CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-config

Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile

Quality

70%

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-config/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured dispatch skill with genuinely executable commands and strong fail-closed error handling for the inline path. Its main weaknesses are redundant routing descriptions across three sections and heavy reliance on external workflow files for the primary configuration paths.

Suggestions

State the flag routing once (the <routing> table) and have <objective> and <context> reference it instead of restating it.

Move the generic Pi dispatch boilerplate to a shared reference file and keep only the GSD-specific dispatch notes inline.

Spell out what "Preserve all workflow gates from the target workflow" concretely requires, or point to where those gates are defined.

DimensionReasoningScore

Conciseness

The body is mostly lean, but the flag-routing logic is stated three times (in <objective>, the <routing> table, and <context>), and lines like "The text inside <arguments> is exactly what the user typed" spend tokens on conventions that could be tightened.

3 / 5

Actionability

Guidance is largely executable — "command -v gsd-tools", the install hint string, "gsd-tools query config-set-model-profile <profile-name> --raw", and concrete gsd_dispatch role/task parameters — but the default/--advanced/--integrations paths only delegate to external workflows without showing any of their steps.

4 / 5

Workflow Clarity

The sequence (parse flag → load workflow or run inline command → preserve gates) is clear with explicit checkpoints: a PATH pre-check that stops with an install hint, and fail-closed dispatch handling that stops on unresolved roles or child failure with optional-vs-required escalation. It falls short of 5 because the primary config paths inherit their validation from the external workflows rather than defining feedback loops here.

4 / 5

Progressive Disclosure

The three workflow references are one level deep and clearly signaled in a dedicated <execution_context> block with an instruction to read them first, and sections are well organized. Minor gaps come from the duplicated routing content inlined in three sections and the Pi dispatch boilerplate that a shared reference could carry.

4 / 5

Total

15

/

20

Passed

Description

58%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 has a clear, specific "what" anchored to a named tool, but it omits any "when to use" guidance and lacks natural trigger variations. It sits above average on specificity and distinctiveness while being weakest on trigger-term coverage and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to configure or change GSD settings, toggle workflow options, or switch model profiles."

Replace the vague "advanced knobs" with the concrete setting names the advanced mode actually exposes (planning tuning, timeouts, branch templates).

Include natural user phrasings and synonyms ("GSD config", "set profile", "turn on verifier") so the skill triggers on how users actually ask for it.

DimensionReasoningScore

Specificity

The description lists several concrete configuration areas — "workflow toggles, advanced knobs, integrations, and model profile" — which goes beyond naming the domain with 1-2 actions, but "advanced knobs" is generic and coverage of what each area involves is not comprehensive.

4 / 5

Completeness

The "what" is clear (configure GSD settings across four named areas), but the "when" is entirely missing — there is no "Use when..." clause or equivalent explicit trigger guidance, which caps this dimension at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Terms like "GSD settings", "model profile", and "integrations" are ones a user might naturally say, but the description provides no synonyms, natural trigger variations, or command-style phrases (e.g. "configure GSD", "switch model profile") that users would type.

3 / 5

Distinctiveness Conflict Risk

The scope is tied to a specific named tool (GSD) and its settings, making it mostly distinct with minimal overlap risk; however, the absence of distinct trigger phrases leaves minor overlap risk with other gsd-* skills a user might invoke for configuration tasks.

4 / 5

Total

14

/

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-config/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.