CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paseo-help

Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces through MCP or the CLI.

Quality

90%

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

88%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-engineered troubleshooting skill body: product-specific knowledge only, executable commands, and a clearly sequenced diagnostic workflow with explicit permission and validation gates. The only meaningful improvement is trimming mild repetition and moving per-platform path details into a reference file.

DimensionReasoningScore

Conciseness

The body is dense with product-specific facts Claude cannot know (topology modes, per-OS paths, bundled CLI locations) and avoids explaining generic concepts, but there is mild redundancy — the three topology modes are restated in the "Apply later checks" bullet list, and "Prefer the deployed docs over memory" repeats the earlier fetch-first instruction. This matches anchor 4 (efficient, minor instances that could be trimmed) rather than the perfectly lean anchor 5.

4 / 5

Actionability

Provides copy-paste-ready commands ("paseo daemon status --json", "paseo provider diagnostic <provider> --json", the health-probe URL), exact per-OS log and CLI paths, and concrete UI navigation ("Settings → your host → Overview → Full status"). No time-sensitive version numbers are hardcoded; instructions point to current docs, matching anchor 5.

5 / 5

Workflow Clarity

The diagnostic pipeline is explicitly ordered (fetch llms.txt first → establish topology before diagnosing → diagnose before changing state → escalate with evidence) with validation checkpoints gating each stage (probe the health URL or read daemon.log "only when those values match the affected daemon"; no restarts/config edits without explicit permission; compare resolved binary against a fresh login shell). This matches the anchor 5 pattern of clear sequencing with explicit checkpoints; the destructive/batch cap does not apply since the skill deliberately forbids state changes.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the ~90-line body is well-sectioned with one-level-deep, clearly signaled external references (llms.txt index, troubleshooting page, GitHub/Discord links). It falls short of anchor 5 because inline per-OS path tables and bundled-CLI locations could arguably live in a reference file, keeping the overview leaner — good structure with minor organization gaps (anchor 4).

4 / 5

Total

18

/

20

Passed

Description

87%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 states concrete capability areas, gives explicit natural-language triggers, and actively disambiguates the sibling operational skill. Minor headroom remains in enumerating distinct actions and additional trigger synonyms.

DimensionReasoningScore

Specificity

"Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting" enumerates several concrete capability areas, but a single generic verb ("answer questions") carries them rather than multiple distinct actions. It sits between anchor 4 and 5 — noticeably above the midpoint but short of the comprehensive multi-action example.

4 / 5

Completeness

Explicitly answers both "what" (answer questions about Paseo setup, configuration, connectivity, providers, workspaces, updates, logs, troubleshooting) and "when" with concrete trigger phrases ("Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken"), matching the anchor 5 example structure.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("how Paseo works, how to configure it, or why something is broken") plus solid topic keywords (setup, connectivity, providers, logs, troubleshooting). Coverage is good but a few common variations (e.g., "fix", "error", "not working") are absent, matching anchor 4 rather than the fully comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (questions/help/troubleshooting) and explicitly disambiguates the sibling skill ("use the paseo skill instead to operate agents and workspaces through MCP or the CLI"), minimizing conflict risk. Re-reading anchor 4 confirms this is a better fit for the clear-niche anchor 5.

5 / 5

Total

18

/

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

getpaseo/paseo

Path

skills/paseo-help/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.