CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-fast

Execute a trivial task inline — no subagents, no planning overhead

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./pi/package-skills/gsd-fast/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 lean, operational shim: explicit dispatch semantics with fail-closed error handling, a crisp boundary against gsd-quick, and a clearly signaled single workflow reference. All guidance is concrete and appropriately terse, with only minor redundancy in the dispatch rules.

DimensionReasoningScore

Conciseness

The body is dense and operational — dispatch semantics, fail-closed rules, and a read-first instruction with no concept explanations or padding. It falls just short of anchor 5 because fail-closed behavior is restated ("STOP that step and surface the error... stop the run. Never execute the role's work inline") and could be tightened slightly.

4 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: "call `gsd_dispatch` with `role` (the installed role name) and `task` (the full task text)", an explicit Agent(...) to role/prompt mapping, and explicit failure handling ("If `gsd_dispatch` reports the role unresolved or the child failed, STOP"). It misses anchor 5 only because `<process>` is the bare "Execute end-to-end." with the real steps deferred to the external workflow file.

4 / 5

Workflow Clarity

A clear sequence is present — read `<execution_context>` files "Before doing anything else", then follow the workflow — with explicit fail-closed checkpoints and recovery paths ("offer to skip it and continue; if it is required, stop the run"). It is not anchor 5 because validation of the task's outcome itself is delegated to the un-included workflow file rather than stated here.

4 / 5

Progressive Disclosure

The body is under 50 lines, cleanly sectioned (<objective>, <execution_context>, <process>), and contains exactly one clearly-signaled, one-level-deep reference (@__GSD_PI_ENGINE_ROOT__/gsd-core/workflows/fast.md) with an explicit instruction to read it. No bundle files exist to nest, so this matches the well-organized simple-skill case at anchor 5.

5 / 5

Total

17

/

20

Passed

Description

37%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 communicates the skill's core distinction — direct inline execution without subagent or planning overhead — but is thin on specifics. It names no concrete task types and omits any explicit "use when" trigger guidance, leaving applicability to be inferred from the word "trivial".

Suggestions

Add an explicit "Use when..." clause with concrete triggers, e.g., "Use when the user asks for a typo fix, a small config change, a tiny refactor, or a forgotten commit."

Name 2-3 concrete task types in the description itself (e.g., "Fix typos, tweak configs, make small refactors, commit forgotten changes") instead of the generic "trivial task".

Include natural user phrasings and synonyms such as "quick fix", "small change", "one-line edit", or "fast task" so the description matches what users actually type.

DimensionReasoningScore

Specificity

"Execute a trivial task inline" names the domain but offers only the generic action "execute" — no concrete task types (typo fixes, config changes, etc.) appear in the description, matching the anchor for minimal/generic actions rather than 1-2 concrete ones.

2 / 5

Completeness

A clear "what" is present ("Execute a trivial task inline — no subagents, no planning overhead") but there is no "Use when..." clause or equivalent trigger guidance; the "when" is only weakly implied by "trivial", which caps this at the clear-what/missing-when anchor.

3 / 5

Trigger Term Quality

The available keywords ("trivial task", "inline", "no subagents", "planning overhead") are workflow jargon rather than phrases users naturally say; natural terms like "quick fix" or "small change" are missing, matching the one-or-two-generic-keywords anchor.

2 / 5

Distinctiveness Conflict Risk

"no subagents, no planning overhead" carves out a niche against planning-heavy skills, but "trivial task" is broad and could overlap with any lightweight sibling skill (e.g., gsd-quick), matching the somewhat-specific-but-overlapping anchor.

3 / 5

Total

10

/

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

open-gsd/gsd-core

Path

pi/package-skills/gsd-fast/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.