compact single-file body is well organized with a clear overview, command, model description, and per-file bullets, and references are one level deep (check.mjs given with a full path). However, view.mjs is referenced only in passing ("The state labels in view.mjs describe visible progress and observed publications") without a path, and no bundle files are provided to verify, so it falls just short of the well-signaled-references anchor 5.

4 / 5

Total

19

/

20

Passed

Description

75%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.

A strong description that clearly and explicitly states both what the skill does and when to use it, with a distinctive niche and low conflict risk. Trigger terms are precise but jargon-heavy internal vocabulary lacking natural synonyms, and only one concrete action is named.

Suggestions

Add one or two more concrete actions to the what-clause (e.g., mention that the check runs the Web presentation tests and replays the TLC event trace) to lift specificity beyond a single action.

Broaden trigger terms with more natural phrasings a user would say, such as "late progress", "stale progress rows", or "progress visibility", alongside the current code-area triggers.

DimensionReasoningScore

Specificity

"Check whether Web keeps late progress hidden after observing the published outcome of a Space Wake" names the domain and one concrete action, matching the 1-2-actions-but-not-comprehensive anchor. It does not list several specific actions, so it falls below anchor 4.

3 / 5

Completeness

The description explicitly answers both what ("Check whether Web keeps late progress hidden after observing the published outcome of a Space Wake") and when ("Use when changing the Space progress presentation cache, signal projection, or publication matching") with concrete trigger phrases. This matches the anchor-5 example structure; the when-clause is explicit and specific, exceeding anchor 4.

5 / 5

Trigger Term Quality

Triggers like "Space progress presentation cache, signal projection, or publication matching" are relevant to the domain but rely on internal jargon with no natural synonyms or user-facing phrasings. Some relevant keywords exist, but coverage of natural terms is missing, matching anchor 3 rather than 4.

3 / 5

Distinctiveness Conflict Risk

The "Space Wake" progress-visibility niche is highly distinctive with trigger terms tied to specific code areas, so conflict with other skills is minimal. It clearly matches the clear-niche anchor 5 rather than the minor-overlap anchor 4.

5 / 5

Total

16

/

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

amplifthq/opentag

Path

.agents/skills/verify-wake-progress/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.