CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paseo

Paseo reference for managing projects, workspaces, workspace scripts, agents, schedules, and heartbeats.

Quality

79%

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 ./.claude/skills/paseo/SKILL.md

The canonical home for this skill is paseo in phatblat/dotfiles

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a strong reference skill: every tool is documented with concrete parameters, the CLI surface is executable as written, and behavioral guidance (profiles, waiting, steering defaults) is specific and unambiguous. Its main weaknesses are minor duplication (fast_mode, notifyOnFinish) and a fully inlined structure that could offload the CLI/discovery detail to reference files.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no explanations of MCP, worktrees, cron, or provider/model concepts), but the Codex fast_mode instruction appears three times ("pass settings: { features: { \"fast_mode\": true } }"" in create_agent, update_agent, and inspect_provider sections) and notifyOnFinish guidance repeats across the Agents and Waiting sections, so minor trimming is possible.

4 / 5

Actionability

Guidance is fully executable: copy-paste-ready CLI blocks with exact flags, required/optional parameter lists for every MCP tool, literal settings payloads, and a concrete profile-materialization procedure ("combine provider and model as the provider/model value", "copy featureValues to settings.features"); specific examples cover the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

As a reference skill it has no single sequential procedure, but its embedded workflows are clearly sequenced with explicit defaults and fallbacks (profile selection: call list_profiles, read notes, materialize, fall back to provider discovery and tell the user; waiting: leave notifyOnFinish on, move on, don't poll). It lacks the explicit validation checkpoints of the 5 anchor, though no destructive or batch workflow requires them.

4 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers, clearly signaled tool references, and an explicit cross-skill pointer to paseo-help, with no nested reference chains. It sits at the 4 anchor rather than 5 because ~130 lines of inlined reference material (CLI flag surface, provider discovery details) leave minor organization gaps with no content split into reference files, and the under-50-line exception does not apply.

4 / 5

Total

17

/

20

Passed

Description

66%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 clearly names the product and its six capability areas and is unlikely to be confused with unrelated skills, but it lacks any explicit "when to use" trigger clause and leans on one generic verb. Adding a Use-when clause with natural trigger phrases would raise both completeness and trigger quality.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user mentions Paseo, or asks to create workspaces, launch or steer agents, run workspace scripts, or set up cron schedules/heartbeats.'

Replace the generic 'managing' with distinct action verbs per area (e.g. 'creates and archives workspaces, launches and steers agents, starts workspace scripts, sets up cron schedules and heartbeats').

Include natural trigger synonyms users would actually say, such as 'cron', 'background agent', 'worktree', 'daemon', or 'MCP tools'.

DimensionReasoningScore

Specificity

The description enumerates six concrete capability areas ("projects, workspaces, workspace scripts, agents, schedules, and heartbeats") anchored to a named product, but relies on the single generic verb "managing" rather than distinct action verbs, so it sits between the 3 anchor (1-2 concrete actions) and the 4 anchor (several specific actions).

4 / 5

Completeness

The "what" is clear (a Paseo reference for managing the six listed entity types), but there is no "Use when..." clause or equivalent explicit trigger guidance, only a weak implication that it applies when Paseo is involved; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like "workspaces", "agents", "schedules", and "heartbeats" match what users would say, plus the distinctive product name "Paseo"; common variations such as "cron", "daemon", "background agents", "terminals", or "MCP" are missing, which keeps it below the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The product name "Paseo" gives it a clear niche with minimal wrong-skill risk, but broadly applicable nouns like "agents", "schedules", and "projects" create minor overlap with other agent-orchestration skills, matching the 4 anchor rather than the 5 anchor's fully distinct triggers.

4 / 5

Total

15

/

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

phatblat/dotfiles

Path

.claude/skills/paseo/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.