CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shortcut

Manage Shortcut stories, epics, objectives, iterations, docs, labels, teams, and more using the short CLI — view, search, update, and create items for project management and issue tracking. Use when the user mentions Shortcut, references tickets or tasks in Shortcut, or when you see URLs matching `app.shortcut.com/*` (use this skill instead of WebFetch).

86

1.88x
Quality

90%

Does it follow best practices?

Impact

81%

1.88x

Average score across 5 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is hefgi/shortcut

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 strong, well-structured CLI skill body: fully actionable routing to exact commands, explicit prerequisite/version checkpoints, and clean one-level-deep progressive disclosure verified against the actual bundle. The only weaknesses are minor redundancy between the routing table, the create note, and the Prerequisites section, plus error responses that lack explicit retry loops.

DimensionReasoningScore

Conciseness

The body is a lean ~85 lines of routing tables and concrete commands with essentially no explanation of concepts Claude already knows, but it has minor trimmable redundancy: the routing table's `create` row is followed by a separate "Create supports stories, epics..." line, and the Prerequisites section partially duplicates the error table's CLI-not-found handling. This fits the level-4 anchor (efficient with minor over-explanation) rather than level 5, where every token would earn its place.

4 / 5

Actionability

Guidance is fully executable throughout: `which short && short --version` with concrete version thresholds, a routing table mapping each argument pattern to an exact command (e.g. `short story <id>`, `short search -t "<text>"`), copy-paste install commands, and an error table with detection strings and specific responses. This matches the anchor for copy-paste-ready commands covering the common cases.

5 / 5

Workflow Clarity

A clear four-step sequence (prerequisites check → parse arguments → present results → handle errors) with explicit checkpoints: the version check branches into three concrete outcomes (install-and-STOP, warn-upgrade, continue), and the error table gives detection conditions and responses. It falls short of level 5 because error responses are one-shot guidance without explicit retry/re-check loops (e.g. after auth fix, resume at step 2), and presentation formatting is described but not validated against actual output. No destructive/batch validation cap applies.

4 / 5

Progressive Disclosure

The body is a well-organized overview that splits detail appropriately: command families live in references/commands.md (verified to exist with matching `## Section` headers for every section cited: Stories, Create, Objectives, Teams, Iterations, Docs, Labels), the API spec in references/shortcut.swagger.json, and both are clearly signaled one level deep in a final reference table with navigation guidance ("use `## Section` headers to find specific command families").

5 / 5

Total

18

/

20

Passed

Description

92%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.

An exemplary description: concrete actions over a comprehensive entity list, explicit and multi-form trigger guidance (mentions, ticket references, URL patterns), and explicit conflict-avoidance direction versus WebFetch. Only minor synonym coverage (story, epic, Clubhouse) is missing from the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — "view, search, update, and create items" — against a comprehensive set of named domain entities ("stories, epics, objectives, iterations, docs, labels, teams"), matching the anchor for comprehensive concrete-action coverage. It does not fit the level-4 anchor because no meaningful capability gaps remain for this domain.

5 / 5

Completeness

Both what ("Manage Shortcut stories... using the short CLI — view, search, update, and create") and when ("Use when the user mentions Shortcut, references tickets or tasks in Shortcut, or when you see URLs matching app.shortcut.com/*") are explicitly and concretely answered, mirroring the level-5 anchor example structure.

5 / 5

Trigger Term Quality

Good natural-keyword coverage: "Shortcut", "tickets", "tasks", and the URL pattern "app.shortcut.com/*" are phrases users would naturally say. It falls short of level 5 because common variations like "story/stories", "epic", or the legacy name "Clubhouse" are absent.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — the Shortcut platform specifically — with distinct, Shortcut-bound triggers (mentions, ticket references, app.shortcut.com URLs) plus explicit conflict guidance ("use this skill instead of WebFetch"), keeping overlap risk with other PM/issue-tracking skills minimal. The generic phrase "project management and issue tracking" is contextual only, not a trigger.

5 / 5

Total

19

/

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

hefgi/dotfiles

Path

.agents/skills/shortcut/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.